Wednesday 26 April

Workshop: EFMI working group on translational health informatics – emerging technological approaches for addressing translational medicine needs

Translational medicine is a field focused on removing barriers in utilising new scientific discoveries in healthcare, moving from bench to bedside. The increased adoption of new open source tools such as TranSMART and i2b2 is complemented with the initiatives carried out for standardising Genetic Testing Report and OMICS information. This workshop will analyse existing approaches adopted by open source initiatives and standard technologies in order to identify common strategies for addressing challenges associated with management of information, data privacy and access control in order to promote the adoption of Translational Medicine in healthcare providers and research centres.

Organisers
Dr Alberto Moreno-Conde; Institute of Biomedicine of Seville

Dr Mauro Giacomini; University of Genoa

Jesús Moreno-Conde; Institute of Biomedicine of Seville

Dr Riccardo Bellazzi; University of Pavia

Carlos Luis Parra-Calderón; Institute of Biomedicine of Seville

Dr Amnon Shabo; Philips

Linking health and social care

08:30 – 08:45
Generation Scotland: electronic health record linkage in practice
Campbell A, Boekel L, Porteous D

08:45 – 09:00
Data linkage in social care: a pilot project
Orrell A, Heaven M, Roberts D, Parry M, Robinson C

09:00 – 09:15
Linking mental health to social network data
Wongkoblap A, Vadillo MA, Curcin V

09:15 – 09:30
The effect of improved identifiers on linkage of electronic health data for neonatal bloodstream infection surveillance
Fraser C, Gilbert R, Muller-Pebody B, Harron K

09:30 – 09:45
Effects of national housing quality standards on hospital emergency admissions: a quasi-experiment using data linkage
Rodgers S, Poortinga W, Bailey R, Johnson R, Dunstan F, Berridge D, Lyons R

Trials and big data

08:30 – 08:45
The effects of heterogeneity in the comparative effectiveness of individual treatments in randomised trials
Pericleous P, van Staa T, Sperrin M

08:45 – 09:00
IT infrastructure of an oncological trial where xenografts inform individual second line treatment decision
Lindoerfer D, Mansmann U

09:00 – 09:15
Methods for analysing large routine clinical datasets, with applications to electronic health records from the Clinical Practice Research Datalink
Rhodes K, Turner R, Payne R, White I

09:15 – 09:30
Medical and healthcare curriculum exploratory analysis
Komenda M, Karolyi M, Pokorná A, Vaitsis C

09:30 – 09:45
Chart-adapt: bringing the benefits of big data technologies to the critical care unit
Brankin P, Moss L, Piper I, Hawthorne C, Kinsella J, Shaw M, Elliot R

Diabetes and ageing

08:30 – 08:45
My diabetes my way: user experiences of an electronic personal health record for diabetes
Cunningham S, Allardice B, Wake D

08:45 – 09:00
Involving physical activity in insulin recommender systems with the use of wearables
López B, Pozo A, Torrent-Fontbona F

09:00 – 09:15
Shared decision-making via personal health record technology for routine use of diabetic youth: a study protocol
Davis S, Roudsari A, Courtney K

09:15 – 09:30
POWER2DM: Predictive model-based decision support for diabetes patient empowerment
Namli T, Gönül S, De Graaf A

09:30 – 09:45
Increasing access to healthcare in rural Africa using telemedicine: using an mHealth system for diabetes patients in Cameroon as a case study
Holl F, Munteh P, Burk R, Swoboda W

09:45 – 10:00
A medication reminder mobile app: does it work for different age ranges?
Fallah M, Yasini M

Barriers and facilitators of informatics interventions

08:30 – 08:45
An approach for enhancing adoption, use and utility of shared digital health records in rural Australian Communities
Almond H, Cummings E, Turner P

08:45 – 09:00
Documentation time during outpatient consultations with a new EHR: fears and figures
Joukes E, Cornet R, Abu-Hanna A, de Keizer N

09:00 – 09:15
Exploring innovation capabilities of hospital CIOs: an empirical assessment
Esdar M, Liebe JD, Weiß JP, Hübner U

09:00 – 09:15
The invisibility of disadvantage: why do we not notice?
Showell C, Cummings E, Turner P

09:30 – 09:45
Using healthcare work process modelling in hospitals to increase the fit between the healthcare workflow and the electronic medical record
Morquin D, Ologeanu-Taddei R, Watbled L

Care pathways and data linkage

08:30 – 08:45
A study investigating the use of routinely collected health data to identify current treatment pathways among people with age-related hearing loss
Evans HE, Costafreda Gonzalez S, Denaxas S, Hayward A, Livingston G,
Schilder A

08:45 – 09:00
Using linked data from health and social care to understand patient pathways and high resource users in Scotland
Ward H, Baird D, Lee A, Mooney A, Munro J

09:00 – 09:15
Improving the accessibility and interpretation of advanced analytics when monitoring the quality and safety of patient outcomes
Dawe H

09:15 – 09:30
Care pathways related to Scottish Ambulance Service contacts for people with psychiatric or self-harm emergencies
Duncan E, Best C, Dougall N, Skar S, Fitzpatrick D, Evans J, Corfield A, Stark C, Wojcik W, Goldie I, White C, Snooks H, Maxwell M

09:30 – 09:45
Development of a questionnaire for determining important information needed in hospital care coordination
Peltonen LM, Lundgrén-Laine H, Siirala E, Löyttyniemi E, Aantaa R,
Salanterä S

09:45 – 10:00
Appraising healthcare delivery provision: A framework to model business processes
Luzi D, Pecoraro F, Tamburis O

Panel: Diversity in health informatics – empowering women in health IT

Diversity drives innovation. The healthcare workforce is predominately female, while health informatics development force is largely male; an imbalance that hinders diffusion of innovation. This panel will initiate a conversation on whether constrains and traditions impede necessary advancement, and propose strategies for equal opportunities. We seek answers to the following questions; how can health informatics effectively use diversity to drive change, innovation and transformation? Can stories by female entrepreneurs, change makers and leaders bring perspectives that improve working conditions and shape patient care? The audience will be invited to share ideas and suggest tools and strategies to further foster diversity

Panellists
Professor Anne Moen; Institute for Health and Society; University of Oslo

Anna Sort; PlayBenefit

Jane Dwelly, HIMSS UK

Dr Petra Wilson; Health Connect Partner

Maxine Macintosh; HealthTech Women UK

Catherine Chronaki; HL7 Foundation

Panel: Making the LHS a reality with data standards: what do we have and what do we need?

The Learning Health System (LHS) has been seen as a potential solution to many of the problems of early 21st century evidence-based medicine. To deliver on this promise, the LHS needs to be ubiquitous, and capable of operating within the context of legacy EHR and other health and social care related systems. Yet the LHS requires much greater management of clinical meaning than has been the case in most healthcare interoperability projects. This panel will discuss existing data standards and their readiness to maintain knowledge in machine-usable forms, what additional standards may be required, and the role of asset registers.

Panellists
Chair: Professor Brendan Delaney; Imperial College London

Professor Charles Friedman; University of Michigan: Data standards and knowledge representation in the LHS

Dr Michael Ibara; Collaborative Data Interchange Standards Consortium: eSource and linking with registries, clinical trials and mobile health

Dr Vasa Curcin; King’s College London: The EU FP7 TRANSFoRm project and using ontologies to add context to standards

Professor Dipak Kalra; EuroRec: The European Institute for Innovation Though Health Data (I~HD) Interoperability Asset Register

Population health and epidemiology

08:30 – 08:45
Forecasting areas with persistently high rates of potentially preventable
hospitalisations: utilising high capacity parallelisation in an application of exhaustive model selection with repeated cross-validation
Tuson M, Turlach B, Kok MR, Vickery A, Whyatt D

08:45 – 09:00
Using electronic health records to assess depression and cancer comorbidities
Mayer MA, Gutierrez A, Leis A, De la Peña S, Sanz F, Furlong LI

09:00 – 09:15
Implementation of a Charlson comorbidity index for the SAIL databank
Rees A, Wang T, Thayer D, Atkinson M

09:15 – 09:30
Patient activation is associated with fewer visits to both general practice and emergency departments: a cross-sectional study of patients with long-term conditions
Deeny S, Barker I, Steventon A

09:30 – 09:45
Identifying anonymous residence types using administrative datasets
Tingay K, Roberts M, Musselwhite C

09:45 – 10:00
Impact of age on relative survival following transcatheter aortic valve implantation
Martin G, Sperrin M, Hulme W, Buchan I, Mamas M

Text processing

08:30 – 08:45
Improving terminology mapping in clinical text with context-sensitive spelling correction
Dziadek J, Henriksson A, Duneld M

08:45 – 09:00
Medical text classification using convolutional neural networks
Hughes M, Li I, Kotoulas S, Suzumura T

09:00 – 09:15
Acronym disambiguation in Spanish electronic health narratives using machine learning techniques
Rubio Lopez I, Costumero R, Ambit H, Gonzalo C, Menasalvas E, Rodríguez González A

09:15 – 09:30
A case study on sepsis using PubMed and deep learning for ontology learning
Arguello Casteleiro M, Maseda Fernandez D, Demetriou G, Read W, Fernandez-Prieto MJ, Des Diz JJ, Nenadic G, Keane J, Stevens R

09:30 – 09:45
Automated classification of semi-structured pathology reports into ICD-O using SVM in Portuguese
Oleynik M, Patrão DF, Finger M

09:45 – 10:00
Internet of Things in health trends through bibliometrics and text mining
Konstantinidis S, Billis A, Wharrad H, Bamidis P

Workshop: IP commercialisation and exploitation from health informatics research

The purpose of this workshop is to discuss the challenges faced by researchers in protecting new technologies and solutions arising from health data research, and to present some clear routes for the protection of new technologies. IP specialists from Maucher Jenkins will outline considerations that need to be made in the protection and exploitation of health data research, and will provide advice and guidance as we explore a range of potential scenarios.

Organisers
Reuben Jacob, Partner; Maucher Jenkins

Fiona Kellas, Associate; Maucher Jenkins

Longitudinal and temporal data analysis

10:30 – 10:45
Informative observation in health data: association of past level and trend with time to next measurement
Sperrin M, Petherick E, Badrick E

10:45 – 11:00
From single cells to populations: modelling and analysing the dynamics of disease progression from cross-sectional studies using phenotypically-driven pseudotime
ordering
Campbell K, Yau C

11:00 – 11:15
Multivariate and longitudinal health system indicators
Powell GA, Luo Y, Verma A, Stephens DA, Buckeridge DL

11:15 – 11:30
Precision epidemiology for kidney disease in the East Midlands
Major R, Xu G, Shepherd D, Brunskill N

11:30 – 11:45
Patient stratification in psoriasis using large-scale patient-level data
Geifman N, Peek N, Buchan I, the PSORT Executive Committee

11:45 – 12:00
Latent profile analysis to learn subgroups of lung function for personalised medicine
Belgrave D, Granell R, Simpson A, Lowe L, Buchan I, Henderson J, Custovic A

Panel: Informatics for suicide risk detection and prevention

We will explore the benefits and challenges of using informatics for suicide risk detection and prevention. How far is informatics likely to help in clinical risk detection? What are the obstacles that need to be overcome to develop decision support tools usable by clinicians? Is there scope to feedback patterns of behaviour to patients or to collaborate with patients in devising self-management tools? Could health informatics in the form of interactive software or educational apps be used as successfully as face-to-face strategies to reduce suicide attempts? Or will there be technical, psychological, ethical, organisational, cultural, economic or other reasons why these are difficult to adopt?

Panellists

Professor Enrique Baca-García; Department of Psychiatry, Fundación Jiménez Díaz Hospital, Madrid: Emerging trends for studying suicide attempts using data mining to predict future behaviour

Dr Rina Dutta; King’s College, London: Different strategies for natural language processing of free text written by clinicians to identify subtle markers of suicide risk

Dr Gergö Hadlaczky; Stockholm County Council Centre for Suicide Research and Prevention: Challenges in suicide risk assessment using statistical methods

Design, co-design, and development

10:30 – 10:45
Co-designing eHealth for co-care of parkinson’s disease: participants’ experiences
Wannheden C, Hvitfeldt-Forsberg H, Granström E, Eftimovska E, Revenäs Å

10:45 – 11:00
Developing the Safety Case for MediPi: An open-source platform for self managment
Habli I, Carr A, Murphy D, Dugdale I, Dyson A, Robinson R

11:00 – 11:15
Meeting clinicians’ needs in the design of a personal health record
Tite I, Potts H

11:15 – 11:30
Exploring the gap between mHealth app design practices and knowledge derived from scientific research
Panteleev V, Peute L, Wildenbos GA

11:30 – 11:45
Missing feature of health app development: patients
Nguyen A, Baysari M, Fernon A, Wong M, Day R

11:45 – 12:00
UK health and social care case studies: iterative technology development
Dawson T, Blanchard A, Gilbert L

Workshop: Reinventing heuristic evaluations: exploring methods to engage clinicians in usability evaluations

Usability evaluations are essential to the success of health information system implementation, but are often costly and dependent on right expertise being available. Heuristic Evaluation (HE) is considered a straightforward method consisting of clear stages. Involving clinicians in HE may facilitate usability evaluations in healthcare, yet there are challenges. Many questions remain unanswered regarding how to implement user involvement in HE; where and how could clinicians best be involved in this process? To what level of autonomy and with what added benefit? In this workshop, we will explore experiences of involving clinical users in HE, discuss challenges and best practice.

Organisers

Dr Maria Hägglund; Health Informatics Centre, Karolinska Institutet

Dr Romaric Marcill; INSERM CIC-IT Lille

Dr Sylvia Pelayo; EVALAB INSERM CIC-IT Lille

Dr Isabella Scandurra; Örebro University

Workshop: Using patient-reported data for research and to improve health outcomes and services: identifying opportunities and challenges

The advent of new information technologies, such as smartphones, wearables and social media, has created an unprecedented opportunity for acquiring health data directly from patients. Patient-reported data have the potential to enrich population-based research, improve disease management, and guide redesign of healthcare services. To unlock this potential, we need to understand the main opportunities and challenges of patient-reported data. This workshop aims to identify these opportunities and challenges, and to explore whether there is an appetite for establishing a special interest group around patient reported data within the health informatics community.

Organisers
Dr Sabine van der Veer; The University of Manchester

Professor Will Dixon; The University of Manchester

Dr Chris Gibbons; University of Cambridge

Dr Goran Nenadic; The University of Manchester

Dr Retha Steenkamp; UK Renal Registry

Panel: What does the public think about the commercial use of health data?

The commercial use of health data is a controversial topic, whether in collaboration with the public sector or for internal use by the company. Over the past few years, there has been a consistent message that many citizens do not support the idea of “their” health data being used by commercial companies. Citizens may be more accepting of commercial uses that have explicit public benefit and less so for company profit.

Four presentations and discussions will describe the nuanced public views and consider how public authorities should decide who gets access to health data and for which commercial uses.


Panellists

Chair: Dr Mary Tully; The University of Manchester: Introduction

Dr Natalie Banner; Wellcome Trust: The One-Way Mirror: Public attitudes to commercial access to health data

Dr Mhairi Aitken; Farr Institute Scotland: Discrete choice experiment on commercial use of health data

Kyle Bozentko; Jefferson Center, Minnesota: Citizen’s juries on the commercial use of health data

Dr Malcolm Oswald; The University of Manchester: So What Should Public Authorities Do?

Panel: Connected Health Cities: creating learning health systems in North England

The Connected Health Cities (CHC) programme aims to develop learning health systems in four city regions in North England over a 3-year time period (2016-2019). In particular, the programme seeks to create civic partnerships exploiting data to:

• drive public sector reform by deriving actionable information from routinely-collected health data
• fuel region-wide health science that citizens trust; and
• accelerate business growth for the digital health revolution

Central to each CHC is a combinatorial health innovation centre ("Ark") that assembles data, experts and technology. To apply and evaluate the methodology, each CHC has selected several care pathways that represent a specific regional need.

Panellists
Prof John Ainsworth; University of Manchester: Overview of the Connected Health Cities programme and information governance

Dr Niels Peek; University of Manchester: Clinical and behaviour change

Dr Stefan Williams; Bradford Institute for Health Research: Practical application of data analytics

Dr Dennis Kehoe; AIMES Grid Services: Technical infrastructure

Diabetes and long-term conditions

10:30 – 10:45
Co-morbid determinants of chronic disease progression: three explorations using biomarkers and health records
Kiddle S, Baker E, Quint J, Stewart R, Buchan I, Dobson R

10:45 – 11:00
Exposure to diabetes drugs and cancer incidence in a nationwide observational data linkage study
Farran B, McGurnaghan S, Colhoun H

11:00 – 11:15
Using Lambeth DataNet to identify ethnic variation in the control of hypertension
Ashworth M, Curcin V, Molokhia M

11:15 – 11:30
LDL-cholesterol is inversely associated with risk of heart failure: a replication study of two national databases of linked electronic health records
Moayyeri A, Brophy S, Rahman M, Denaxas S, Lyons R, Hemingway H

11:30 – 11:45
An algorithm to identify end stage renal disease in the UK biobank cohort
Nolan J, Zhang Q, Herrington W, Sudlow C

11:45 – 12:00
Dementia case ascertainment in population-based cohort studies: lessons from the Whitehall II study
Ly A, Wilkinson T, Schnier C, Singh-Manoux A, Kivimaki M, Brunner E, Sanchez A, Sudlow C

Natural language processing

10:30 – 10:45
Acquisition of expert/non-expert vocabulary from reformulations
Antoine E, Grabar N

10:45 – 11:00
Fast and simple text classification gets things done
de Bruijn B, Marshall MS, Dekker A

11:00 – 11:15
Personalised guideline-based treatment recommendations using natural language processing techniques
Becker M, Böckmann B

11:15 – 11:30
HTP-NLP: A new NLP system for high throughput phenotyping
Schlegel D, Crowner C, LeHoullier F, Elkin P

11:30 – 11:45
Natural language processing pilot study for clinical trial pre-screening through to enrolment
Thompson S

11:45 – 12:00
Temporal expression extraction and normalization in Italian clinical reports
Viani N, Napolitano C, Priori SG, Bellazzi R, Sacchi L