Sort by:
Sunday
25 Aug 2019
09:00 - 18:00
EU-China
1st EU-China Health Summit on Medical Innovation and Collaborative Technology Transfer
Blueprint for a joint mission in Aging
Upon pre-registration
Room: Tête d'or 1
Chairman 1: Catherine Chronaki | Chairman 2: Zhi Yang
Sunday
25 Aug 2019
09:00 - 18:00
IAHSI
Academy General Assembly
Room: Tête d'or 2
Chairman 1: Reinhold Haux
Sunday
25 Aug 2019
09:00 - 18:00
IMIA board
IMIA board meeting
Room: Salon Tête d'or
Chairman 1: Christoph Lehmann
Sunday
25 Aug 2019
08:50 - 16:10
211 Public Health
Advancing the Health and Wellness for Populations: A Review of Public Health, Population Health, and Global Health Informatics
Room: Gratte Ciel 3
Chairman 1: Brian E Dixon
08:50 - 16:10
Advancing the Health and Wellness for Populations: A Review of Public Health, Population Health, and Global Health Informatics (Brian E Dixon, Hadi Kharrazi, Jamie Pina, Christopher Harle, Suranga Kasthurirathne)
In this tutorial, attendees will review the current and emerging trends in three related, yet distinct, disciplines within the field of biomedical informatics. Public health or epidemiology informatics seeks to apply informatics to support communication, surveillance, information, and learning systems relevant to public health. Population health informatics seeks to implement evidence-based solutions to improve the health of populations. Global health informatics seeks to apply informatics to health care and population health outcomes in low-and-middle income countries. The tutorial examines the state-of-the-art in each discipline and discusses trends shaping the future research agenda in each area. Attendees will also discuss how these disciplines “fit” together to facilitate improvements in population health outcomes.
Mr. Professor Brian E Dixon
Indiana University Richard M. Fairbanks School of Public Health
Monday
26 Aug 2019
16:40 - 18:00
70 Qual Care
Supporting Quality of Care by Co-Creation in the International Nursing Informatics Community
Room: Gratte ciel SP
Chairman 1: Inge Madsen
16:40 - 18:00
Supporting Quality of Care by Co-Creation in the International Nursing Informatics Community (Inge Madsen, Greg Alexander, Laura-Maria Peltonen, Judy Murphy)
With the current rapid technological advancements in the health sector, the need for a more focused and international approach to support Nursing Informatics (NI) has emerged. Previous research has identified four themes that need acknowledgement to advance NI in the next decade, including education; research; practice; and collaboration. Building on Donabedian’s framework (1988), this workshop aims to strengthen collaboration between actors and to share knowledge and wisdom between actors in the NI community by adressing these themes. The main goal of the workshop is to explore how the international NI community can better support NI in practice. The outcomes of the workshop may be used to guide the strategic planning of NI organisations globally, regionally and locally.
Ms. ass. professor Inge Madsen associated professor
VIA Faculty of Health Sciences.
Sunday
25 Aug 2019
08:50 - 12:45
791 Blockchain
Innovations in Digital Health: Standards, Profiles, and Blockchain
Room: Gratte Ciel 2
Chairman 1: Philip Christian Zuniga
08:50 - 12:00
Innovations in Digital Health: Standards, Profiles, and Blockchain (Philip Christian Zuniga, Raymond Francis Sarmiento, Ada Angeli Cariaga, Marie Jo-anne Mendoza, Rose Ann Zuniga)
The workshop proposal on ‘Innovations in Digital Health: Standards, Profiles, and Blockchain’ aims to create an open space for health informatics practitioners to learn about emerging technologies in digital health.

This will also serve as an avenue for them to participate in the ongoing discourse on leveraging digital health, specifically the use of standards and interoperability, as a tool to promote better health outcomes.

The workshop objectives are to (1) explain the concept of standards, profiles, and blockchain in the realm of healthcare; (2) demonstrate knowledge on standards, profiles, and blockchain by participating in each topic’s corresponding activity; and (3) evaluate the application of standards, profiles, and blockchain in healthcare in an open forum set-up.

Facilitated by the team members of Standards and Interoperability Lab – Asia (SIL-Asia), the workshop will cover topics on Fast Healthcare Interoperability Resources (FHIR), Integrating the Healthcare Enterprise (IHE), and the application of blockchain in healthcare.
Ms. Kristin Chloe Pascual
Standards and Interoperability Lab - Asia
Sunday
25 Aug 2019
13:00 - 14:20
709 Certification
IMIA Certification in Ethics: Are We Ready?
Room: Gratte Ciel 2
Chairman 1: Paulette Lacroix
13:00 - 14:20
IMIA Certification in Ethics: Are We Ready? (Paulette Lacroix, Eike-Henner W Kluge, Pekka Ruotsalainen, Najeeb Al-Shorbaji)
The focus of this workshop is to introduce the proposed international ethically grounded certification program for health informatics professionals, including data scientists.  The recently revised International Medical Informatics Association (IMIA) Code of Ethics for Health Information Professionals, based on the Universal Declaration of Human Rights, encompasses fundamental human rights and provides a set of derivative principles and rules specific to health informaticians, potentially serving as the basis of a globally valid ethics-based certification programt that would be administered and maintained by IMIA as a collaborative initiative with the World Health Organization (WHO). IMIA, a non-government organization (NGO), has official relationship status with the WHO and in 2013 developed the WHO and IMIA Industry Stakeholder Consultation on Data Reuse.  In this workshop the discussion will highlight issues with the processing of health data in today’s world of Big Data, and identify where current privacy legislation falls short.  There is also concern that the current research ethics paradigm does not fully address these issues. The need for ethics becomes positively pressing as electronic health/medical/patient records related services are outsourced to information technology providers who are not themselves engaged in the delivery of healthcare but merely providean informatics service, such as the rising use of global radiology services, and because the framework of fiduciary obligation that binds healthcare providers does not exist in their case. This workshop provides an opportunity for participants to examine and discuss the elements of the proposed certification program, identify potential areas of concern and offer recommendations.
Ms. Paulette Lacroix Senior Privacy Consultant and Principal
PC Lacroix Consulting Inc.
Monday
26 Aug 2019
08:30 - 11:50
991 NLP
Developing Natural Language Processing Solutions to Facilitate Clinical and Translational Research
Room: Bellecour 2
Chairman 1: Hua Xu
08:30 - 11:50
Developing Natural Language Processing Solutions to Facilitate Clinical and Translational Research (Hua Xu, Hongfang Liu)
Natural language processing (NLP) technologies, which can unlock information embedded in clinical narratives, have received great attentions in the medical domain. Many NLP methods and systems have been developed in the medical domain. However, there is still a lack of best practices for building successful NLP solutions in the medical domain. In this 3-hour tutorial, we would like to introduce methods, tools, and best practices on building NLP solutions for clinical and translational research. We will start with an introduction of basic NLP concepts and available tools, and then focus on important applications of NLP in the medical domain such as phenotyping. We plan to use lectures, demonstrations and hands-on exercises to cover the basic knowledge/tools and use case studies to illustrate important trade-offs in the design and implementation of clinical NLP applications. Each instructor has over 10 years of experience in clinical NLP research and application and they will share their recommendations in building successful NLP applications in clinical research.
Mr. Hua Xu
University of Texas Health Science Center at Houston
Ms. Professor Hongfang Liu
Mayo Clinic
Monday
26 Aug 2019
13:00 - 16:10
255 Res Data Coll
Introduction to Research Data Collection with REDCap: Perspectives from France, the United States, and Beyond
Room: Bellecour 2
Chairman 1: Stephany Duda
13:00 - 16:10
Introduction to Research Data Collection with REDCap: Perspectives from France, the United States, and Beyond (Stephany Duda, Hugo Potier, Marie Sanchez, Paul Harris)
REDCap is an electronic data capture solution designed for health research and operations. We propose a half-day tutorial introducing potential users to the core features of REDCap, including electronic form and survey design, single- and multi-site study tracking, user management, mobile data collection, and data quality monitoring. We will also present an overview of advanced features such as REDCap plugins, electronic health record integration, and the support resources provided by the global REDCap Consortium. Our instructors include French and US REDCap experts: Paul Harris (USA, professor of biomedical informatics and creator of REDCap), Marie Sanchez (France, senior data manager), Hugo Potier (France, health informatics director), and Stephany Duda (USA, associate professor of biomedical informatics).
Ms. Dr. Stephany Duda
Vanderbilt University
Monday
26 Aug 2019
08:30 - 11:50
131 LOINC
Introduction to LOINC, the global vocabulary for tests, measurements, and observations in healthcare
Room: Bellecour 3
Chairman 1: Daniel J. Vreeman
08:30 - 11:50
Introduction to LOINC, the global vocabulary for tests, measurements, and observations in healthcare (Daniel J. Vreeman)
LOINC® is a freely available international standard for identifying laboratory and other clinical observations. LOINC is now ubiquitous in health data systems worldwide, and is essential ingredient of system interoperability. This tutorial will give participants a thorough and practical introduction to LOINC. This tutorial will present an overview of LOINC and its use around the world, discuss the LOINC concept model and data structures, and share practical tips for implementing LOINC.
Mr. Dr. Daniel J. Vreeman
Indiana University School of Medicine
Monday
26 Aug 2019
08:30 - 16:10
124 Pred Analit
Advanced Methods for Predictive Analytics
Room: Salon Tête d'or
Chairman 1: Glen Martin
08:30 - 16:10
Advanced Methods for Predictive Analytics (Glen Martin, Niels Peek)
Clinical prediction models (CPMs) are becoming abound in the statistical, medical and informatics literature, owing to their many practical uses. While advances in methods and analytical techniques provide opportunities to develop, validate and implement CPMs in health data, keeping up-to-date with research in this field can be challenging. This tutorial aims to support researchers and practitioners who are involved with or interested in using statistical and/or machine learning methods for predictive analytics. The tutorial will cover ‘best practices’ in CPM research, discussing common statistical and machine learning methods that can be used for predictive analytics (e.g. what do these models mean and how can we use them?). Finally, we will cover novel and advanced techniques that could support predictive modelling in electronic health records. The tutorial aims to be accessible and engaging, with attendee participation encourage throughout both the lectures and in hands-on exercises.
Mr. Dr. Glen Martin
University of Manchester
Mr. Prof. Niels Peek
THe University of Manchester
Monday
26 Aug 2019
08:30 - 16:10
447 life cycle
Hands-On Full Life Cycle Data Science Tutorial
Room: Gratte Ciel 3
Chairman 1: Lisiane Pruinelli
08:30 - 16:10
Hands-On Full Life Cycle Data Science Tutorial (Lisiane Pruinelli, Tamara Winden, Steve Johnson)
The United States National Institutes for Health (NIH) supports multiple initiatives for data driven discovery and for workforce development in data science. Many healthcare leaders lack a broad understanding of the concepts and resources available to conduct real-world analytic projects. The goal of this tutorial is to give leaders a foundation for understanding data science principles and tools. This is a hands-on tutorial where participants will learn and actively participate in all phases of a data science project in order for them to have a better overall understanding and to improve collaboration with data science staff at their own organization, inter-organization, including international projects. They will undertake a data science project using Jupyter notebooks focusing on data preparation, exploratory data analysis and building a machine learning model using the Python scikit-learn toolset. The tutorial will conclude with a discussion of how the model can be implemented within the clinical practice for clinical decision-making.
Ms. Dr. Lisiane Pruinelli
University of Minnesota
Monday
26 Aug 2019
08:30 - 16:10
1134 FHIR
Clinicians on FHIR
Room: Gratte ciel SP
08:30 - 16:10
Clinicians on FHIR (Laura Heermann Langford, Russell Leftwich, Viet Nguyen, James McClay)
HL7 created Fast Healthcare Interoperability Resources (FHIR®) as a next generation standard to address clinical data interoperability. Clinicians on FHIR evolved in 2014 as an event held at each HL7 Working Group Meeting (3 times yearly) to educate clinicians about HL7 FHIR® and provide feedback to the HL7 FHIR® team regarding the clinical viability and usability of the FHIR® standard. This MedInfo 2019 Tutorial will bring the Clinicians on FHIR® activity to a broader clinical audience attending MedInfo 2019. The tutorial is designed to educate attendees about HL7 FHIR® and tools available to access, review, and provide feedback to the HL7 FHIR team regarding the evolving HL7 FHIR® standard. It is also intended to make the audience aware of the potential of FHIR® for innovation in their organizations.
Ms. Dr. Laura Heermann Langford
Intermountain Healthcare
Mr. Dr. Russell Leftwich Senior Clinical Advisor, Interoperability
InterSystems
Senior Clinical Advisor for Interoperability, Intersystems Corporation. Adjunct Assistant Professor, Biomedical Informatics, Vanderbilt University. Previously practicing physician holding boards in Internal Medicine and Clinical Informatics. Active in US standards development community around clinical domains in HL7 CDA and HL7 FHIR. Founder and co-chair of HL7 Learning Health Systems Work Group and co-chair HL7 Clinical Interoperability Council.
Mr. Viet Nguyen
Stratametrics
Mr. Dr. James McClay M.D.
University of Nebraska Medical Center
Monday
26 Aug 2019
13:00 - 16:10
776 openEHR
openEHR clinical modelling 101
Room: Gratte Ciel 1
Chairman 1: Heather Leslie
13:00 - 16:10
openEHR clinical modelling 101 (Heather Leslie, John Tore Valand, Silje Ljosland Bakke, Vebjørn Arntzen)
Clinical modelling of data sets using the openEHR two level approach of archetypes and templates allows clinicians, informaticians and implementers to develop detailed data specifications that cater for clinical, professional, cultural and regulatory variance using standardised atomic data patterns, known as archetypes.

In this tutorial, four of the most experienced openEHR clinical modelling experts will be available to support participants to build their first openEHR template to represent a practical clinical data set, learning how to aggregate, constrain and configure archetypes to support data capture in a real-life clinical scenario.
Ms. Dr Heather Leslie
Atomica Informatics
Monday
26 Aug 2019
08:30 - 18:00
China
China symposium
Room: Tête d'or 1
Monday
26 Aug 2019
08:30 - 18:00
IMIA GA
IMIA General Assembly
Room: Tête d'or 2
Chairman 1: Christoph Lehmann
Monday
26 Aug 2019
08:30 - 11:50
Fr Session
French Session
Room: Gratte Ciel 1
Chairman 1: Pierre Zweigenbaum
Monday
26 Aug 2019
08:30 - 11:50
313 Snomed
SNOMED CT and Healthcare Terminologies: Ontologies in Support of Global Interoperation of the Electronic Health Record
Room: Auditorium
Chairman 1: James Campbell
08:30 - 11:50
SNOMED CT and Healthcare Terminologies: Ontologies in Support of Global Interoperation of the Electronic Health Record (James Campbell, Olivier Bodenreider, Daniel Karlsson, Kin Wah Fung, Dion McMurtrie)
This three hour hands-on workshop will explore in detail major portions of the SNOMED CT concept model,1,2 and present practical use cases for application of SNOMED CT ontologies in the interoperation of electronic health record(EHR) data globally. The workshop will employ the ontology authoring platform Protégé®2 and workshop participants should bring their own computers loaded with Protégé,3,4 in order to participate fully. However, observers are also welcome and workshop slide sets and reference materials will be published. Workshop leaders will distribute access to an OWL release of SNOMED CT prior to MEDINFO supplemented by extension development from Australia, UK, US and Sweden that will provide the web ontology platform for workshop exercises. Description logic queries for use and evaluation by workshop participants will be published prior to the conference along with the OWL ontologies. The concept model for <<404684003|Clinical finding (finding)| will be presented and discussed. Use cases for ontological query of problem list data across national borders in support of clinical care, research and epidemiology will be presented and discussed. Workshop participants will explore description logic queries employing the SNOMED CT concept model in response to the use cases and tailor the exercises to reflect their home country application environments. Interoperation of SNOMED CT clinical data with the International Classification of Diseases be discussed and demonstrated using SNOMED CT knowledge-based map sets. Core data elements comprizing the HL7 CDA record summary will be discussed as time permits, including Problem list and Procedure history. Recent ontology developments in the SNOMED CT concept model for <<363787002|Observable entity (observable entity)| developed in cooperation with the Regenstrief Institute5 and European colleagues will be presented. Use cases for interoperation of laboratory, pathology and molecular pathology (genomic) data will be presented and discussed in detail. Intensional value sets of observables codes for quality reporting and research will be demonstrated using the concept model to inform the construction of ontological queries of data sets. Specific examples of interoperable exchange of laboratory results between US (LOINC6), UK (SNOMED CT), European counties(International Union for Pure and Applied Chemistry, Nomenclature for Properties and Units7) will be explored by attendees supported by workshop leaders. Recent elaborations of the SNOMED CT concept model for <<373873005|Pharmaceutical / biological product (product)| and <<105590001|Substance (substance)| will be presented and demonstrated interactively to workshop attendees who will explore the SNOMED CT medications ontologies in order to answer the questions posed by a series of workshop scenarios. Practical use cases for interoperation of medication data in clinical medicine and research will be explored connecting the Australian Medicines Terminology8, RxNorm8 and international medication classifications such as the Anatomical Therapeutic Chemical Classification9.
Mr. Dr. James Campbell Professor of Internal Medicine
University of Nebraska Medical Center
Monday
26 Aug 2019
13:00 - 16:10
539 Open source
Free/Libre/Open Source Software and Open Data Workshop for Open Science.
Room: Auditorium
Chairman 1: Shinji Kobayashi
13:00 - 16:10
Free/Libre/Open Source Software and Open Data Workshop for Open Science. (Shinji Kobayashi, Terry Hannan, Seong K Mun, Luis Falcon, Chris Paton, Alvin Marcelo, Hamish Fraser, Chansaly Phommavong, Jørn Braa, Lutfan Lazuardi)
Free/Libre/Open Source Software(FLOSS) has been widely adopted in digital health and contributing to universal health coverage for low and middle income countries. There are active open source development community, such as OSEHRA, OpenMRS, GNU Health, DHIS2, OpenIMIS, and other products all over the world.

Open data movement is also showing its feasibility for healthcare, and open science is a vital part of current activity of machine learning based artificial intelligence research.

On the other hand, new regulation in developed countries for clinical software might be discouraging FLOSS implementation of digital imaging software.

In this workshop, we will review the current status of FLOSS and related works, and discuss about the future of FLOSS utilization for digital health.
Mr. Shinji Kobayashi
Monday
26 Aug 2019
16:40 - 18:00
1102 FHIR FAIR
FHIR for FAIR: Advancing interoperability for health data
Room: Bellecour 1
Chairman 1: Carlos Luis Parra Calderón
16:40 - 18:00
FHIR for FAIR: Advancing interoperability for health data (Catherine Chronaki, Giorgio Cangioli, Anne Moen, Carlos Luis Parra Calderón)
Findable, Accessible, Interoperable and Reusable, or the FAIR data principles aim to guide scientific data management and stewardship and are relevant to all stakeholders in the digital ecosystem. The objective of the FAIR4Health project is to facilitate and encourage the research community to FAIRify, that is share and reuse datasets derived from publicly funded research initiatives. Such actions will demonstrate the potential impact that the FAIR strategy will have on health outcomes and health research.
Taking the FAIR4Health project as a starting point, this workshop will engage the audience to reflect on ways that HL7 FHIR standards can support the FAIRification process providing input to policy, standards, and research.
Ms. Catherine Chronaki
HL7 Foundation
Mr. Giorgio Cangioli
Ms. Prof. Dr. Anne Moen RN, PhD
University of Oslo, Oslo, Norway
Mr. Carlos Luis Parra Calderón
Monday
26 Aug 2019
08:30 - 11:50
311 Connect Health
Interdisciplinary Perspectives on Connected Health Research: Facilitators and Barriers for Sustainable Platform Development
Room: Bellecour 1
08:30 - 11:50
Interdisciplinary Perspectives on Connected Health Research: Facilitators and Barriers for Sustainable Platform Development (Pauline Whelan, Charlotte Stockton-Powdrell, Lex van Velsen, Monique Tabak, Klaus-Hendrik Wolf)
Connected Health tools, including mobile apps, wearable devices, smart sensors and other forms of smart and ubiquitous computing have the potential to revolutionise many aspects of healthcare design and delivery [1,2,3]. This workshop will bring together leading international Connected Health researchers, with clinicians, health informaticians, information systems experts, engineers, industry partners and others working in the field of Connected Health research. Through the workshop we will discuss the barriers and facilitators for Connected Health platforms. The workshop will be a collaborative environment to nurture and support the development of interdisciplinary Connected Health research projects where shared interests are identified and new research ideas are generated among delegates. The workshop will involve a series of facilitated discussions around the following key areas: a) clinical applications of Connected Health platforms b) design, implementation and the evaluation lifecycle c) sustainable and interoperable architectures for Connected Health d) building for sustainability in Connected Health research. Concerns about health inequalities in the affordability and accessibility of Connected Health devices and platforms will be outlined in the introduction to frame the discussions.
Ms. Pauline Whelan
University of Manchester
Mrs. Charlotte Stockton-Powdrell
University of Manchester
Monday
26 Aug 2019
13:00 - 16:10
546 IT workforce
Identifying and developing the health information workforce: A Knowledge Cafe conversation
Room: Bellecour 1
Chairman 1: Karen Day
13:00 - 16:10
Identifying and developing the health information workforce: A Knowledge Cafe conversation (Karen Day, Kathleen Gray, Rebecca Grainger, Kerryn Butler-Henderson)
The capacity for digital health is influenced by the availability and deployment of health information professionals. These professionals have varied backgrounds ranging from computer to clinical and business sciences, may belong to one of several and diverse professional associations, and therefore are often invisible. We propose a framework for building workforce capacity to improve health services performance. This workshop will host a Knowledge Café, whereby faciliated conversations in small groups about workforce capacity building for future digital health will explore the tough questions in health informatics workforce development. These conversations will be thematically analysed by the workshop facilitators (authors) and reported in a peer reviewed journal.
Ms. Dr. Karen Day
The University of Auckland
Monday
26 Aug 2019
13:00 - 14:20
1049 HL7
HL7 International Patient Summary: Can it Support Children with Complex Care Needs?
Room: Gratte Ciel 2
Chairman 1: Michael Rigby
13:00 - 14:20
HL7 International Patient Summary: Can it Support Children with Complex Care Needs? (Maria Brenner, Catherine Chronaki, Péter Altorjai, Elena Petelos, Rianne Oostenbrink, Michael Rigby)
International Patient Summary (IPS) work has been driven by the need to promote use of health data in emergency or unplanned care. However, these efforts have not yet addressed children and in particular, children with complex care needs.

This workshop will explore the care plan component of the IPS for young children with complex care needs. Moreover, it will explore connections of the IPS care plan to consent and autonomy as the means of connecting the family with the health team in a child-centred manner, focusing on the specific situation of transfer of care.
Ms. Catherine Chronaki
HL7 Foundation
Mr. Dr. Péter Altorjai
EAP: European Academy of Paediatrics, Primary - Secondary care working group, chair of primary care
Graduated in 2000 at Semmelweis Medical University, Budapest. Spent 6 years at hospital based secondary paediatric care setting, and primary care paediatrician since 2008. Member of the management board of both Hungarian Paediatric Society and the Association of Hungarian Primary Care Paediatricians. Invited speaker and chair in international paediatric conferences since 2011, also participated in many national (TÁMOP, EFOP, ...) and EU (MOCHA, COST) projects. Recently elected to the chair position of primary care at the Primary Secondary Care permanent working group of the European Academy of Paediatrics.
Ms. Elena Petelos
University of Crete
Ms. Rianne Oostenbrink
Erasmus University
Mr. Michael Rigby
Imperial College London
Monday
26 Aug 2019
16:40 - 18:00
141 Telehealth
Telehealth Integrated into the Electronic Health Record Benefits and Barriers
Room: Bellecour 2
16:40 - 18:00
TELEHEALTH INTEGRATED INTO THE ELECTRONIC HEALTH RECORD; BENEFITS AND BARRIERS (Lynn Johnson, Mark Genuis)
This workshop discusses the power of telehealth when it is located within the electronic health record. It then seeks input from the participants on the benefits and barriers.
Ms. Professor Lynn Johnson
University of Michigan
Mr. Dr. Mark Genuis President
ICE Health Systems
Monday
26 Aug 2019
13:00 - 16:10
941 FAIR Health
FAIR Health Data Sharing Initiatives in Europe: Opportunities and Challenges for international cooperation
Room: Bellecour 3
Chairman 1: Ulli Prokosch
13:00 - 16:10
FAIR Health Data Sharing Initiatives in Europe: Opportunities and Challenges for international cooperation (Ulli Prokosch, Thomas Ganslandt, Ulrich Sax, Christian Lovis, Carlos Luis Parra Calderón, Peter R Rijnbeek, Nigel Hughes, Wiro Niessen, Barend Mons, Kees Van Bochove)
In the data-driven age of medical research many initiatives and projects focus on data linkage and functional integration as well as data reuse. Providing “FAIR data” is a common challenge for all of them. For this workshop leaders of six nation-wide and European initiatives/projects have joined in order to identify the major concepts, challenges and hurdles.
In discussions with the audience they search for opportunities to strenghten all those approaches by joining workforces and aligning concepts.
Mr. Prof. Dr. Ulli Prokosch
Monday
26 Aug 2019
16:40 - 18:00
971 ICD-11
ICD-11
Room: Bellecour 3
16:40 - 18:00
ICD-11 (Robert Jakob, Angelika Haendel, Miroslav Zvolský, Mervat Abdelhak)
This workshop will be highly interactive and participatory. An overview of ICD-11, its structure, content and timeline will be presented. Technical issues pertaining to ICD-11 implementation will also be discussed and compared to lessons learned from ICD-10. Preliminary research results will be presented regarding the education of clinical coders from a global perspective. Participants will be engaged in the discussion as to when ICD-11 will be implemented in their countries and for what purpose. In addition participants will have an opportunity to discuss issues of concern and their countries readiness for ICD-11 implementation.
Ms. Angelika Haendel M.A.
University Hospital Erlangen
Angelika Haendel, MA, B.Sc. DRG Controlling at the University Hospital of Erlangen, Germany. Responsibilities include Clinical Documentation, DRG Controlling, Quality Management, and Integrated Care. Immediate past president of the International Federation of Health Information Management Associations (IFHIMA), board member of the German Association of Medical Documentation and Health Information Management (DVMD), co-chair of the EFMI working group HIME.
Mr. Robert Jakob
World Health Organization, Department of Health Statistics and Information Systems, Switzerland
Mr. Miroslav Zvolský
Institute of Health Information and Statistics of the Czech Republic
Ms. Dr. Mervat Abdelhak
CAHIIM and University of Pittsburgh
Monday
26 Aug 2019
16:40 - 18:00
421 Health Indic
Global digital health indicators
Room: Salon Tête d'or
Chairman 1: Caroline Perrin
16:40 - 18:00
Global digital health indicators (Caroline Perrin, Diana Zandi, Antoine Geissbuhler, Amy Sy)
The World Health Organization's Global Observatory for eHealth (GOe)  has been monitoring the landscape of eHealth – its evolution and impact to strengthen and promote the use of information and communication technologies (ICTs) in health. The Observatory has conducted four global surveys to date  on eHealth/digital health to report on the national, regional, and global progress in the adoption  of the foundations for eHealth/digital health . For over a decade the Observatory has provided timely, high-quality evidence and information to support national governments and international bodies in improving policy, practice and management of eHealth. It has been recognized that measuring and reporting on the use of digital technologies to improvehealth outcomes is an area that needs close monitoring and regular updates to better respond to the changing needs of Member States. Therefore current indicators are being reviewed for alignment with a new indicator framework through which the high-level policy goals outlined in WHO resolutions on eHealth and digital health (WHA58.28, WHA66.24,WHA 71.7)  are translated into operational objectives. This indicator framework is being developed through a Delphi consensus method. The aim of the IMIA workshop is to to present and discuss the proposed indicators with the IMIA community, and to receive input for refinement of the framework before the indicators are tested
Ms. Caroline Perrin
Monday
26 Aug 2019
16:40 - 18:00
494 Nursing
Visualizing Data Patterns of Interest to Nursing
Room: Gratte Ciel 1
Chairman 1: Bonnie Westra
16:40 - 18:00
Visualizing Data Patterns of Interest to Nursing (Deborah Ariosto, Karen Monsen, Bonnie Westra, Lynda Hardy)
Workshop Summary

Clinicians generate and interpret vast amounts of data that beg for simple yet powerful tools and methods to provide insight into care problems. Data visualization is a method of understanding the significance of data by placing it in a visual context. This new context often deepens the meaning and urgency for patient care and/or practice change.

Historical approaches to data analyses produced tables and static charts. Sophisticated modeling and what-if scenarios required specialists with advanced skills. With advances in mainstream visualization products, interactive, iterative examination of complex data is much simpler and more fun.
Nurse leaders and analysts who support them can benefit from the ability to visualize data and explore patterns in service delivery. We can track data points that are local to a patient or facility or globally to populations or disease. Data visualization is pushing healthcare forward by increasing the ability for data sharing in new ways.

This workshop will provide an overview of the data visualization design principles, demonstrate exemplars in clinical practice as well as facilitate hands on activity to explore and visualize clinical data sets.
Ms. Dr. Deborah Ariosto PhD, MSN, RN-BC
Vanderbilt University Medical Center
Ms. Deborah Ariosto
Vanderbilt University Medical Center
Ms. Dr. Karen Monsen
Ms. Bonnie Westra
University of Minnesota, School of Nursing
Ms. Dr. Lynda Hardy
The Ohio State University
Dr. Hardy is the Director of Data Science and Discovery at The Ohio State University. Dr. Hardy places extended efforts on a multidisciplinary approach to education and implementation of informatics and data science to actively inform methods of improving access to comprehensive, quality, cost-effective health care services and achieve health equity for all Americans. Dr. Hardy’s current focus also includes a multidisciplinary approach to patient outcomes through data science and visualization with a special focus on clinical and analytical approaches to opioid use.
Monday
26 Aug 2019
08:30 - 09:50
278 Patient Gen Data
The Wave of Patient Generated Health Data: Implications for Health Systems
Room: Gratte Ciel 2
Chairman 1: Daniel Capurro
08:30 - 09:50
The Wave of Patient Generated Health Data: Implications for Health Systems (Daniel Capurro, Anne Turner, George Demiris)
Patient generated health data (PGHD) presents the promise of improving patient engagement in their own care, collecting health information outside of clinical encounters which can provide insights into hard to understand phenomena such as adherence and health behavior. In parallel, several challenges emerge from the use of PGHD. Some examples include une-qual access to sensors and health literacy, from the patients’ perspective, as well as its incorporation to clinical records, its visualization, and analysis, from the providers’ perspec-tive. This session will cover emerging PGHD issues such as assessing patient information needs, visualization of PGHD data and implications for clinical care.Patient generated health data (PGHD) presents the promise of improving patient engagement in their own care, collecting health information outside of clinical encounters which can provide insights into hard to understand phenomena such as adherence and health behavior. In parallel, several challenges emerge from the use of PGHD. Some examples include unequal access to sensors and health literacy, from the patients’ perspective, as well as its incorporation to clinical records, its visualization, and analysis, from the providers’ perspective. This session will cover emerging PGHD issues such as assessing patient information needs, visualization of PGHD data and implications for clinical care.
Patient generated health data (PGHD) presents the promise of improving patient engagement in their own care, collecting health information outside of clinical encounters which can provide insights into hard to understand phenomena such as adherence and health behavior. In parallel, several challenges emerge from the use of PGHD. Some examples include unequal access to sensors and health literacy, from the patients’ perspective, as well as its incorporation to clinical records, its visualization, and analysis, from the providers’ perspective. This session will cover emerging PGHD issues such as assessing patient information needs, visualization of PGHD data and implications for clinical care.
Mr. Dr. Daniel Capurro MD, PhD
Pontificia Universidad Catolica de Chile
Ms. Dr. Anne Turner Professor
University of Washington
Mr. Dr. George Demiris
University of Pennsylvania
Monday
26 Aug 2019
10:20 - 11:50
846 Pat voice
The Patients’ Voice: Standards at work for Patient Reported Outcomes
Room: Gratte Ciel 2
Chairman 1: Catherine Chronaki
10:20 - 11:50
The Patients’ Voice: Standards at work for Patient Reported Outcomes (Catherine Chronaki, Morten Bruun-Rasmussen, Martin Ingvar, Pascal Coorevits, Karen Marie Lyng, Sanne Jensen, Anne Moen)
Active patient engagement in care and treatment is fostered by systematically including the patient perspective at all levels.. Taking account of patient generating data and collecting Patient Reported Outcomes (PRO) is promising to facilitate engagement. However, achieving intended impact requires a framework that places the patient at the center, linking the individual’s health needs and desired health outcomes to the health and care team and an information model that cuts through layers of the learning health system (primary, secondary, specialty care). This workshop brings together three interdependent, but interelated components: a) robust Health Informatics Infrastructure based on international standards, b) Data Exchange and Quality, and c) Content – Questionnaires. We will present case studies from Denmark, Sweden, and Norway in the context of global standardization efforts in HL7 (FHIR and CDA) and standard sets in the International consortium for health outcome measures (ICHOM).
Ms. Catherine Chronaki
HL7 Foundation
Mr. Director Morten Bruun-Rasmussen
MEDIQ
Mr. Martin Ingvar
Karolinska University
Mr. Pascal Coorevits
I~HD
Mrs. Dr Karen Marie Lyng
The Danish Health Data Authority
Mrs. Sanne Jensen
Danish Health Data Authority
Ms. Prof. Dr. Anne Moen RN, PhD
University of Oslo, Oslo, Norway
Thursday
29 Aug 2019
14:10 - 15:30
759 IMIA Update Comp
IMIA recommendations on education in biomedical and health informatics – An update of competences in regard to professional roles in an international context
Room: Bellecour 2
Chairman 1: Sabine Koch
14:10 - 15:30
IMIA recommendations on education in biomedical and health informatics – An update of competences in regard to professional roles in an international context (Sabine Koch, Najeeb Al-Shorbaji, Vajira Dissanayake, Andre Kushniruk, Mark Merolli, Kaija Saranto, Marcelo Silva, Graham Wright)
Biomedical and health informatics (BMHI) education exists internationally since many years. The International Medical Informatics Association (IMIA) has twice published recommendations on education in BMHI. The last revision is now more than eight years old and in the light of a rapidly changing field, there is a need to adapt the recommendations to current expectations from teachers, students and tentative employers in the different IMIA regions. An IMIA taskforce for the next revision of the IMIA recommendations had been appointed in 2017 and workshops were held at Medinfo 2017 and MIE 2018. The aim of this workshop is to capture broad opinions and perspectives from a variety of stakeholders from different IMIA regions. We will first present the current state of the IMIA recommendations on BMHI education, followed by small group work and a plenary discussion.  The results of these discussions will serve as input to the next revision of the recommendations.
 
Ms. Prof. Sabine Koch PhD
Karolinska Institutet
Mr. Mark Merolli
The University of Melbourne
Ms. Professor Kaija Saranto PhD, RN, FACMI, FAAN
University of Eastern Finland
Mr. Professor Graham Wright
Rhodes University
Professor Graham Wright is a chartered information systems practitioner with a clinical and managerial background.
Sunday
25 Aug 2019
14:50 - 16:10
79 Prof Growth
Students and Emerging Professionals in Nursing and Health Informatics: Identifying Opportunities for Professional Growth and Networking
Room: Gratte Ciel 2
Chairman 1: Laura-Maria Peltonen
14:50 - 16:10
Students and Emerging Professionals in Nursing and Health Informatics: Identifying Opportunities for Professional Growth and Networking (Laura-Maria Peltonen, Raji Nibber, Erika Lozada Perezmitre, Maxim Topaz, Lisiane Pruinelli)
Building international networks within nursing and health informatics takes time and effort. International collaboration is of utter importance to advance nursing and health informatics globally. The International Medical Informatics Association - Nursing Informatics Special Interest Group - Student and Emerging Professionals (IMIA NI SIG SEP) group offers integration with the international informatics community. This workshop organized by the IMIA NI SIG SEP aims to explore collaboration opportunities, existing challenges and questions related to nursing and health informatics in clinical and academic settings. The workshop will engage the audience in a discussion around issues from a global perspective with a particular focus on needs of students and emerging professionals. The expected outcomes of this workshop include: 1) networking opportunities for students and emerging professionals, 2) identifying possibilities for international collaboration in education, practice and research, and 3) understanding the principles of strategic action for the nursing and health informatics community.
Mrs. Dr Laura-Maria Peltonen
Monday
26 Aug 2019
16:40 - 18:00
775 EMR Child
How can we deliver the vision of electronic medical records to improve maternal and child healthcare in low- and middle-income countries?
Room: Gratte Ciel 2
Chairman 1: Taiwo Adedeji
16:40 - 18:00
How can we deliver the vision of electronic medical records to improve maternal and child healthcare in low- and middle-income countries? (Taiwo Adedeji, Philip Scott, Hamish Fraser)
Maternal and child health are major priorities in low- and middle-income countries (LMICs). Electronic medical records (EMR) are widely perceived to be an important element of a coherent policy and programme approach to improving healthcare services in both developed and developing countries. Nigeria is an example of a low- and middle-income nation that has great ambitions for digital health strategy but so far only minimal implementation. This workshop will explore barriers and opportunities for moving forward vital improvements in healthcare delivery and outcomes and how modern information technology can support this. The presentations will describe the strategic building blocks for building an electronic healthcare information infrastructure and draw upon recent experience in Africa and elsewhere. Participants will be invited to debate key questions around priorities, learning from success and failure in developed nations, pre-conditions for success and sustainability.
Mr. Mr Taiwo Adedeji
University of Portsmouth
Mr. Dr Philip Scott PhD
University of Portsmouth
Monday
26 Aug 2019
14:50 - 16:10
1002 CDSS
Discovering and Contributing to International Standards Development for Clinical Decision Support
Room: Gratte Ciel 2
Chairman 1: Robert Jenders
14:50 - 16:10
Discovering and Contributing to International Standards Development for Clinical Decision Support (Robert Jenders, Klaus-Peter Adlassnig, Peter Haug)
Health Level Seven International (HL7) is the principal international health information technology standards development organization (SDO).  Among its standards are those for clinical decision support (CDS), including Arden Syntax, Infobutton and the Clinical Quality Language (CQL) standards.  Continuing improvement of these standards and ongoing development of future decision support standards require wide participation in order to maximize their success.

Accordingly, the purpose of the workshop is twofold.  First, the instructors, who are active members of the CDS work group of HL7, will convey the latest developments regarding existing CDS standards and efforts to develop new standards, including case examples of practical implementations.  Second, they will solicit feedback so that attendees who do not participate in SDOs such as HL7 and the Object Management Group (OMG) can have input via the instructors into the standards activities of these organizations while placing them in the context of other SDOs and harmonization efforts.
Mr. Prof. Robert Jenders
Charles Drew University University of California, Los Angeles
Mr. Dr. Peter Haug MD
Intermountain Healthcare and the University of Utah
Monday
26 Aug 2019
18:30 - 19:30
Open ceremony
Opening ceremony
Room: Auditorium
Chairman 1: Patrick Weber
Monday
26 Aug 2019
19:30 - 20:30
J-M Bourez
European Vision of Medical Informatics: the role of the European Institute of Innovation and Technology
Directeur Général EIT Health France. Investment committee member TTO Lutech .EIF – EIT Health European Venture Center of Excellence Leader

After studying medicine in Lille and marketing in a business school in Paris, Jean Marc Bourez has experienced different positions in pharma industry since 1992, Commercial Operations,  Medical Affairs, Strategic Marketing, Business Excellence, Business Development Strategy and Open Innovation. Former head of eHealth & Open Innovation process at Sanofi, he has been appointed as CEO of EIT Health France, a Knowledge Innovation Community supported by European Institute of Technology, a body of the European Union. In this position, Jean-marc is leading a collaborative project with the European Investment Fund to develop a pan-European Platform of co-investment in Life sciences. Jean-Marc is also Chairman and co-founder of a MedTech Company founded in 2017.
The European perspective
The European Union is currently working to encourage more effective use of information and communications technology, in particular for delivery of health services, including disease prevention and health promotion, and has various initiatives and strategies in place. The European Commission has allocated €2 billions under the Horizon 2020 program for research and innovation in Big Data under the call ‘Personalising Health and Care’ and has since April 2018 a supportive policy for digital transformation of health and care with a strong focus on Big Data.
The role of EIT Health
In recognition of the considerable challenges across Europe but also the immense opportunities in this sector, ‘The use of existing Big Data to improve healthcare’ was selected as a topic for the EIT Health Think Tank for 2018. The task was to evaluate the current position in Europe, identify barriers, recommend strategies to overcome them, and propose actionable projects and activities to make the best use of Big Data at a regional and European level for the benefit of citizens. 3 axes have been prioritized to develop concrete achievements: 1. Identifying and harnessing the benefits of available data, 2. Building capacities/capabilities to realize benefits, 3. Community engagement and participation
Room: Auditorium
Chairman 1: Philippe Cinquin
Monday
26 Aug 2019
20:30 - 21:30
Welcome cocktail
Welcome cocktail
Tuesday
27 Aug 2019
08:10 - 09:50
T2-01
Evaluation of decision support systems 1
Room: Bellecour 1
Chairman 1: Yasushi Matsumura
08:10 - 08:30
Performance Evaluation of Clinical Decision Support Systems (CDSS): Developing a Business Intelligence (BI) Dashboard (Vania Teixeira, Analía Mori, Andrés Usera, Juan Carlos Bacigalupo, Daniel Luna)
This document describes the development of a Business Intelligence (BI) dashboard for tracking the drug-drug interaction (DDI) alerts implemented as Clinical Decision Support Systems (CDSS) in Electronic Health Records (EHR). CDSS are known for their potential to reduce medical error. The use of requirements in the development of BI dashboards is crucial to obtain successful software. In this work, the requirements were analysed using a score methodology, considering the relevance of the indicators and visualization methods. CDSS effectiveness and acceptance have been questioned, so, it is fundamental to monitor their behaviour and performance. The dashboard was designed in order to satisfy the needed indicators. Using BI as a tool for monitoring the CDSS performance made it possible to operationalize the EHR content repository, maximizing the understanding in relation to the override and, by inference, to optimize the CDSS system by opening new lines of work.
Ms. PhD Vania Teixeira
08:30 - 08:50
Evaluation of a web-based clinical decision and workflow support tool for cirrhosis (Jennifer Garvin, Julie Ducom, Michael Matheny, Anne Miller, Dax Westerman, Carrie Reale, Jason Slagle, Natalie Kelly, Russ Beebe, Jejo Koola, Erik Groessl, Emily Patterson, Matt Weinger, Samuel Ho)
Abstract We used formative evaluation to refine a decision and workflow support tool for liver cirrhosis with clinicians. We conducted semi-structured interviews using a prototype and clinical scenarios. Clinician recommendations were incorporated into the tool. Clinicians found the tool useful. A future study will assess the impact in clinical practice. Keywords: clinical decision support; human factors engineering; liver cirrhosis; interview Introduction Gaps exist in delivering evidence-based care for patients with chronic liver disease and cirrhosis when compared to evidence based guidelines [1]. We designed and evaluated the CirrODS (Cirrhosis Order set and clinical Decision Support) tool with clinicians to improve clinical decision-making and workflow for liver cirrhosis [2,3,4]. Methods Clinicians participated in several rounds of formative evaluation using prototypes with subsequent redesign of CirrODS. Physicians (n=20) at three hospitals used clinical scenarios based on patients with cirrhosis and the workflow support tool. The admission orders made with and without the CirrODS tool were compared. Physician participants also described their experience using CirrODS and provided recommendations, which were coded into categories and themes and used to make modifications. We evaluated the clinical content, safety, and usability of CirrODS using both qualitative and quantitative methods. Results We created an interactive CirrODS prototype that presents relevant patient data and recommendations for evidence-based tests and treatments to be ordered. Physicians viewed the tool positively and suggested that it would be most useful at the time of admission. CirrODS was perceived to serve clinical needs especially for less experienced providers. Interviews also suggest that it is likely important to include functionality so that individual users can tailor the timing of the use of the tool to their individual workflow preferences. Discussion We iteratively evaluated and revised CirrODS with clinicians to improve the use of evidence-based treatment of cirrhotic patients during routine hospital practice by non-specialists. The results gathered during evaluation were promising, and end users expressed interest and appreciation for CirrODS. Overall, the tool maintained good usability while facilitating the ordering of a higher percentage of high-priority measures compared with those ordered without the tool. We also demonstrated the usefulness of formative evaluation based on user-centered design to develop EHR-based CDS tools. Conclusions Using a formative approach with clinicians we evaluated and refined an innovative clinical decision-making and workflow support tool to facilitate the adoption of evidence for patients with cirrhosis. A future study will assess the impact on quality of care for patients with cirrhosis in clinical practice. Acknowledgements The views expressed in this article are those of the authors and do not necessarily reflect the position or policy of the Department of Veterans Affairs or the United States government or our academic affiliates. We thank the inter-view participants for their valuable contributions. This work was supported by VA Health Services Research and Development (HSR&D) grant IIR 13-052 and CIN 13-416.
Ms. Jennifer Garvin
The Ohio State University, The University of Utah, The US Department of Veterans Affairs
Dr. Garvin is currently the Division Director and Associate Professor in the Health Information Management and Systems Division in the School of Health and Rehabilitation Sciences. She develops applied informatics tools and methods to advance clinical and public health practice. She is currently a VA Research Health Scientist and an Affiliated Investigator with Center for Health Information and Communication at the Richard L. Roudebush VAMC, Indianapolis, IN. In terms of clinical practice, she and her team develop natural language processing tools to improve care for chronic systolic heart failure in the Department of Veterans Affairs (VA). Through several VA Health Services Research and Development grants she developed the Congestive Heart Failure Information Extraction Framework (CHIEF) which she used to automate heart failure quality measurement and she has extended the design to provide data for a decision support clinical reminder for titration of beta blocker therapy in primary care. As part of this research she also studies the contextual factors related to implementation of CHIEF using the Promoting Action on Research Implementation in Health Services framework, the Sociotechnical Model for Health Information Technology (HIT) Model, and User-centered Design to guide the research. These approaches allow her to study how to use HIT to facilitate the adoption of evidence into clinical practice, to partner with clinicians and other stakeholders in development, and to design and deliver clinical content so that it supports decision making.
08:50 - 09:10
Leveraging health information technology to measure and improve opioid prescribing (Jessica Ancker, Yuhua Bao, Danni Wu, Sarah Nosal, J Travis Gossey)
Introduction: The opioid epidemic has reached crisis proportions in the United States, with the rate of overdose deaths currently exceeding that of traffic deaths. Physicians themselves have inadvertently contributed to the problem by prescribing more than the minimum required to control pain. Quality improvement initiatives and targeted continuing education often produce only modest changes in physician prescribing behavior, and traditional clinical decision support is often ignored. Instead, we have shown that redesigning an eprescribing interface to reduce the number of clicks needed to perform a recommended action (while also increasing the number of clicks needed to select a non-recommended action) made an immediate and lasting improvement in prescribing practices. We applied similar insights to redesign our eprescribing interface. The objectives of the current project were to use our electronic prescribing system to (a) conduct a retrospective study of opioid prescribing quantities during a series of local and state-level quality improvement initiatives intended to reduce opioid prescribing, and (b) implement and assess the electronic intervention to encourage prescribers to reduce the quantity prescribed for new opioid prescriptions.
Methods: The Weill Cornell Physician Organization is the multi-specialty faculty practice of the Weill Cornell Medical College in New York City, representing both private practices serving commercially insured patients and hospital-based clinics that accept Medicaid (public insurance for low-income Americans). The Institute for Family Health is a NYC-based community health center that serves all patients regardless of their insurance status. Both institutions use the Epic EHR. (a) Prescriptions of short-acting opioids by providers in the Weill Cornell internal medicine department were retrieved from the EHR database from 2016 through 2017. A first prescription of an opioid was defined as a prescription for a patient who had no recorded opioid prescriptions in the previous 12 months. (b) The EHR redesign intervention was implemented at Weill Cornell in March 2018 and at the Institute for Family Health in June 2018.
Results: The proportion of new opioid prescriptions complying with recommended 3-day supply rose modestly throughout 2016 and 2017, coinciding with initiatives that included hospital-based education about opioid risks, New York State Department of Health letters to high-volume opioid prescribers, and hospital quality improvement meetings with local high-volume prescribers. Numbers of new opioid prescriptions also declined slightly. The post-intervention data collection will be completed in December 2018 (9 months of post-intervention data for Weill Cornell and 6 months for the Institute for Family Health).
Conclusions: A two-year series of state and local quality improvement and educational initiatives was accompanied by a modest reduction in the quantity of pills dispensed to opioid-naive patients. Nevertheless, as of late 2017, less than 20% of new opioid prescriptions met the CDC recommendations of 3 days’ supply or less. This retrospective study is consistent with previous literature showing the difficulty of changing prescribing behavior through persuasion and supports the need for our human factors/behavioral economics intervention to reduce risky prescribing. The completed analyses showing the effects of the intervention will be available in summer 2019.
Ms. Dr. Jessica Ancker
09:10 - 09:30
Using Analytics to Prospectively Improve Quality of Clinical Decision Support (Michael Leu, Tokunbo Akande, Livingston Martin, Nikita Pozdeyev, Reza Sadeghian)
Introduction Seattle Children’s Hospital has a robust means for creating evidence-based clinical pathways consisting of clinical algorithms, decision support, and reports. Order sets are built in a systematic way [1], so that they are more usable and require less cognitive load to use than ad hoc created order sets [2].  In November, 2015, we had a 10 day improvement retreat in Japan to streamline our creation of these pathways.  The result of the retreat was that we should define population definitions earlier, then use analytic reports to inform the creation/update of pathways, to try and reduce cycles of rework (e.g. to reduce errors of omission).  Subsequently, we piloted this new method of creating decision support on several pathways, with the distinct multidisciplinary teams that managed these pathways. Methods The teams would evaluate existing clinical decision support, and prototype decision support for these clinical pathways, then use results of orders analysis for patients with the specified diagnosis to determine whether orders were used at the expected time in the workflow, the origin of these orders, and to determine if orders should be added to the decision support. Results In using this approach on several different pathways, different benefits were observed.  Selected findings included:
Kawasaki Disease pathway:  We found that these patients were written for nonsteroidal anti-inflammatory agents (NSAIDs) such as ibuprofen, sometimes even after the diagnosis was made – so the algorithm and decision support were updated to alert providers not to give NSAIDs while on aspirin.  We also found that while IVIG and aspirin were in the Admission order set, these were rarely ordered as the diagnosis was often made later.  As a result, these medications were moved to a separate order set to increase their use within decision support. Tracheostomy pathway:  We found that the respiratory therapists were ordering a “clinician respiratory communication” order that variably described characteristics of patient tracheostomy tubes.  For safety, we created a new order that contained all standard tracheostomy tube details, as well as back up tube manufacturer, model, and size. Intussusception pathway:  We found that the preliminary imaging studies for this diagnosis were ordered from the “ED Abdominal Pain” order set and not the “ED Intussusception” order set.  Making changes to the pathway in “pre-diagnosis” decision support allowed us to achieve good compliance with the new recommendation to diagnose by ultrasound. Discussion and Conclusions It is a relatively new to use analytical tools to prospectively inform the construction of new clinical decision support.  Our pilot studies suggest that this method allows better understanding of provider ordering workflows in ways that support effective ordering, support creating tools to target patient safety concerns, and help to determine ordering patterns that may represent common errors which can be specifically targeted by educational efforts.  These efforts have had the additional benefit of allowing incorporation of these changes into the decision support specifications prior to analyst build, presumably resulting in reduced rework and provision of higher quality decision support at the time of initial go live.
Mr. Michael Leu
University of Washington
09:30 - 09:50
A Generic Rapid Evaluation Support Tool (GREST) for clinical and commissioning decisions (Jack Dowie, Vije Rajput, Mette Kjer Kaltoft)
A fast and frugalgeneric tool can provide decision support to those making decisions about individual cases, particularly clinicians and clinical commissioners operating within the budget and time constraints of their practices. The multi-national Generic Rapid Evaluation Support Tool (GREST)is a standard preference-sensitive Multi-Criteria Decision Analysis-based tool, but innovatory insofar as anequity criterion is introduced as one of six. Equity impact reflects the number of population QALYs lost or gained in moving from Old (current intervention) to New (contemplated intervention). In the exemplar UK implementation Claxton’s NHS Willingness to Pay per QALY is the numeraire. Any weight from 0 to 100% may be assigned to the equity criterion but its presence affirms that it is persons-as-citizens who experience any opportunity harms or benefits arising from actions within the health service commons. A fully-operational but demonstration-only version is available  on open access, as proof of concept and method.
Mr. Prof. Jack Dowie Professor Emeritus of Health Impact Analysis
London School of Hygiene and Tropical Medicine
Tuesday
27 Aug 2019
14:10 - 15:30
T2-16
Clinical decision support 1
Room: Bellecour 1
14:10 - 14:30
Scoring Patient Fall Reports Using Quality Rubric and Machine Learning (Melanie Klock, Hong Kang, Yang Gong)
Patient falls, a subcategory of patient safety events, cause further harm and anxiety to patients in healthcare systems. Patient fall reports are a valuable resource to identify safety issues that demand further attention. Still, the main challenge for patient fall reports is the lack of quality and detail in writing. A method of evaluating patient fall reports would help us better understand the root causes of falls and prevent their recurrence to improve patient safety. Employing the Agency for Healthcare and Quality rubric for assessing the quality of fall reports, we compared three different machine-learning models and identified the most effective method for scoring fall reports using AHRQ’s rubric. The results of this study are intended to be applicable in healthcare facilities to score reports during reporting for reporters to improve report quality. The ultimate goal is to increase learning from fall reports for better prevention of patient falls.
Mr. Prof. Yang Gong Associate Professor
University of Texas Health Science Center at Houston
Professor Yang Gong, MD, PhD is a principle investigator on patient safety and clinical decision support.
Ms. Melanie Klock
University of Texas at Austin
14:30 - 14:50
Using Machine Learning on Home Health Care Assessments to Predict Fall Risk (Yancy Lo, Selah Lynch, Ryan Urbanowicz, Randal Olson, Ashley Ritter, Christina Whitehouse, Melissa O\'Connor, Susan Keim, Margaret McDonald, Jason Moore, Kathryn Bowles)
Falls are the leading cause of injuries among older adults, particularly in the more vulnerable home health care (HHC) population. Existing standardized fall risk assessments often require supplemental data collection and tend to have low specificity. We applied a random forest algorithm on readily available HHC data from the mandated Outcomes and Assessment Information Set (OASIS) with over 100 items from 59,006 HHC patients to identify factors that predict and quantify fall risks. Our ultimate goal is to build clinical decision support for fall prevention. Our model achieves higher precision and balanced accuracy than the commonly used multifactorial Missouri Alliance for Home Care fall risk assessment. This is the first known attempt to determine fall risk factors from the extensive OASIS data from a large sample. Our quantitative prediction of fall risks can aid clinical discussions of risk factors and prevention strategies for lowering fall incidence.
Ms. Yancy Lo
Institute for Biomedical Informatics, University of Pennsylvania
14:50 - 15:10
Generation of personalized decision trees from electronic health records (Elisa Salvi, Lucia Sacchi, Fred Godtliebsen, Torje Henriksen, Kassaye Yigzaw, Meskerem Hailemichael, Joseph Hurley, Silvana Quaglini, Johan Bellika)
To optimize care for a specific patient, physicians often rely on decision models. Among the available types of models, decision trees (DTs) are one of the most commonly-used. Building a DT to formalize a specific clinical decision problem is time-consuming, since it requires collecting and processing all the medical evidence that is relevant for that clinical domain. Thus, DTs are usually built once, considering a generic patient population and may not be targeted to the specific patient’s characteristics (e.g., sex, age, clinical history). In addition, as any decision model, maintaining a DT up-to-date to the latest clinical evidence is also challenging and time-consuming.
In this work, we aim at taking a first step towards the automatic generation of personalized DTs from the evidence collected into electronic health records (EHRs). The proposed method is both knowledge-based and data-driven.
To provide a proof of concept, we applied our method on one EHR system, to build a DT for the selection of treatment for patients affected by chronic pain. Although we are far from being able to apply this method in clinical practice, this is the first step towards the automatic generation of up-to-date, personalized models for supporting clinical decision making.
Mrs. Elisa Salvi
University of Pavia
15:10 - 15:30
A decision support system for pathology test result reviews in an emergency department to support patient safety and increase efficiency (Anthony Nguyen, Hamed Hassanzadeh, Yushi Zhang, John O'Dwyer, David Conlan, Michael Lawley, Jim Steel, Kylynn Loi, Peter Rizzo)
The review of pathology test results for missed diagnoses in Emergency Departments is time-consuming, laborious, and can be inaccurate. An automated solution, with text mining and clinical terminology semantic capabilities, was developed to provide clinical decision support. The system focused on the review of microbiology test results that contained information on culture strains and their antibiotic sensitivities, both of which can have significant impact to ongoing patient safety and clinical care. The system was highly effective at identifying abnormal test results, reducing the number of test results for review by 92%. Furthermore, the system reconciled antibiotic sensitivities with documented antibiotic prescriptions in discharge summaries to identify patient follow-ups with a 91% F-measure – allowing for the accurate prioritisation of cases for review. The system dramatically increases accuracy, efficiency, and supports patient safety by ensuring important diagnoses are recognised and correct antibiotics are prescribed.
Mr. Dr. Anthony Nguyen
Commonwealth Scientific and Industrial Research Organisation (CSIRO)
Wednesday
28 Aug 2019
08:10 - 09:50
T2-04
Clinical decision support 2
Room: Bellecour 1
Chairman 1: Ulli Prokosch
08:10 - 08:30
Effects of Computerised Guideline-Oriented Clinical Decision Support System on Antithrombotic Therapy in Patients With Atrial Fibrillation: A Systematic Review and Meta-Analysis (Ryota Sakurai, Kazuhiko Ohe)
A systematic review and meta-analysis was conducted to investigate the effects of computerised guideline-oriented clinical decision support system (CDSS) on antithrombotic therapy in patients with atrial fibrillation. PubMed, the Cochrane Library, and Web of Science were queried. Four studies were included in this meta-analysis. The proportion of appropriate antithrombotic therapy in accordance with clinical guidelines was significantly higher in the CDSS group than in the control group (risk ratio (RR): 1.03, 95% confidence interval (CI): 1.01 to 1.04, P = 0.004). Although the incidence of thromboembolic events was similar between the 2 groups (RR: 1.12, 95% CI: 0.88 to 1.42, P = 0.357), the incidence of major bleeding tended to be lower in the CDSS group compared with the control group (RR: 0.79, 95% CI: 0.61 to 1.01, P = 0.063). Computerised guideline-oriented CDSS may be effective for appropriate antithrombotic therapy as compared with control in patients with atrial fibrillation.
Mr. Ryota Sakurai
08:30 - 08:50
Decision Support tools for drugs prescription process in a Hospital in Argentina (Valeria Zapico, Luciana Rubin, Soledad Diaz, Maria Laura Gambarte, Romina Rebrij, Carlos Otero, Daniel Luna)
While medications can improve the health of patients, the prescription process is complex and prone to errors.
The structured medical order entry systems (CPOE) with clinical decision support (CDS) are increasingly implemented to improve patient safety, however the organizations that decide to implement them will have several challenges: understanding which classes of CDS can admit their systems, ensure that clinical knowledge is adequate and design tools for proper monitoring.
We share our experience of over ten years of development and implementation of clinical decision support tools during drugs prescription process and tools that have allowed us to monitor them correctly.
Ms. Luciana Rubin
Hospital Italiano de Buenos Aires
08:50 - 09:10
Enhancing Guideline-Based Prescribing and Personalized Medication Scheduling (Charles Wachira, Samuel Osebe, William Ogallo, Aisha Walcott)
Poor communication of medication administration instructions is an important preventable cause of medication nonadherence. The Universal Medication Schedule improves adherence by providing a simplified set of dose timing rules. However, this framework does not readily generalize to persons with varying daily routines. We propose a point-of-care solution for enhancing guideline-based electronic prescribing and personalizing dose schedules. We describe a JSON-based approach to encode and execute standard treatment guidelines to support electronic prescribing and present an algorithm for optimizing medication administration schedules based on a patient’s daily routine. We evaluated the structure and accuracy of our JSON formalism focusing on Kenya’s hypertension treatment guidelines. Our experiments compare the medication schedules generated by our algorithm with those generated by pharmacists. Our findings show that treatment guidelines can be efficiently represented and executed using the JSON formalism, and that different medication administration schedules can be generated automatically and optimized for patients’ daily routines.
Mr. Charles Wachira
IBM Corporation, IBM Research Africa
09:10 - 09:30
Implementation of Clinical Decision Support Services to Detect Potential Drug-Drug Interaction using Clinical Quality Language (Binh-Phi Nguyen, Thomas Reese, Stefan Decker, Daniel Malone, Richard D. Boyce, Oya Beyan)
The potential drug-drug interactions (PDDI) rules are currently represented without any common standard, therefore it is difficult to update, maintain and exchange these rules.  The PDDI minimum information model developed by the Semantic Web in the Healthcare and Life Sciences Community Group describes PDDI knowledge in an actionable format.  In this paper, we will report implementation and evaluation of CDS Services which represent PDDI knowledge with Clinical Quality Language (CQL). The suggested solution is based on emerging standards including CDS Hooks, FHIR, and CQL. Two use cases are selected, implemented with CQL rules and tested at the Connectathon held at the  32nd Annual Plenary & Working Group Meeting of HL7.
Mrs. Dr. Oya Beyan
RWTH Aachen University
09:30 - 09:50
A Chinese survey of women’s use and expectation of pregnancy applications (li qing, Weiying Shan)
This study aimed to explore the use and expectation of smartphone applications about pregnancy among pregnant women using a survey method. A total of five hundreds pregnant women from 3 hospitals in the city of Chengde in hebei province in China were randomly selected to conduct a questionnaire survey. The study found that 61.48% of pregnant women used at least one pregnancy APPs, mainly for fetal development information (83.3%) and maternal changes information (65.3%); only 8% of pregnant women worried about the security of personal information very much. The main expected functions of pregnancy APPs are prenatal examination reminder (65%) and fetal monitoring (54.7%). Also, 77.3% of pregnant women hoped that information provided pregnancy APPs should be recognized by relevant authorities. It indicated that pregnancy APPs in the market in China was not able to meet the needs of pregnant women and needed further improvement in future.
Mrs. li qing
Wednesday
28 Aug 2019
14:10 - 15:30
T2-18
Clinical decision support 3
Room: Bellecour 1
14:10 - 14:30
Improving the Performance of Clinical Decision Support for Early Detection of Sepsis: A Retrospective Observational Cohort Study (Ling Li, Kasun Rathnayake, Malcolm Green, Mary Fullick, Amith Shetty, Scott Walter, Jeffrey Braithwaite, Harvey Lander, Johanna Westbrook)
Sepsis remains a significant global health problem. It is a life-threatening, but poorly defined and recognized condition. Early recognition and intervention are essential to optimize patient outcomes. Automated clinical decision support systems (CDS) may be particularly beneficial for early detection of sepsis. The aim of this study was to use retrospective data to develop and evaluate seven revised versions of an electronic sepsis alert rule to assess their performance in detecting sepsis cases and patient deterioration (in-hospital mortality or ICU admission). Four revised options had higher sensitivity but lower specificity than the original rule. After discussion with clinical experts, two revised options with the highest sensitivity were selected. Further analysis on the number of alerts and time intervals between alerts and patient outcomes was conducted to decide the option to be implemented. This study has provided a data-driven approach to improve the CDS on early detection of sepsis.
Ms. A/Prof Ling Li
Macquarie University
14:30 - 14:50
A Collaborative Decision Support Tool for Managing Chronic Conditions (Nadin Kokciyan, Martin Chapman, Panagiotis Balatsoukas, Isabel Sassoon, Kai Essers, Mark Ashworth, Vasa Curcin, Sanjay Modgil, Simon Parsons, Elizabeth Sklar)
This paper describes work to assess the feasibility of using a decision support tool to help patients with chronic conditions, in particular stroke, manage their condition in collaboration with their carers and the health care professionals who are looking after them. The system contains several novel elements, in particular: the integration of data from commercial wellness sensors, electronic health records and clinical guidelines; the use of computational argumentation to track the source of data and to resolve conflicts and make recommendations; and argumentation-based dialogue to support interaction with patients. The proposed approach is implemented as an application that can run on smart devices (e.g. tablets). The users have personalised dashboards where they can visualise their health data, and interact with a conversational chatbot providing further explanations about their overall well-being.
Mr. Professor Simon Parsons
14:50 - 15:10
Providing Comorbid Decision Support via the Integration of Clinical Practice Guidelines at Execution-Time by Leveraging Medical Linked Open Datasets (William Van Woensel, Samina Abidi, borna jafarpour, Syed Abidi)
Clinical Decision Support Systems (CDSS) utilize computerized Clinical Practice Guidelines (CPG) to deliver evidence-based care recommendations. However, when dealing with comorbidity (i.e., patients with multiple conditions), disease-specific CPG often interact in adverse ways (e.g., drug-drug, drug-disease interactions), and may involve redundant elements as well (e.g., repeated care tasks). To avoid adverse interactions and optimize care, current options involve the static, a priori integration of comorbid CPG by replacing or removing therapeutic tasks. Nevertheless, many aspects are relevant to a clinically safe and efficient integration, and these may change over time—task delays, test outcomes, and health profiles—which are not taken into account by static integrations. Moreover, in case of comorbidity, clinical practice often demands nuanced solutions, based on current health profiles. We propose an execution-time approach to safely and efficiently cope with comorbid conditions, leveraging knowledge from medical Linked Open Datasets to aid during CIG integration.
Mr. Prof. Syed Abidi
Dalhousie University
15:10 - 15:30
SIGICAM: A new software to improve the patient care supported by a constraint-based model (Carla Taramasco, Rodrigo Olivares, Fabián Riquelme)
Health facilities are residences that receive patients with different requirements. The management of patients falls on the clinical staff trained in this activity. However, given the demand of the population, the task of managing beds is sometimes too complicated when carried out manually. In this work, we propose the design and implementation of a technological platform that through an improved optimization approach, manages the patient-bed allocation efficiently, considering hospital resources, offered units and patient diagnosis. This tool is deployed in hospitals of the Atacama regional health service in Chile, boosting the work of the clinical staff of the health facility.
Mr. Dr. Fabián Riquelme
Thursday
29 Aug 2019
08:10 - 09:50
T2-07
Clinical decision support 4
Room: Bellecour 1
Chairman 1: Vimla Patel
08:10 - 08:30
An ontology-based personalized decision support system for use in the complex chronically ill patient (Esther Román-Villarán, Francisco de Paula Pérez-León, Germán Antonio Escobar Rodríguez, Alicia Martinez-Garcia, Celia Alvarez, Carlos Luis Parra Calderón)
Management of the complex chronically illpatient is highly problematic. This is due to theneed to complement recommendations in clinical guidelines with recommendations based on treatments performed on a representative set of patients. It is necessary to identify conflicts between the recommendations of different guidelines designed for handling specific chronic diseases. The PITeS-TIiSS project (code PI15/01213) aims to overcome this problem by designing and deploying an ontology-based personalized clinical decision support tool. This helps to improve personalized decisions and reduces variability in clinical practice in an integrated care environment. This paper describes the methodology followed in developing the ontology used to infer clinical knowledge and to develop and implement the support tool. The tool will access the information provided by the Electronic Health Record of Andalusian Health Public Service, the main healthcare provider in Spanish region with more than eight million inhabitants.
Mr. Carlos Luis Parra Calderón
08:30 - 08:50
Evaluation of a clinical decision support system for the prescription of genetic tests in the gynecological cancer risk (Jesus Moreno-Conde, Celia Alvarez, Cristina Suárez, María Ángeles Martínez, Jose Manuel Silvan, Carlos Luis Parra Calderón)
Clinical Decision Support System (CDSS) has been implemented to support physicians about the medical prescription of genetic testing. CDSS is based on open source software. A CDSS for prescribing these genetic tests in BRCA1 and BRCA2 and preventing gynecological cancer risks has been designed and performed in the ‘Virgen del Rocío’ University Hospital. Clinical evidence demonstrates that BRCA1 and BRCA2 mutations can develop gynecological cancer, but genetic testing has a high cost to the healthcare system. The developed technological architecture integrates open source tools like Mirth Connect and OpenClinica. The system allows general practitioners and gynecologists to classify patients as low risk (they do not require a specific treatment) or high risk (they should be attended by the Genetic Council), According to their genetic risk, recommending the prescription of genetic tests. The aim main of this paper is the evaluation of the developed CDSS, getting positive outcomes.
Mr. Jesus Moreno-Conde
Biomedical Informatics, Biomedical Engineering and Health Economics, Institute of Biomedicine of Seville, IBIS / Virgen del Rocío University Hospital / CSIC / University of Seville
08:50 - 09:10
Renal biopsy recommendation based on text understanding (Yang Lu, Zheng Jia, Xian Zeng, Chunyue Feng, Xudong Lu, Huilong Duan, Haomin Li)
Due to various etiologies and pathogenesis of kidney diseases, in order to determine the specific type of kidney disease of the patients, how severe it is and the best treatment for it, an invasive procedure called renal biopsy may be needed. The hypothesis of this study is whether a text understanding technology based on admission record can recommend such an invasive procedure objectively. To understand clinical documents from nephrology, a semi-automatic learning-based lexicon construction method based on CRF and Word2vec was used. We constructed a dictionary of symptom terms for the nephrology department from clinical documents, and then extracted patients’ symptoms and detected their negation from admission notes; combined with the preliminary diagnosis given by the doctor, an eigenvector was produced and fed to a machine learning classifier. Comparing the gold standard marked by physicians, the final recommendation achieved 83.5% accuracy, 80.6% precision, 76.6% recall, and 78.6% f1-measure respectively.
Mr. Dr. Haomin Li
Zhejiang University
09:10 - 09:30
Methodology of Sepsis Prognosis Prediction Model Tailored Clinical Practice (Min Jeoung Kang, Li Zhou, Frank Y. Chang, Christopher Knaplund, Jose Garcia, Jr., Kenrick Cato, Sarah Collins, Patricia Dykes)
This research suggests methods to build a sepsis prognosis prediction model tailored to clinical practice through the combination of clinical notes and physiological data using machine learning methods.
Ms. Min Jeoung Kang
Brigham and Women's Hospital
09:30 - 09:50
Improving adherence to clinical pathways through Natural Language Processing on Electronic Medical Records (Noa Cruz Diaz, Lea Canales, Javier García Muñoz, Bernardino Pérez, Ignacio Arnott)
This paper presents a pioneering and practical experience in the development and implementation of a clinical decision support system (CDSS) based on Natural Language Processing (NLP) and Artificial Intelligence (AI) techniques. Our CDSS notifies primary care physicians to clinical pathways in real time about recommendations regarding the respective healthcare process. This is, to the best of our knowledge, the first real-time CDSS implemented in the Spanish National Health System. We achieved an improvement of adherence rates in 8 out of 18 practices. Moreover, the provider’s feedback was very positive, describing the solution as fast, very useful and little intrusive since it did not affect the dynamics of their work. Thus, our CDSS reduced clinical variability and thereby revealed the usefulness of NLP and AI techniques to evaluate and improve health care.
Ms. Dr. Lea Canales
Savana
Thursday
29 Aug 2019
14:10 - 15:30
T2-19
Clinical decision support 5
Room: Bellecour 1
Chairman 1: Hyeoun-Ae Park
14:10 - 14:30
Developing a Taxonomy of Online Medical Calculators for Assessing Automatability and Clinical Efficiency Improvements (Tim Green, Chi-Ren Shyu)
Medical calculators play an important role as a component of specific clinical decision support systems that synthesize measurable evidence and can introduce new medical guidelines and standards. Understanding the features of calculators is important for calculator adoption and clinical acceptance.  This paper presents a novel classification system for medical calculators. Metadata on 766 medical calculators implemented online were collected, analyzed, and categorized by their input types, method of presenting results, and advisory nature of those results.  Reference rate, publication year, and availability of references were collected.  We found the majority of calculators are likely not automatable. 16% of medical calculators present advisory results to clinicians.  83% of medical calculators provide references. We show a 9 year lag from publication to implementation of calculators. New medical calculators should be developed with EHR integration and the advisory nature of results in mind so that calculators may become integral to clinical workflow
Mr. Tim Green
University of Missouri-Columbia
14:30 - 14:50
Automatic sleep stages classification combining semantic representation and dynamic expert system (Adrien UGON, Carole PHILIPPE, Amina KOTTI, Marie-Amélie DALLOZ, Andrea PINNA)
Interest for sleep has been growing in the last decades, considering benefits in well-being, but also for sleep troubles diagnosis. The gold standard to monitor sleep consists in recording the course of many physiological parameters during a whole night. The human interpretation of resulting curves is time consuming. We propose an automatic knowledge-based decision system to support sleep staging. This system allows to deal with temporal data, such as events, to combine and aggregate atomic data, so as to obtain high-abstraction-levels contextual decisions. The proposed system relies on a semantic reprentation of observations, and on contextual knowledge base obtained by formalizing clinical practice guidelines. Evaluated on a dataset composed of 131 full night polysomnographies, results are encouraging, but point out that further knowledge need to be integrated.
Mr. Dr Adrien UGON
ESIEE-Paris
14:50 - 15:10
Development and Preliminary Evaluation of a Visual Annotation Tool to Rapidly Collect Expert-Annotated Weight Errors in Pediatric Growth Charts (PJ Van Camp, Mahdi Cecilia Monifa, Lei Liu, Ni Yizhao, Andrew Spooner, Tzu-Yu Wu)
Patient weights can be entered incorrectly into electronic health record (EHR) systems. These weight errors can cause significant patient harm especially in pediatrics where weightbased dosing is pervasively used. Determining weight errors through manual chart reviews is impractical in busy clinics, and current EHR alerts are rudimentary. To address these issues, we seek to develop an advanced algorithm to detect weight errors using supervised machine learning techniques. The critical first step is to collect labelled weight errors for algorithm training. In this paper, we designed and preliminarily evaluated a visual annotation tool using Agile software development to achieve the goal of supporting the rapid collection of expert-annotated weight errors. The design was based on the fact that weight errors are infrequent and medical experts can easily spot potential errors. The results show positive user feedback and prepared us for the formal user-centered evaluation as the next step. 
Mr. PJ Van Camp
University of Cincinnati
15:10 - 15:30
Development, implementation and preliminary results of an electronic reminder for HIV screening using a service oriented architecture (Luciana Rubin, Natalia Pérez López, Alejandro Gaiera, Fernando Campos, Daniel Luna, Fernan Gónzalez Bernaldo de Quirós)
30% of the argentinian population and 58% of Plan de Salud HIBA patients are unaware of their HIV status. The Ministry of Health and US Preventive Service Task recommends physicians to assess HIV infection in persons aged 15 to 65. 
An HIV screening electronic reminder integrated in an EHR was created; using FHIR to represent clinical information and CDS-Hooks to represent the exchange of information with a CDS service. The tool had a 1% intervention rate, and it was accepted in a 67,4%. The number of HIV screening tests requested during the weeks after the CDSS implementation and in the same period in 2017 were obtained. 575 orders were requested in the 2017 period and 893 in the 2018. 89 (almost 10%) of these came from the electronic tool. The preliminary results indicate that this non disruptive, action oriented reminder can contribute to increase the ordering for HIV screening.
Ms. Luciana Rubin
Hospital Italiano de Buenos Aires
Tuesday
27 Aug 2019
16:30 - 17:50
T2-21
Clinical guidelines and decision making
Room: Tête d'or 2
Chairman 1: Niels Peek
16:30 - 16:50
Project and Preliminary Evaluation of SimHosp, a tool for Decision making in nursing (Gustavo Cervi, Cecilia Flores, Ana Lima, Rita Caregnato, Rute Somensi, Ana Respício)
Computerized simulators are important tools that support teaching in many areas. The use of these instruments is often described as significant for students and teachers. In this paper, a software piece was developed to aid decision-making in nursing, allowing the simulation of real situa-tions, addressed in the classroom. The simulator architec-ture corresponds to a multiagent system supported by a state machine model. To build the knowledge base, a list of contents was selected, including the Nursing Intervention Classification (NIC). An experiment was carried out with the participation of eleven students of the third year of the course. A questionnaire was applied and, as a result, there were more than 90% of acceptance as a relevant educa-tional tool. The simulation, through this tool, contributed to apply theoretical knowledge to the students, besides helping in the development of the nursing decision-making ability.
Mr. Msc Gustavo Cervi
Federal University of Health Sciences of Porto Alegre (UFCSPA)
16:50 - 17:10
A Model Driven Approach to the Design of a Gamified eLearning System for Clinical Guidelines (Job Nyameino, Fazle Rabbi, Khalid Mughal, Martin Were, Yngve Lamo)
Clinical practice guidelines (CPGs) are indispensable in the practice of evidence-based medicine. However, the cost of effective CPG dissemination strategies is prohibitive and not cost-effective. Therefore, scalable strategies using available technology are needed. We describe a formal model-driven approach to design a gamified e-learning system for clinical guidelines. We employ gamification to increase user motivation and engagement in the training of guideline content. Our approach involves the use of models for different aspects of the system, an entity model for the clinical domain, a workflow model for the clinical processes and a game model to manage the training sessions. A game engine instantiates a training session by coupling the workflow and entity models to automatically generate questions based on the data in the model instances. Our approach is flexible and adaptive as it allows for easy updates of the guidelines, integration with different device interfaces and representation of any guideline.
Mr. Dr. Job Nyameino
17:10 - 17:30
A Digital Health Platform to Deliver Tailored Early Stimulation Programs for Children With Developmental Delays (Raquel Dias, Syed Abidi, William Van Woensel, Asil Naqvi, Zahra Take, Marcela Lima, João Guilherme Alves)
Developmental delay is a deviation from the regular development of normative milestones during childhood. Early stimulation is a standardized and straightforward technique to support children with developmental delays (aged 0-3 years) in reaching basic motor skills, which are essential for the execution of everyday activities, such as playing, feeding and locomotion. In doing so, early stimulation reduces the chances of permanent motor impairment, thus allowing the child to live a more functional life. However, outcomes of this treatment de-pend heavily on the involvement of the family, who are re-quired to continue the early stimulation activities at home on a daily basis. To empower and educate families to administer standardized early stimulation programs at home, we developed an electronic early stimulation program, which provides personalized guidance to parents to administer early stimulation; together with evidence-based clinical decision support to therapists in tailoring ESP to observed needs.
Mr. Prof. Syed Abidi
Dalhousie University
17:30 - 17:50
Development and Assessment of RecosDoc-MTeV to Improve the Quality of Direct Oral Anticoagulant Prescription for the Venous Thromboembolic Disease (Brigitte Seroussi, Houda Ouarrirh, Ismaël Elalamy, Grigorios Gerotziafas, Isabelle Debrix, Jacques Bouaud)
Potentially inappropriate prescribing of direct oral anticoagulants is frequent with the most common errors being dosage, administration, and duration of therapy. We developed RecosDoc-MTeV, a documentary-based clinical decision support system (CDSS) for the management of direct oral anticoagulant prescription to prevent and treat venous thromboembolism. Simultaneously, the network of Parisian public hospitals (AP-HP, France) developed narrative clinical practice guidelines (CPGs) and a companion smartphone application to enhance medication and patient safety related to direct oral anticoagulant prescription. To assess the effectiveness of these CDS tools, we performed a retrospective review of 274 random patients hospitalized in 2017, which were either at risk of venous thromboembolism or actually treated for the disease. Consistency between the two CDS tools was measured at 96.7%. Administered treatments were compliant in 67.2% and 72.3% of the cases, with AP-HP CPGs and RecosDoc-MTeV, respectively. These results support that implementing CDSSs for the prescription of direct oral anticoagulants may ensure safe prescribing of high-risk medications.
Ms. Brigitte Seroussi
Tuesday
27 Aug 2019
08:10 - 09:50
T2-02
Electronic Health Records 1
Room: Tête d'or 2
Chairman 1: Chunhua Weng
08:10 - 08:30
Using health information exchange : usage and perceived usefulness in primary care (Aude Motulsky, Claude Sicotte, Marie-Pierre Moreault, Tibor Schuster, Nadyne Girard, David Buckeridge, Marie-Pierre Gagnon, Robyn Tamblyn)
Health information exchange (HIE) is seen as an essential technology for improving health care quality and efficiency by allowing exchange of patient-centered data over time and across organizations. The objective of this study was to evaluate the usage and the perceived usefulness of a nationwide HIE in a centralized model that was implemented in 2013 in the province of Quebec, Canada. A mixed-method study was conducted with a longitudinal descriptive analysis of usage data combined with in-depth comparative case study in four selected primary care organizations and two emergency departments. Perceived benefits were reported by users across all dimensions of care performance, including accessibility, efficiency, quality and safety, and patient experience. However, the experience of users was very heterogeneous and strongly  associated with the commercial electronic record system available in their work place, and the implementation strategy.
 
Ms. Aude Motulsky
08:30 - 08:50
Transforming Nursing Documentation (Melinda Jenkins, Avaretta Davis)
Graduate nursing education is positioned to transform nursing documentation so that it more fully describes nursing assessments, diagnoses, interventions, and outcomes to measure improvements in care. Learning to document with structured nursing terminology is integral to the update of “Information Technology for Evidence-Based Practice”, a required online course taken by all students in the Rutgers Doctor of Nursing Practice program.  Beginning with SOAP and terminology required for billing, students create a hypothetical clinical note adding elements of the Nursing Minimum Data Set, using Clinical Care Classification terms.  Next, students are asked to select a nursing-related clinical practice guideline, electronic clinical quality improvement measure, and a screening tool that applies to their encounter note.  Then, they identify Patient Reported Outcome Measures as well as improvement activities in the CMS Quality Payment Program.  The course is well-received; many graduate students now face changes in documentation and electronic tools and can predict future evolution.
 
Ms. Dr. Melinda Jenkins
Rutgers University
08:50 - 09:10
Improving medication use : evaluation of a nationwide e-prescribing system (Aude Motulsky, ManQing Liang, Marie-Pierre Moreault, Elizabeth Borycki, Andre Kushniruk, Claude Sicotte)
Electronic prescribing, defined as the electronic generation and transmission of a medication order for community-dwelling patients, is presented as an essential technology to improve medication use. The objective of this study was to evaluate a nationwide e-prescribing system in Quebec, Canada. A mixed-method study was conducted, from July 2017 until June 2018. A descriptive analysis of usage was performed using aggregated usage data, combined with an exploratory descriptive analysis of the e-prescribing system from the perspective of users of two electronic health records (EHR) and pharmacy management systems (PMS) (n=9 prescribers; 8 pharmacy technicians and 11 pharmacists). Overall, the adoption of the system was low, with only 2% of prescriptions being electronically transmitted and retrieved during the study period. Alignement problems were identified on the prescriber’s and receiver’s side, generating safety issues, and hindering the potential for benefits realization.
Ms. Aude Motulsky
09:10 - 09:30
Differences between what is said during the consultation and what is recorded in the electronic health record (Virginie Lacroix-Hugues, Sarah Azincot-Belhassen, Pascal Staccini, david darmon)
Electronic Health Records (EHRs) can be used for research but this raises the problem of data quality. Objective: To evaluate the quality of the information recorded in an EHR by a general practitioner (GP) during a regular office consultation. Method: 191 dialogs between GP and patient were recorded and translated into International Classification of Primary Care Second edition (ICPC-2) codes. Written information of the corresponding EHR was extracted and coded for comparison. Results: The primary reason for the consultation was recorded in the EHR in 41.2% of the cases and the diagnosis in 44.1%. Diagnoses noted in the EHR were less often communicated to the patients than the primary reasons were (p<0.0001). Conclusion: There is a loss of information between the dialog during a consultation and what is reported in the EHR. Consequences in terms of continuity and safety of care can be expected.
Mrs. Doctor Virginie Lacroix-Hugues
09:30 - 09:50
Developing an Electronic Record Tool Representative of Primary Health Care in the Public Health Care System of Buenos Aires City (Analia Baum, Florencia Faretta, Denis Levi, Lucía Marques de Paivaa, Fernan Gónzalez Bernaldo de Quirós, María Victoria Giussi Bordoni)
Electronic Health Records (EHR) face the challenge of collecting data from gender identity to provide standardized and quality data to manage public policies in order to improve health disparities of the Trans population. Innovation in Health Information Technologies (HIT) develops in the midst of a cultural change process related to social representations of gender in favor of a diversity perspective. Understanding the health field as a complex adaptive system, the changes in the systems must consider multiple factors in every stage of the process. It is relevant to consider the people involved in it and the culture in which they are embedded. This article describes the implementation strategies of a functionality that represents the transgender population in the EHR of the Public Health Care System of the Buenos Aires City.
Mrs. Dr. María Victoria Giussi Bordoni
Ministry of Health
Tuesday
27 Aug 2019
11:50 - 13:10
T2-13
Electronic Health Records 2
Room: Tête d'or 2
Chairman 1: Yang Gong
11:50 - 12:10
Can openEHR represent the clinical concepts of an obstetric-specific EHR — ObsCare software? (Danielle Santos Alves, Priscila A. Maranhão, Ana Pereira, Gustavo M. Bacelar-Silva, Tiago Silva-Costa, Thomas Beale, Ricardo J. Cruz-Correia)
ObsCare is an obstetric-specific Electronic Health Record in use in nine Portuguese obstetric departments. Like other EHRs, it faces major challenges related to semantic interoperability and data quality. OpenEHR is proposed to address those needs. The study aimed to describe the data in ObsCare, the ObsCare care process workflow and to validate whether archetypes in the openEHR Clinical Knowledge Manager repository can represent the clinical concepts. The study included the phases: a) ObsCare form selection; b) Description of the workflow care process; c) Detailed data extraction; and d) CKM models analysis. 379 variables were analyzed: 219 were fully represented in CKM repository; 99 were partially represented and needed archetype modification; and 61 were not represented and need new archetypes. To conclude, our study showed that the openEHR CKM repository requires further enhancements to be able to fully answer to the needs of an obstetric-specific EHR, the ObsCare software.
Ms. Danielle Santos Alves
Federal University of Pernambuco (UFPE)
12:10 - 12:30
Usability Across Health Information Technology Systems: Searching for Commonalities and Consistency (Ross Koppel, Craig Kuziemsky)
Usability of health information technology (HIT) remains a predominant concern—one often exacerbated by clinicians’ need to access information created by many different professionals in different settings, often using very dissimilar EHRs or even with the same EHR but with different configurations. Because of these variations, we argue that we must no longer think of usability as anchored in one setting, or one EHR, or one data standard or one type of clinician. Rather, usability must be understood as a collective and constantly emerging process. This paper thus seeks to address that reality by: 1) substantially expanding our previously-developed conceptual matrix of the wide range of settings and interfaces comprising modern HIT; and 2) adding actual examples of EHR usability issues with similar data but with very different displays or processes
Mr. Prof. Ross Koppel Ph.D.
Univ of Pennsylvania
12:30 - 12:50
The Role of Electronic Health Records in Improving Communication Between Health Professionals in Primary Healthcare Centres in Riyadh: Perception of Health Professionals. (bander alanazi, Kerryn Butler-Henderson, Mohammed Alanazi)
Background: Improving communication among healthcare providers is one of the critical components of safe and quality patient care.
Objective: To examine how occupation and training of health professionals in Riyadh, Saudi Arabia influence their perception of the role of electronic health record (EHR) in improving communication between healthcare providers in primary healthcare centres (PHCCs).
Methods: A descriptive, cross-sectional design employing purposive sampling was used for this survey study.
Results: Health professional’s occupation and training were found to influence their perception of the role of EHR in improving interprofessional communication. Physicians and professionals with a training on EHR had the highest rating of EHR’s role in improving communication between healthcare professionals.
Conclusion: All healthcare providers should be trained and encouraged to use EHR systems to improve communication among them.
Mr. phd bander alanazi
University of Tasmania,
12:50 - 13:10
Incongruence of patient problem information across three phases of home care admission: There’s a problem with the problem list (Paulina Sockolow, Natasha Le, Yushi Yang, Sheryl Potashnik, Ellen Bass, Kathryn Bowles)
In home health care, the patient problem list is an important component of the admission and care planning processes and determines the subsequent care received. We examined the information received from the referring facilities and its relationship with the final patient problem list generated at home care admission. Researchers observed 12 home care admissions and collected all documents related to the admission and care planning process. Problems identified in documents provided to admission nurses (input documents) and in documents subsequently created by admission nurses (output documents) were coded to form a standardized set of problem terms across all documents. Documents available, distribution of problems within the documents, and concordance between input and output documents were assessed. A varying number of the 17 unique problems found across all documents were distributed by document type. Patients were referred to homecare with more clinical problems than were documented in the output document
Ms. Dr. Paulina Sockolow
Tuesday
27 Aug 2019
08:10 - 09:50
T2-03
Electronic Health Records 3
Room: Gratte Ciel 3
Chairman 1: Bastien Rance
08:10 - 08:30
Does a Stage 7 EHR Translate into Meaningful Use for Nurses? (Eric Maillet, Leanne Currie, Gillian Strudwick, Véronique Dubé)
The purpose of this presentation is to describe a program of research, thus far three studies, that seeks to examine meaningful use of EHRs for nurses. The authors are replicating a cross-sectional study in a hospital that has achieved EMRAM level 7, with the goal to investigate the actual use of the EHR and the impact on nursing.  In addition, the current study will examine the relationship between factors related to the use of the EHR and nurses’ perception of quality of care. In this podium presentation we will present the results of the current study with a comparison to the results of the previous two studies.
Mr. Dr Eric Maillet
University of Sherbrooke
08:30 - 08:50
Availability and Quality of Information Used by Nurses While Admitting Patients to a Rural Home Care Agency (Paulina Sockolow, Ellen Bass, Yushi Yang, Natasha Le, Sheryl Potashnik, Kathryn Bowles)
Home care admission nurses need high quality information that is not uniformly available. Despite this challenge, these nurses make four critical clinical decisions when constructing the admission plan of care: (1) patient problems to address in the home care episode; (2) patient medication management; (3) services in addition to skilled nursing; and (4) skilled nursing visit pattern. We observed 12 in-home admissions at a rural home care agency and interviewed nurses before and after. We analyzed content and quality of documents. To evaluate quality, for each decision we assessed concordance between documents. Interview responses provided context in the mixed methods analysis. Across all admissions, documents and content were not uniformly present. Nurses rarely received visit pattern or medication management information. There was consistent discordance in the number of problems among and between available documents and the plan of care. Electronic health record design recommendations include interoperability and structured, consistent, actionable data.Home care admission nurses need high quality information that is not uniformly available. Despite this challenge, these nurses make four critical clinical decisions when constructing the admission plan of care: (1) patient problems to address in the home care episode; (2) patient medication management; (3) services in addition to skilled nursing; and (4) skilled nursing visit pattern. We observed 12 in-home admissions at a rural home care agency and interviewed nurses before and after. We analyzed content and quality of documents. To evaluate quality, for each decision we assessed concordance between documents. Interview responses provided context in the mixed methods analysis. Across all admissions, documents and content were not uniformly present. Nurses rarely received visit pattern or medication management information. There was consistent discordance in the number of problems among and between available documents and the plan of care. Electronic health record design recommendations include interoperability and structured, consistent, actionable data.
Ms. Dr. Paulina Sockolow
08:50 - 09:10
Contents of Informational and Management Continuity of Care (Anne Kuusisto, Paula Asikainen, Kaija Saranto)
Continuity of patient care (COC) is considered an essential feature of good quality care, but the ambiguity of the concept has given rise to methodological challenges in scientific studies. This study has a strong link to the functional definitions of electronic health records (EHR). In order to evaluate how COC is achieved, through a discharge summary, for example, the contents of COC should be defined. Conceptual consensus on COC as a multidimensional concept has increased. This study was conducted to provide an overview of the dimensions and descriptions of informational and management continuity of care. A scoping review was conducted. We found that informational continuity of care refers to data tool, data content, data structures or information quality related processes. Management continuity of care refers to information flow, co-operation, co-ordination, multiprofessionality or management processes. We identified the need to define next the contents of relational and cross-border continuities.
Ms. Anne Kuusisto
Satakunta Hospital District
09:10 - 09:30
Health Professionals’ Experience with Patients Accessing their Electronic Health Records: results from an online survey (Monika Alise Johansen, Per Egil Kummervold, Tove Sørensen, Paolo Zanaboni)
The aim of this study was to investigate hospital professionals’ experience and attitude with patients accessing their own electronic health records. The study was conducted one year after service establishment. Data was collected through an online survey. In total, 457 replies were received. The results revealed that a quarter of the administrative staff received feedback from patients or relatives regarding mistakes or missing information in their EHR. In addition, 67.5% of health professionals expected more patients to have basic knowledge of their health status in the future, and 21.4% found that patients already gained better knowledge about diagnosis, treatment or follow-up. The results also revealed some challenges with the service, especially for health professionals working in psychiatry, with some scepticism on whether the service is suitable for the sickest and most vulnerable patients
Mrs. Dr Monika Alise Johansen
Norwegian Centre for E-health Research
09:30 - 09:50
Feasibility study for establishment of a national dialysis outcomes registry in India (Oommen John, Abhinav Bassi, Rohina Joshi, Sradha Kotwal, Kamal Shah, Sanjay Singh, Stephen Jan, Martin Gallagher, John Knight, Vivekanand Jha)
Haemodialysis is the main modality of renal replacement therapy in India. Electronic Health Records are not routinely available in Indian Healthcare establishments. The outcomes of those starting dialysis is not known as there is no national dialysis registry in India. We developed an online dialysis outcomes data collection portal, defining a minimum data set for measuring clinical and socio economic outcomes, and describe here the methodology undertaken for defining the minimum data sets, the development of the electronic data collection interface, training of the clinical staff for data collection, change management interventions and results of the feasibility study for establishment of a national dialysis registry in India.
Mr. Dr Oommen John
The George Institute for Global Health Indian Association for Medical Informatics
Wednesday
28 Aug 2019
08:10 - 09:50
T2-05
Electronic Health Records 4
Room: Tête d'or 2
08:10 - 08:30
Supporting Care for Pediatric Cancer Survivors in the Electronic Health Record (L Taylor Ber, Carolyn Petersen, Christoph Lehmann)
Health outcomes research conducted in the past 30 years established that survivors of childhood cancer are at an increased risk for morbidity and mortality due to therapies which treated their primary malignancies [1][2]. Despite ample research on the long-term effects of anti-cancer treatments, there is a lack of long-term surveillance [3][4]. This work was designed to develop data ele-ments/logic for EHR functionalities, which can be used to develop decision support for physicians treating long-term survivors. Key terms such as, Childhood Cancer Survivors, Pediatric Oncology Survivorship Guidelines, Recommendations for Longevity of Pedi-atric Cancer Survivors were used to search the database PubMed for guidelines and current recommendations for treatment. Papers identified in the search were used to supplement the Long-Term Follow-Up Guidelines published by the Children’s Oncology Group, from which we described 858 long-term effects and 728 key action statements [5]. Key action statements were further ana-lyzed and required data elements were identified and described (Figure 1). Descriptive analytics on the statements and appendix revealed radiation caused the greatest number of adverse effects and the uro-genital system was the organ system with the most recommendations (Figure 2). We recommend that the Children’s Oncology Group work be revisited to disambiguate and increase decidability, which will lead to better support for physicians and more effec-tive surveillance once adopted by EHR vendors.
Mr. Dr. Christoph Lehmann
Vanderbilt University School of Medicine
08:30 - 08:50
Standardizing Key Issues from Hospital through an Electronic Multi-professional Discharge Checklist to Ensure Continuity of Care (Anne Kuusisto, Mikko Härkönen, Anne Joensuu, Minna Nevalainen, Terhi Pakkanen, Paula Ranne, Juha Puustinen)

This article describes development of the multi-professional discharge checklist and its implementation into the nursing documentation system (NDS) as part of the patient’s overall care plan. The aim was to harmonize patient’s admission and care period documenting and to improve the quality of electronic nursing discharge summaries. The ultimate goal was to ensure continuity of care. The multidisciplinary discharge checklist was developed in two phases to support the discharge of elderly patients (over 65 years). First, the information content of the checklist was defined, and second, it was integrated into the NDS. Focus groups of social and healthcare professionals (n = 82) in specialist health care, primary health care and social services defined the information content and participated in the feedback and checking rounds. The development work should continue. Particular attention should be given to the technical performance of discharge checklists in the NDS.
 
Ms. Anne Kuusisto
Satakunta Hospital District
08:50 - 09:10
Governance and Sustainability of An Open Source Electronic Health Record: An Inter-pretive Case Study of OpenDolphin in Japan (Placide POBA-NZAOU, Naoto Kume, Shinji Kobayashi)
Electronic Health Records (EHRs) are at the heart of reforms aimed at improving the efficiency and quality of healthcare services provided to citizens. Although there is still some skepticism, open source (OS) EHR is a growing phenomenon in health informatics. Given the widespread adoption of OS software (OSS) in several domains, including operating systems, and enterprise systems, the repeated shortfalls faced by healthcare organizations with dominant proprietary EHRs create an opportunity for other alternatives, such as OSS to demonstrate their abilities in addressing these well-documented problems, including inflexibility, high costs, and low interoperability. However, scholars have expressed extensive concerns about the sustainability of OS EHR. Recognizing that OSS project sustainability relies on their governance arrangements, this case study reports on the evolution of the governance and sustainability of a Japanese OS EHR project and provides rich insights to other open source EHR initiative stakeholders, including physicians, developers, researchers, and policy-makers.     
Mr. Dr. Placide POBA-NZAOU
University of Quebec in Montreal, Montreal, Quebec, Canada
09:10 - 09:30
Using Electronic Health Records and Machine Learning to Predict Postpartum Depression (Shuojia Wang, Jyotishman Pathak, Yiye Zhang)
Postpartum depression (PPD) is one of the most frequent maternal morbidities after delivery with serious implications. Currently, there is a lack of effective screening strategies and high-quality clinical trials. The ability to leverage a large amount of detailed patient data from electronic health records (EHRs) to predict PPD could enable the implementation of effective clinical decision support interventions. To develop a PPD prediction model, using EHRs from Weill Cornell Medicine and NewYork-Presbyterian Hospital between 2015-17, 9,980 episodes of pregnancy was identified. Six machine learning algorithms, including L2-regularized Logistic Regression, Support Vector Machine, Decision Tree, Naïve Bayes, XGBoost and Random forest were constructed. Our model’s best prediction performance achieved an AUC of 0.79. Race, obesity, anxiety, depression, different types of pain, antidepressants, and anti-inflammatory drugs during pregnancy were among the significant predictors. Our results suggest a potential for applying machine learning to EHR data to predict PPD and inform healthcare delivery.
Mr. Dr. Jyotishman Pathak
Cornell University, New York
09:30 - 09:50
Use of a Clinical Decision Support System is associated with reduced loss to follow-up among patients receiving HIV care in Kenya (Tom Oluoch, Ronald Cornet, Nicolette de Keizer)
Loss to follow-up (LTFU) among patients receiving HIV care in resource-limited settings is a major obstacle to the global goal of achieving HIV epidemic control by 2020. We analysed data from a clustered randomized study in western Kenya to assess the effect of a clinical decision support system on LTFU. There was a 1.4 higher odds of LTFU at HIV clinics with no CDSS. CDSS can potentially reduce the proportion of patients that are LTFU; however, CDSS should be used alongside other interventions such as patient education, structural improvement of health facilities and provider characteristics.
Mr. Tom Oluoch
US Centers for Disease Control and Prevention
Wednesday
28 Aug 2019
11:50 - 13:10
T2-14
Electronic Health Records 5
Room: Tête d'or 2
11:50 - 12:10
How and in what Contexts does Networked Health IT Improve Patient Safety? Elicitation of Theories from the Literature (Rebecca Randell, Maysam Abdulwahid, Joanne Greenhalgh, Natalie King, Judy Wright, Justin Keen)
Healthcare systems worldwide are investing in networked health IT systems that link healthcare providers across multiple organisations. Much of the policy arguments in favour of such investment rely on the assumption that networked health IT will lead to improved patient safety. As part of the first stage of a realist review to determine how and in what contexts networked, inter-organisational health IT does lead to improved patient safety, we elicited stakeholders’ theories from the literature that reveal possible answers to this question. A key mechanism appears to be that the information provided supports improved decision making. Greatest benefits are likely to be found in relation to medication information, in scenarios where the patient is less able to provide accurate information about their medications themselves. However, access and use of this information depends on ease of access, clinicians’ perception of the likelihood that the desired information will be available, and clinicians’ trust in the information.
Ms. Dr. Rebecca Randell
University of Leeds
12:10 - 12:30
Impact of Patient Online Access to their Electronic Medical Records through Patient Portals: A Systematic Review (Archana Tapuria, Talya Porat, Dipak Kalra, Glen Dsouza, Vasa Curcin)
Objectives: A significant cost element of health care provision are one-on-one interactions with individuals at clinic visits or by phone. HIT (Health Information Technology) and patient-shared Electronic Healthcare Records (EHRs) have the potential to decrease these costs, improve access to healthcare data, self-care, quality of care, and health and patient-centred outcome. Patient portal is a secure online website that provides patients convenient 24-hour access to personal health information via an Internet connection. This systematic literature review was aimed at identifying the benefits and issues around promoting patients access to their own EHRs through patient portals. The purpose is to outline and summarise study results on the impact of patients’ online access to their own EHRs through the patient portals. Methods: Searches were conducted in PubMed, MEDLINE, COCHRANE library, CINHAL and Google scholar. Over 400 papers were screened, and following the PRISMA guidelines, they were initially filtered based on duplicates, then by reading the titles and finally based on their abstracts. 24 papers were retained, analysed and summarised. Papers were included if patient access to their own EHRs through patient portals was the primary intervention used in the study. The search technique used to identify relevant literature for this paper, involved input from 5 experts. The protocol is registered with PROSPERO. Results: Patient access to their own EHRs through the patient portals was found to improve patient outcomes such as medication compliance (3 studies), achieving blood pressure control (1 study), controlling sugar levels and glycemic control (2 studies), improving functional status and reduced high-cost healthcare utilisation in patients with chronic conditions (2 studies), enhance timely patient centred care (1 study). These were noted in a range of study populations. In addition, patient portals were found to improve self-reported levels of engagement or activation related to self-management (2 studies), enhanced knowledge, and improve recovery scores, and organisational efficiencies in a tertiary level mental health care facility. However, three studies did not find statistical effect of patient portals on health outcomes (1 study). This review clearly describes the types of studies, participants, interventions and outcomes, as well as the data sources and search strategy and tabular summaries of the studies included. Secondly, the focus has been solely on the impact of patient access to their EHRs through patient portals. Conclusions: This literature review identified some benefits and harms involved in promoting patients’ access to their own EHRs through the patient portals. The findings of this review could help healthcare providers look at the benefits offered by promoting patient access to EHRs and decide on the best approach for their own specialties and clinical set up. A robust cost-benefit evaluation of such initiatives along with its impact on major stakeholders within the healthcare system would be essential in understanding its overall impact. Such initiatives could help the government address concerns in developing national standards, whilst taking care of local variations and fulfilling the healthcare needs of the population.
Mrs. Dr Archana Tapuria
King's College London
12:30 - 12:50
Towards an open-source oncology electronic medical records system for low-resource settings: development of chemotherapy management in OpenMRS (Johnblack Kabukye, Alexis M. Casaceli, Ellen Ball, Mario De Armas, Ronald Cornet)
Cancer is a major public health challenge in low and middle income countries (LMICs). In this paper we describe work in progress to develop functionality within an open-source electronic medical records system to support safe and standardized cancer care in low-resource settings. We engaged cancer care providers from LMICs to elicit and prioritize requirements, and following a rapid application development approach we developed chemotherapy prescription and documentation functionality within OpenMRS.
Mr. Johnblack Kabukye
Uganda Cancer Institute
12:50 - 13:10
An obstetric application architecture for information, diagnosis and control of diabetes in high risk pregnancy (Danielle Santos Alves, Marcus Caio de Moura Ferreira Gomes, Magdala Novaes)
Hyperglycemia associated with pregnancy is related to several unfavorable perinatal outcomes, as well as increased incidence of future complications. Thus, the diagnosis of hyperglycemia in the pregnancy-puerperal context should be a global health priority. In this article, we present the development of a mobile application prototype to inform, provide a correct diagnosis and provide tools for obstetric telemonitoring in women with diabetes associated with pregnancy. After a detailed analysis of the proposals for a new diagnostic strategy considering possible scarcity of resources, key points were selected and inserted into the prototype, in order to cover as many aspects as possible and make it as complete as possible. The application has been adapted to the Brazilian reality, however, with adjustments from the international protocols, it has the potential to be used in several places in the world.
Ms. Danielle Santos Alves
Federal University of Pernambuco (UFPE)
Tuesday
27 Aug 2019
14:10 - 15:30
T2-17
Health-enabling technologies 1
Room: Gratte Ciel 3
Chairman 1: Jingyuan Cheng
14:10 - 14:30
Wireless Sensor Network for Fall Prevention on Geriatric Wards: A Report (Nico Jähne-Raden, Henrike Gütschleg, Marie Cathrine Wolf, Ulf Kulau, Klaus-Hendrik Wolf)
With regard to the growing number of older adults, it needs smart solutions for fall prevention. Especially at geriatric institutions, the risk of falling is very high and frequently leads to injuries, resulting in serious consequences. We pre-sent the Inexpensive Node for Bed Exit Detection (INBED), a comprehensive signaling system for fall prevention. The INBED system is based on a Wireless Sensor Network (WSN) infrastructure via IEEE802.15.4 and highly-specialized open Hardware (HW) in-house developed wearable. The device, which will be attached to the patients, can detect several types of movement. Occurring events are forwarded to the nursing staff immediately by using the self-organizing and scalable network including Wide Area Network (WAN) inte-gration. The system can help to relieve the staff while the per-sonal freedom of movement and privacy of patients is in-creased. With this development, the energy-efficient, simple and intuitive mechanisms of proximity communication can be combined with broadband benefits.
Mr. Nico Jähne-Raden
Peter L. Reichertz Institute for Medical Informatics University of Braunschweig - Institute of Technology and Hannover Medical School
14:30 - 14:50
Pro-Actively Guiding Patients through ADL via Knowledge-Based and Context-Driven Activity Recognition (William Van Woensel, Samina Abidi, Syed Abidi)
Assisted Ambient Living (AAL) focuses on self-sufficiency, assisting disabled people to perform activities of daily living (ADL) by automating assistive actions in smart environments. Importantly, AAL provides opportunities for dynamically guiding patients with cognitive deline through an ADL. Activity recognition is a pivotal task, since it allows detecting when an ADL is started by recognizing its constituent activities. When dealing cognitive decline, activity recognition should also be able to detect when activities are performed incorrectly—e.g., performed out-of-order, at the wrong location or time, or with the wrong objects (e.g., utensils)— which is nevertheless not a common goal in activity recognition. Moreover, it should be able to cope with non-uniform ways of performing the ADL that are nevertheless correct. We present an novel knowledge-driven activity recognition approach, which employs semantic reasoning to recognize both correct and incorrect actions, based on the ADL workflow as well as associated environment context.
Mr. Prof. Syed Abidi
Dalhousie University
14:50 - 15:10
Feasibility and Acceptability of Smart Augmented Reality Assisting Patients with Medication Pill Box Self Management (Madeleine Blusi, Juan Carlos Nieves)
Complex prescribed medicine regimens requires extensive self management. Handling multiple pills can be confusing, using a pillbox organiser is a common strategy. A smart Medication Coach Intelligent Agent (MCIA) can support patients in handling medicine. The aim of this research was to evaluate feasibility and acceptability of the MCIA. A prototype was tested where 15 participants, age 17-76, filled a pillbox according to prescription assisted by the MCIA implemented in a Microsoft Hololens. A quantitative method using questionnaires was applied. Results showed that using the MCIA implemented in an AR-headset, to assist people with prescribed polypharmacy regimen in filling a pillbox, was feasible and acceptable. There was a difference related to age regarding people’s willingness to use an AR-headset for medication self management. People older than 65 felt less comfortable using the technology and were also more hesitant to use the technology than those under 65.
Mrs. Dr. Madeleine Blusi
Umeå University
15:10 - 15:30
SERENE-IoT project: how the maturity cycle allows the correct development process of innovative technologies in the healthcare domain (Samy Strola, Armand Castillejo, Alexandre Moreau-Gaudry)
This article illustrates the maturity process of innovative technologies in the healthcare domain. The role and the involvement of the stakeholders are explained, as well their interaction in the ecosystem. We focus on how the synergy between partners improves efficiency, boosts product development and accelerates market access. The spiral of the innovation concept is introduced to illustrate the different stages ensuring the correct development of a medical technology. This iterative cycle drives the maturity of the product, according to medical needs and feedback, and ensures the correct implementation of the innovation in the clinical framework. We finally illustrate how the innovation process is applied to successful drive the ongoing SERENE-IoT project: the spiral of innovation concept is specifically adapted to fit with the project requirements with the final objective to identify a panel of medico-economic indicators and to establish the medical service delivered and the opportunities in order to capture the full benefit of the proposed technology.
Mr. Dr. Samy Strola
CHU Grenoble Alpes - CIC-IT
Friday
30 Aug 2019
08:10 - 09:50
T2-10
Clinical applications and blockchain technology
Room: Bellecour 1
08:10 - 08:30
Possible usages of smart contracts (blockchain) in healthcare and why no one is using them (Alain Giordanengo)
Security, privacy, transparency, consent and data sharing are major challenges that healthcare institutions must address today. The explosion of the Internet of Things (IoT), the enactment of the General Data Protection Regulation (GDPR), the growing trend of patients self-managing their diseases and the eagerness of patients to share their self-collected health data with primary and secondary health organisations further increase the complexity of these challenges. Smart contracts, based on blockchain technology, can be a legitimate approach for addressing these challenges. Smart contracts define rules and penalties in an agreement, enforce those rules and render them irrevocable. This paper presents a state-of-the-art review (as of May 2018) of the possible usages of smart contracts in healthcare and focuses on data sharing between patients, doctors and institutions.
Mr. Alain Giordanengo
UiT The Arctic University of Norway, Norway
08:30 - 08:50
Usability and Performance of a Blockchain-based Care-Management System in Kenya (Aisha Walcott, William Ogallo, Sekou Remy, Fiona Matu, Charles Wachira, Jane Snowdon, Irene Dankwa-Mullan, Gretchen Purcell Jackson, Julius Mbeya, Wycliffe Omwanda)
The inherent complexities of Africa’s healthcare landscape make it difficult for practitioners to ascertain a deep under-standing of a patient’s condition and effectively coordinate efforts to deliver high quality care. To address these critical challenges, we are developing a blockchain-enabled system for orchestrating outpatient clinical workflows and enabling patient-controlled exchange of health information between care facilities. This paper reports the results of our preliminary investigations to benchmark the usability and performance of the system. We conducted a usability test with care providers at the Lwala Community Alliance in Western Kenya. Thirteen participants (2 hospital records administrators, 3 nurses, 6 clinicians, and 2 laboratory technicians) used the system to complete data entry and review tasks for simulated test scenarios mimicking various patient encounters in an ambulatory clinic. The records clerks completed 2 tasks – register patient and add registered patient to nurse queue. The nurses completed 1 task – conduct nurse triage. The clinicians completed 2 tasks – assess patient then order lab, and review lab results then refer patient. The lab technicians completed 1 task – conduct lab test. Quantitative usability data was collected using standard testing questionnaires. The 1-item Subjective Mental Effort Questionnaire (SMEQ) assessed task difficulty on a scale of 0 to 150. The 10-item System Usability Scale (SUS) Questionnaire assessed user satisfaction expressed as an overall usability score between 0 and 100. For performance testing, we measure the time taken to share data between participating facilities during referrals. We measured the average duration between uploading a link to patient-consented data in a primary facility and downloading the data via the link in a secondary facility, established the latency of Application Programming Interface (API) access in different deployment contexts, and assessed the reliability of the system under varied transaction load conditions. Testing took place in both the lab and field settings and were done with and without a Virtual Private Network (VPN). All users completed their required tasks. The SUS mean usability score was 81.9 (range: 65 to 97.5) among all users and 79.5 (range: 65 to 92.5) among clinicians only. The median SMEQ score for all users was 10 (range: 0 to 25). The mean uploading/download duration of shared data was 88 seconds. The median response time for application server logins was 1700 ms (range: 1012 to 14475) with no VPN, and 4100 ms (range: 2589 to 26195) with VPN. The median response time for blockchain logins was 470 ms (range: 405 to 2873). The mean time to create users and organizations were 79339 ms (range 311160 to 115976) and 63976 ms (range: 39853 to 107317) respectively. The mean time to create and upload consents was 40572 ms (14954 to 113603). Care providers found the application satisfactory and easy to use for supporting clinical documentation and data sharing. The platform can be deployed in resource-constrained settings, though its performance is affected by the number of concurrent users, transaction loads, round-trip delay time for accessing cloud-hosted services, and local network bandwidth.
Mr. Charles Wachira
IBM Corporation, IBM Research Africa
08:50 - 09:10
Pediatric Asthma Care Assessment for the Emergency Department (Adeola Akinfaderin, Kathryn Kovalenko, Pamela Newsome, Jeritt Thayer, Yang Gong)
In the United States alone, approximately 6.2 million children have asthma. Managing the care of pediatric patients presenting in the emergency department with asthma requires clinicians to access multiple locations within the electronic health record. This wealth of information makes it vital to develop methods for sifting through the clutter to information that is relevant to the specific task to be completed. Unfortunately, current information displays have not been developed to maximize provider efficiency when integrating information across a number of disparate locations. Using proven data display theories, we aimed to create a consolidated acute pediatric asthma display to aid in the patient's care with the goal of improving the efficiency and consistency by which they are treated - ultimately reducing the length of stay, complications, and morbidity in these patients.
Mr. Prof. Yang Gong Associate Professor
University of Texas Health Science Center at Houston
Professor Yang Gong, MD, PhD is a principle investigator on patient safety and clinical decision support.
09:10 - 09:30
SIMENS-LIS4SC, a Laboratory Information System for Biological Tests of Sickle Cell Screening and Healthcare (Al Hassim DIALLO, Gaoussou Camara, Jean Baptiste Lamy, Mamadou DIOP, Ibrahima DIAGNE, Demba MAKALOU, Dominique DOUPA)
Neonatal screening and ongoing follow-up of children with sickle cell disease are essential to reduce the mortality caused by this disease. To ensure care continuity, it is essential to include in the patient's record the history and details of biological tests. Thus, it is necessary to provide a laboratory information system for electronic management of biological test prescription and results, and a good integration with the Health Information Systems. In this paper, we propose a Laboratory Information System for the management of biological tests for the neonatal screening and healthcare of sickle cell disease in Senegal.
Mr. Pr. Gaoussou Camara
EIR-IMTICE, Université Alioune Diop de Bambey
09:30 - 09:50
Meta-Analysis of the Sensitivity of Decision Support Systems in Diagnosing Diabetic Retinopathy (Priscyla Waleska Simões, Maitê Gabriel dos Passos, Diego Garcia, Ronaldo Borges Vicente, Larissa Letieli Toniazzo de Abreu, Maria Marlene Souza Pires, Eros Comunello, Luciane Bisognin Ceretta, Laura Lopes Amaral, Tiago Ribeiro de Oliveira, Jéssica Katelyn Siqueira Vieira, Claudia Maria Cabral Moro Barra, Deborah Ribeiro de Carvalho, Patrícia Duarte Simões Pires, Harki Tanaka)
Diabetic Retinopathy (DR) is one of the most common microvascular complications presenting by patients diagnosticated with diabetic diseases. Uncontrolled hyperglycemia may manifest as visual impairment and blindness. The early detection of DR is essential to minimize the risk and consequence of visual diminishing. The standard gold diagnoses tool relies on different imaging modalities and requires a judgment of expert photographers, which are not available in most of the primary care centers or remote location. In that scenario, an automate or semiautomated DR screening systems can contribute to improving the accuracy of the diagnostic. Thus, we performed a Systematic Review and Meta-Analysis to evaluate the Decision Support Systems (DSS) in diagnosing DR. The overall Diagnostic Odds Ratio was 73.15 (95%CI: 37.54-142.50), sensitivity was 97.70 (95%CI: 97.50-97.90) and specificity was 90.30 (95%CI: 90.00-90.60). Our results corroborate with the concept of usefulness of DSSs in early diagnosis, screening and preliminary evaluation of suspicious images of DR
Mr. Diego Garcia
Pontifícia Universidade Católica do Paraná
Thursday
29 Aug 2019
08:10 - 09:50
T2-09
HIS - Software development and evaluation
Room: Gratte Ciel 3
Chairman 1: Elske Ammenwerth
08:10 - 08:30
User-Centered Design of the C3-Cloud Platform for Elderly with Multiple Diseases – Functional Requirements and Application Testing (Lamine TRAORE, Ariane Assélé Kama, Sarah Lim Choi Keung, Liran Karni, Gunnar O Klein, Mikael Lilja, Isabella Scandurra, Dolores Verdoy, Mustafa Yuksel, Theodoros N. Arvanitis, Rosy Tsopra, Marie-Christine JAULENT)
The number of patients with multimorbidity has been steadily increasing in the modern aging societies. The European C3-Cloud project provides a multidisciplinary and patient-centered “Collaborative Care and Cure-system” in the management of elderly with multimorbidity, enabling continous coordination of care activities between multidisciplinary care teams (MDTs), patients and informal care givers (ICG). In this paper, we report how various components of the infrastructure were tested to fulfill the functional requirements and how the entire system was subjected to an early application testing involving different groups of end-users. MDTs from participating European regions were involved in requirement elicitation and test formulation, resulting in 57 questions, distributed via an internet platform, to 48 test participants (22 MDTs, 26 patients) from three pilot sites. The results indicate an overall high level of satisfaction for all Information and Communication Technologie (ICT) components among the users. The early testing also provided user feedback important to consider for technical improvement of the entire system. 
Mrs. Marie-Christine JAULENT
INSERM
08:30 - 08:50
IEC 62304 Ed. 2 -- Software Life Cycle Standard for Health Software (Alpo Värri, Patty Krantz-Zuppan, Richard de la Cruz)
The quality of software is high in medical devices due to the strict regulatory requirements and their implementation in the software development processes through the use of the IEC 62304 standard. The goal of this standard revision project was to extend the scope of the standard to all health software and also to bring the requirements of the 12 year old standard back to the state-of-the-art including provisions for cybersecurity. The joint IEC/SC62A and ISO/TC215 project team revised the standard and adapted its risk management, usability and security requirements to serve both the medical device industry and the overall health software industry. The resulting second version of the standard has gone through a multistage global voting process to achieve a consensus of the requirements to serve both these communities. The resulting standard has potential to have a major impact on the quality of software used in health care globally.  
Mr. Dr. Alpo Värri
Tampere University
Alpo Värri is an associate professor of health informatics in Tampere University. He research interests have included physiological signal processing and pattern recognition. He has also been active in health informatics standardisation in CEN/TC251 and ISO/TC215.
08:50 - 09:10
Model-Driven Architecture (MDA) based software development for epidemiological surveillance systems (Gaoussou Camara, Hippolyte Tapamo, Azanzi Jiomekong, Julien Dupouy)
Epidemiological surveillance systems enable to collect, analyze and disseminate information on the monitored disease to different stakeholders. It may be done manually or using a software. Given the poor performances of manual systems, the software approach is generally adopted. Epidemiological surveillance systems are based on existing softwares, softwares developed from scratch given the specifications or softwares provided by a vendor. These solutions are not always suitable because epidemiological surveillance systems evolve quickly (new drugs, new treatment protocols, etc.), leading to software updates, which can take time (while waiting for a new version) and be expensive. In this article, we present the use of the Model-Driven Architecture (MDA) approach to model and generate epidemiological surveillance systems. The result is a complete MDA based methodology and tool to develop epidemiological surveillance systems. The tool was used to model and generate softwares that are now used for epidemiological surveillance of tuberculosis in Cameroon.
Mr. Hippolyte Tapamo
University of Yaounde I Sorbonne Université, IRD, UMMISCO
09:10 - 09:30
Prioritizing Features to Redesign in an EMR System (Samar Helou, Victoria Abou-Khalil, Goshiro Yamamoto, Eiji Kondo, Hiroshi Tamura, Shusuke Hiragi, Osamu Sugiyama, Kazuya Okamoto, Masayuki Nambu, Tomohiro Kuroda)
Redesigning Electronic Medical Record (EMR) systems is needed to improve their usefulness and usability.

For user-centered redesign, designers should consider which EMR features are the most important to the users. However, prioritizing the EMR features is complicated because: (i) EMR systems involve multiple users with different, and sometimes conflicting, priorities and (ii) targeting one feature will affect other features of the EMR system.

In this work, we propose a method for prioritizing the features to target when redesigning an EMR system. The method takes into consideration the different priorities of the users and the relationships between the different features. We illustrate the method through a case study on redesigning EMR systems in Japanese antenatal care settings.

Our results show the importance of considering the different types of EMR users and the relationships between different EMR features. Designers could use the proposed method as a decision-aid tool in EMR redesign projects.
Ms. Samar Helou
Kyoto University
09:30 - 09:50
Making Usability Testing of Health IT Practical and Efficient: Development of an Integrated Usability Toolkit for Healthcare IT (Andre Kushniruk, Elizabeth Borycki, Joseph Kannry)
In this presentation we describe an integrative methodological approach which is aimed at making usability testing of healthcare information technology  (HIT) more practical and efficient.  It has been recognized that the usability of healthcare IT has become an ongoing issue and as a result many usability studies have been conducted to improve the situation. However, usability issues persist. In this podium presenation we describe our most recent work in integrating several methodological components with the objective of streamlining and improving the usability analysis of HIT. 
Mr. Andre Kushniruk
Thursday
29 Aug 2019
08:10 - 09:50
T2-08
Interoperability
Room: Tête d'or 2
08:10 - 08:30
Enterprise Architecture in Hospitals: Resolving Incongruence Issues (Anne Kristin Ajer, Eli Hustad, Polyxeni Vassilakopoulou)
Enterprise Architecture allows addressing technologies and processes in a holistic way and mirrors choices related to process standardisation and data integration. It has the potential to address long-standing problems in health information systems related to fragmented IT portfolios, immature IT infrastructures, and silo-structured organising. Despite thisNevertheless, uptake of Enterprise Architecture in hospitals has been slow. To understand the issues related to this slow uptake we have undertaken an interview study with architects and managers. The issues identified reveal a level of incongruence between healthcare as a domain and the practice of EA. Specifically, by analysing the experiences of architects and managers we identified four different areas of such incongruence that create the need to reconcile a) Bottom-up vs Top-down Planning b) Clinical vs Systems´ Knowledge, c) Local vs Global Arrangements and d) Patient Safety vs Patient Privacy. Building on prior related research we propose ways for resolving the incongruence issues identified.
Mrs. Polyxeni Vassilakopoulou
University of Agder
08:30 - 08:50
Preliminary Assessment of the Interoperability Maturity of Healthcare Digital Services Vs Public Services Of Other Sectors (Angelina Kouroubali, Anastasia Papastilianou, Dimitrios G. Katehakis)
The development of electronic services for healthcare presents challenges related to the effective cooperation of systems and stakeholders in a highly regulated environment. Assessing the interoperability maturity of the provided services helps to identify interoperability issues in public administration. This paper presents a typical healthcare digital service: the inpatient admission in a public hospital in Greece. The Interoperability Maturity Model (IMM) is applied to assess its maturity, identify improvement priorities, and compare it with digital services of the healthcare sector. An analysis is also performed to compare a group of fourteen healthcare digital public services with sixty-seven public services of other sectors in the country. The IMM is a useful tool to facilitate awareness raising and priority setting concerning interoperability in public administration. What is discovered, through this preliminary assessment, is that healthcare digital services seem to have higher overall interoperability maturity than those of other sectors in Greece.
Mrs. Dr. Angelina Kouroubali
Foundation for Research and Technology- Hellas
08:50 - 09:10
Re-architecting Interoperability: A Model for Governing Information Sharing for Health System Transformation (Dela Aghdasi, Selena Davis, Linying Dong, Karim Keshavjee)
Healthcare systems around the world are facing greater pressures to share digital data between organizations for advanced analytics and program management. Yet, tradition and legal barriers prevent the seamless transfer of data across institutional walls. There is a lack of an umbrella organization or a clear governance structure that represents all stakeholders that can legally hold all appropriate patient data and share it with key entities. In this podium abstract, we describe seven principles for data sharing that could become the basis for a shared vision for how data can flow seamlessly across health care institutions. We also describe a governance maturity model that allows organizations to assess their level of maturity and plan for achieving the next level. Finally, we consider the next steps for our research.

 
Ms. Dr Selena Davis
09:10 - 09:30
Service-Oriented Device Connectivity: Device Specialisations for Interoperability (Björn Andersen, Simon Baumhof, Josef Ingenerf)
There are IEEE 11073 standards for foundational, structural, and semantic point-of-care medical device interoperability, but the first devices with this interface have yet to enter the market. One of the missing pieces for implementation and approval are Device Specialisations that specify how to use information and service models to represent a specific type of device on the network. Required and optional metrics need to be standardised as well as nomenclature terms, units of measure, and extension points. Finally, device-to-device interaction at runtime has to be defined for automatic verification during testing and approval. Applications include C-arm fluoroscopes used in different clinical settings.
Mr. Björn Andersen
University of Lübeck
09:30 - 09:50
Towards a Digital Lean Hospital: Concept for a Digital Patient Board and its Integration with a Hospital Information System (Massah Hamidi, Piratheepan Mahendran, Kerstin Denecke)
Lean management applied to healthcare aims at creating a maximum value for patients by reducing waste and waits. It puts the patient’s needs center stage, emphasizes employee involvement and continuous improvement. To realize this, visual tools such as the huddleboard or the patient board are implemented in hospital wards. The boards are currently realized by whiteboards or flipcharts, which leads to duplicated data entries and loss of information. The objective of this work is to introduce a concept for digitalizing the patient board and integrate with a hospital information system (HIS) for improved data availability. Data on appointments, personnel planning and master patient data can be directly accessed from the HIS database. A digital patient board has several benefits: data can be collected from information systems, making it obsolete to record information several times. Even more functionalities in particular those supporting the communication between a patient and a healthcare team can be included by means of a digital board which improves patient involvement.
Ms. Dr. Kerstin Denecke
Bern University of Applied Sciences
Thursday
29 Aug 2019
11:50 - 13:10
T2-15
Patient centered systems
Room: Tête d'or 2
Chairman 1: Petra Knaup
11:50 - 12:10
A theory-informed digital health intervention in people with severe mental health problems (Sandra Bucci, John Ainsworth, Christine Barrowclough, Shon Lewis, Gillian Haddock, Katherine Berry, Richard Emsley, Dawn Edge, Matt Machin)
There is an important gap in scaling up psychosocial interventions for people with severe mental health problems so that these interventions are not only widely available but also delivered in a timely manner. We examined the feasability of adapting a psychological intervention traditionally delivered face-to-face onto a digital platform. We report both the clinical and technical processes used to adapt and develop the digital platform in a group of people in the early phase of psychosis. The digital platform prompts people to engage with the intervention multiple times a day over a 12-week period. Participants are also able to access a repository of multi-media content to support their mental health. The digital platform has been successfully validated by participants registered with early intervention for psychosis services in the Northwest of England, UK and is currently being tested in a powered efficacy trial.
Mr. Matt Machin
The University of Manchester
12:10 - 12:30
Cancer Survivorship Patient Engagement Toolkit (CaS-PET): An Innovative Cancer Care Delivery Approach (Eun-Shim Nahm, Kenneth Miller Miller, Mary McQuaige, Shijun Zhu, Hyojin Son)
Introduction: Long-term cancer survival rates in the U.S. have significantly increased (15.5 million in 2018), and meeting survivors’ care needs is a population health issue. Cancer patients who transition from active treatment to long-term survivorship develop specific support needs, as they must adapt to a new “normal life” while still managing difficult symptoms associated with treatments. Most survivors are ill-prepared to manage these issues at home. To address these care needs the Institute of Medicine recommends that every cancer patient receive a survivorship care plan (SCP), which includes a treatment summary and a follow-up care plan. Although provision of an SCP is now a standard of practice, overall adoption rates have been low and the effectiveness of SCPs on health outcomes is inconclusive. In an effort to fill this gap, we developed an interactive electronic Cancer Survivorship Patient Engagement Toolkit (CaS-PET). CaS-PET was designed to deliver SCPs with proactive support and continued follow-up, leveraging health IT tools. The toolkit includes (1) SCPs, (2) bi-weekly follow-up using patient portal (PP) eMessages, and (3) online resources (“Well Beyond Cancer” [WBC]). The aim of this study was to test the preliminary impact of CaS-PET using a pilot sample. We hypothesized that at the end of the 3-month CaS-PET intervention, participants would demonstrate significant improvement in health-related quality of life (QoL), symptom burden, impact of cancer, fear of recurrence, level of physical activity, dietary behavior, patient-provider communication, adherence to treatment, and eHealth literacy.

Methods: This was a pre-post design study with participants recruited from a large cancer center located in an inner-city area. Patients were eligible if they were age 18 years or older, diagnosed with a solid tumor, and treated with curative intent within six months from enrollment. Participants could use the Internet/e-mail independently and either had an existing PP account or signed up for one prior to the start of the study. Data were collected at baseline and at the end of the CaS-PET intervention (3 months) online. Data were analyzed using descriptive statistics, linear mixed models, and content analysis (open-ended questions).

Results: A total of 30 cancer survivors (mean age, 5±13.6) participated in the study, and 27 completed the follow up survey. The majority of participants were female (76.7%, n=23) and black (60%, n=18). Half of participants (50%, n=15) were breast cancer survivors and 20% (n=6) were head and neck cancer survivors. At the end of the CaS-PET intervention, participants showed significantly improved QoL (p=.04) and reduced symptom burden (p=.018). In addition, physical activities and eHealth literacy showed a tendency toward improvement. Most participants reported that WBC helped them better manage their health (mean, 18.07±4.6 [3–21]).

Dicussion/Conclusion: Through the study we demonstrated that cancer centers can leverage health IT to deliver SCPs with necessary support. The findings suggest that CaS-PET can be an effective approach to meet the care needs of cancer survivors who are in transition. Further larger-scale RCTs are needed to test the effectiveness of the CaS-PET with survivors with diverse cancer types.
Ms. Dr. Eun-Shim Nahm
12:30 - 12:50
Characteristics and hospital activity of elderly patients receiving admission avoidance home visits – a population-level record linkage study (Maria Cristina Martin, Matt-Mouley Bouamrane, Paul Woolman, Kimberley Kavanagh, David Young)
As pressures on healthcare systems increase, due to an ageing population, hospital admission avoidance interventions have been emphasised. These interventions can be difficult to objectively evaluate due to non-randomised roll-out, requiring observational methods with carefully selected control groups. This study aims to identify the defining characteristics of elderly patients receiving admission avoidance home visits. We conducted a record linkage study using routinely collected data to compare characteristics and outcomes of the general ‘elderly’ population and a subset of ‘high risk’ patients. Intervention patients were found to have significantly different demographics and admission rates to the general population, having four times higher admission rates at baseline. However, they share similarities with ‘high risk’ patients, particularly in that after a period of increased admissions, both groups experienced a reduction in the following year. Identifying defining characteristics of the target intervention population will instruct the careful selection of a control group for evaluation.
Mrs. Maria Cristina Martin
University of Strathclyde
12:50 - 13:10
Evaluating the validity of a knowledge based system for proactive knowledge transfer for caregiving relatives (Dominik Wolff, Marianne Behrends, Thomas Kupka, Michael Marschollek)
The evaluation of the validity of a knowledge-based system is of great importance during its development. It determines whether the system represents the experts’ knowledge correct-ly. This is highly important, but also particularly difficult, if the expert knowledge is not explicit, but only implicit and tacit. In the following the validity’s evaluation of a system for edu-cation of caregiving relatives is presented. To evaluate the system's knowledge delivery strategy against the experts’ opin-ion, several fictious characters were created. The evaluation revealed inconsistencies in the knowledge base. After resolving these, the experts’ opinion is represented to a large extent by the system. Nevertheless, the used evaluation approach is not capable of detecting all inconsistencies. Therefore, a strong need of a system’s learning capacity to integrate feedback from a larger group of real caregiving relatives exists. In ad-dition, a rule-based component, representing disease specific knowledge, should be implemented.