1. BUILDING THE FUTURE OF PERSONALIZED
HEALTHCARE
IN A DATA DRIVEN SOCIETY
University of Twente
University Medical Center Groningen
The Netherlands
Building the future of Health
June, 3-2016; Groningen
Lisette van Gemert-Pijnen
2. The University of Twente is noted for:
• Excellent education & research
• New technology as a catalyst for change, innovation and progress
• Combination of technology & social sciences
• Entrepreneurial attitude
Themes: ICT, Nano-, Bio-, Geo-Engineering, Management, Behavioral Science
26/08/2016
OUR PROFILE: HIGH TECH HUMAN TOUCH
4. • What are the paradigm shifts in Healthcare?
• What are the challenges in a data driven society?
• What are we doing? In the domain of safety
• Food for Thoughts
THIS TALK
BUILDING THE FUTURE OF PERSONALIZED HEALTHCARE
www.cewr.nl (persuasive technology lab)
5. 1. People-centered versus disease-centered
• Health as the ability to adapt and to self-manage, (Huber, 2011)
• Services are focused on individual needs and preferences
• No one size fits all
2. Medicine digitized, unplugged, democratized
• Bottom up
• From hospitals to self-organizing communities (resilience)
PERSONALIZED HEALTHCARE
PARADIGM SHIFTS
7. Amount of data is growing explosively
3. Breaking the wall of knowledge
4. Health Industry blurs medicine
DATA DRIVEN SOCIETY
PARADIGM SHIFTS
8. 5. Pervasive tech: breaking wall of connectivity
• A fusion of Technologies (mobile health environments; IoT)
• Cloud based Healthcare Information Technology
6. New Science: Tech & Health & Behaviors
• Data Stewardship: Safety, Security (e.g. Personal Health Train)
• Data Analytics: Algorithms to understand behaviors
• Data Wisdom: to add value to health &wellbeing
DATA DRIVEN HEALTHCARE
PARADIGM SHIFTS
9. The datification of our world gives us
boundless data in terms of Volume,
Velocity, Variety and Veracitiy
Advanced analytics allows us to
leverage all types of data to gain
insights and add Value
Marr 2015
CHALLENGE: BIG DATA; NOT ALL DATA IS BIG
13. 13
CROSSING BOUNDARIES: CEHRES ROADMAP (VAN GEMERT, 2011)
Why IT? How does IT work? Does IT help? What is ITs impact?
needs & values usability and persuasiveness is anyone getting better? implementation
facilitators & barriers compliance to IT physical & mental & social maintenance
Needs assessments Persuasive Designs Health Behaviour Theories Business models
14. Crossing borders, tech to develop digital surveillance systems to improve health &wellbeing
Crossing boundaries, tech as a method to better measure, aggregate and make sense of behavioral,
clinical and environmental data
STRUCTURAL HYGIENE
BIG DATA TO SUPPORT HEALTH & WELLBEING
15. Safety and Superbugs; a wicked problem
Lack of cooperation across countries, across continents
Lack of regulations, guidelines, laws
Profit-driven instead of needs-driven supply (farming)
Knowledge gap; Inadequate education, information
Inadequate surveillance, Insufficient diagnosis
Inadequate infection control practices, lack of resources,
compliance
Lack of research, development AB slow and no priority
15
18. COMPLIANCE: DEMAND FOR TAILORED INSTRUCTIONS
BOTTOM UP DEVELOPMENT ANTIBIOTIC STEWARDSHIP INFORMATION SYSTEMS
19. Highly Resistant Micro Organism, e.g. MRSA; Zoonotics
(Animal>humans)
Digital surveillance to track, trace infections and to develop an
EWS and predictive model to detect and prevent outbreaks
19
BIG DATA IN INFECTION PREVENTION
Demand for EWS & predictive modelling
20. • Integrating geospatial data with epidemiological and clinical data
• to develop a smart Early Warning System
• Path of movements (sensors data analytics inside/outside hospital)
• Pathogens and HRMO are monitored real-time (over 5 years)
• Predictive modelling; new computational methods for analysing geospatial and
laboratory data
26-8-2016 20
EARLY WARNING SYSTEM
CROSSING BORDERS & BOUNDARIES
21. Development of Predictive model to analyse geospatial, laboratory,
epidemiological and clinical data
1. Exploratory spatial analysis of historical data to investigate emerging
patterns
2. Regression model will be developed to estimate the posterior distributions
of outbreaks (integrating clinical, epidemiological & geospatial data)
3. Predictive modelling will be used at the level of (sub)units in a hospital
26-8-2016 21
PROACTIVE DECISION MAKING
COOPERATION HEALTH-BUSINESS-SCIENCE
22. User centred methods to design a data dashboard
- To tailor the predictive decision model to end users (A-Team
members)
- CeHRes- roadmap for eHealth design will be used
- Persuasive design and usability principles to optimize the system
and comprehensible visualization of data
26-8-2016 22
PERSUASIVE DESIGNS
COOPERATION WITH HCWS
23. Shared Decision making support during outbreaks
Dealing with dilemmas (infections impact society)
Dealing with pressure, emotions, unclear regulations etc.
Dealing with stakeholders
Target users:
professionals from human, veterinary & public health domains dealing with infection prevention &
control (zoonotic case)
Agile development (Avian Influenza & MRSA) with stakeholders, professionals
Coop with T-Xchange (Science-Business-Health)
DILEMMA GAMES TO MANAGE OUTBREAKS
EDUCATION PROFESSIONALS MED-VET
24. 24
E-LEARNING ASP
GAME BASED TRAINING ENVIRONMENT MED-VET (GAMES FOR HEALTH)
How to design and develop performance assessment methods and
techniques, such that the player is unaware of it? Including feedback and
dynamics regarding risk communication and game models.
How to evaluate the serious games and its effectiveness in the virtual and real
world?
25. Implementation: Stakeholder Business model
Maturity Scale ASP; implementation advice
ASP: no one size fits all
Tailoring interventions, to local resources, guidelines
Support for persuasive Auditing
Benchmarking hospitals
27. Big Data Safe Health: STRUCTURAL STEWARDSHIP
food for thoughts
Create Data Wisdom
those who generate data are not the ones that have the
knowledge to analyse, those who analyse lack domain insight
Big data a supplement no substitute of traditional data collection
Ethical considerations (over-under prediction; data management)
Accountability; Who has to prove what and how it is regulated?
Interpretation; Data versus a Clinical eye
26-8-2016 27
28. Search for patterns rather than testing hypotheses
Critical volume, variety, veracity of data
Beyond RCTs; Life Logging
Power of Analytics (Machine learning)
Bottom up evidence (reverse epidemiology)
FOOD FOR THOUGHTS
CRITICAL EVIDENCE
29. SAFETY: CREATIVE BUILDING, NO ROOM FOR SAFE CHILDBIRTH
COCREATION WITH HCWS A MUST!
Simon et al, nederlands tijdschrift voor anesthesiologie, april 2016
Delivery Room
Operating room
Prone to complications:
300 meters distance and 2 floors up!
38. COMPUTERS WITH ATTITUDE NOT ON THE HORIZON
It Was A Bad Idea For Watson The Supercomputer To Learn The Urban
Dictionary…
Value: Sense making Communication (NLP, contextualized)
40. BIG DATA
WEARABLES @WORK; @ HOME
Data analytics: Does IT work? Help?
Engagement: persuasive feedback
Awareness of risks
Prevention of complications
40
Twente-Thales ImEdisense
Telemonitoring in stAble Chronic Heart
Failure
(Twente TEACH)
41. BIG DATA IN PSYCHIATRY
JUST IN TIME COACHING
Data analytics * Design Persuasive Coaching strategies (using virtual reality)
…to better measure, aggregate and make sense of behavioral, psychosocial,
biometric and geodata to develop personalized coaching programs,
….to make predictions about how a given individual will proceed