Is Pervasive Healthcare Old Wine on a New Bottle?

Slide 1: Is 'Pervasive Healthcare' old wine on a new bottle – or is it a real, but emerging, research discipline? Jakob E. Bardram

Slide 2: 2

Slide 3: The Age Tsunami US Demand/Supply of Nurses 3

Slide 4: 4

Slide 5: Source: Eric Dishman. Inventing wellness systems for aging in place, IEEE Computer 37:5 (May 2004), 34–41.. 5

Slide 6: Changing the Centralized Model of Healthcare Acute → Continuous Hospitalization → Home & out-patient Reactive → Pro-active & Preventive IT → Assistive Technology Centralized → Pervasive Sampling → Monitoring Doctor-centric → Patient-centric 6

Slide 7: Pervasive Healthcare • Application of pervasive computing, ubiquitous computing, proactive computing, ambient intelligence technologies for healthcare, health, and wellness management. • Second, it is about making healthcare pervasively available everywhere, anytime, and to anyone. • In essence, pervasive healthcare addresses a set of related technologies and concepts that help integrate healthcare more seamlessly to our everyday lives, regardless of space and time. Source: Korhonen, Ilkka, and Bardram, Jakob B. Guest editorial introduction to the special section on pervasive healthcare, IEEE Transactions on Information Technology in Biomedicine 8:3, 2004, 229–234. 7

Slide 8: Agenda • Historical Roots – Biomedical Engineering, Medical Informatics, UbiComp • Characteristics of Pervasive Healthcare • Research Themes • Examples – Home based monitoring of vital signs – Pervasive Computing in Hospitals • Methods – Evidence-Based Medicine – Clinical Proof-of-Concept • Is the wine new? 8

Slide 9: 9

Slide 10: 10

Slide 11: 11

Slide 12: Historical Roots 12

Slide 13: Biomedical Engineering – BME • Biomedical engineering (BME) is the application of engineering principles and techniques to the medical field. • BME combines the design and problem solving skills of engineering with the medical and biological science to help improve patient health care and the quality of life of healthy individuals. • Research Areas – Bioelectrical and neural engineering – Biomedical imaging and biomedical optics – Biomaterials – Biomechanics and biotransport – Biomedical devices and instrumentation – Molecular, cellular and tissue engineering – Systems and integrative engineering 13

Slide 14: Biomedical Engineering 14

Slide 15: Medical Informatics – MI • Medical informatics (MI) is the intersection of information science, computer science and health care. • MI deals with the resources, devices and methods required to optimize the acquisition, storage, retrieval and use of information in health and biomedicine. • Health informatics tools include not only computers but also – clinical guidelines, – formal medical terminologies, and – information and communication technology(ICT) 15

Slide 16: Medical Informatics • Hospital Information Systems • Electronic Patient Record – Medicine Charts – Nursing Records • Clinical Decision Support Systems • Integration • Standards – DICOM, HL7, • Medical vocabularies – SNOMED, … 16

Slide 17: Ubiquitous Computing Ubiquitous Mobile Internet PC Mini Mainframe 17

Slide 18: Ubiquitous Computing • Embedded / invisible / ambient computing • From 1:1 to N:N computing • Mobility and Wireless connectivity • Collaboration • Sensor networks • Context-aware Computing • Capture and Access • From “computer” to “tool” 18

Slide 19: Pervasive Healthcare – Characteristics • Technology – Sensor technology and networks – Embedded and mobile devices – Context-aware adaptation – Capture & Access • Clinical approach – Pro-active and preventive – Patient-focused – Monitoring rather that sampling – Assistive Technology rather than Information Technology • Research – Multi-disciplinary – from field studies to hardware design – Proof-of-Concept – rather than evidence-based medicine 19

Slide 20: Pervasive Healthcare – Research Themes • Monitoring • Assistive Technologies • Preventive and pro-active health systems • Self-care & Self-treatment • Medication support and compliance • Capture and Access, Training • Clinical Support Systems • Software Architecture • Sensor and Network Design • Field Studies • Persuasive technologies for better health • … 20

Slide 21: Medication I 21

Slide 22: Medication II 22

Slide 23: Telemedicine? 23

Slide 24: Pervasive Monitoring Bodyworn Monitors Mobile Monitoring Body Sensor Wireless Monitors Network MyHeart Project 24

Slide 25: Challenges in Monitoring • Robust measurement and processing methods requires access to large and representative real data sets – Real cases in real environment with real problems and artifacts – Reference data - real well-being - collected in parallel – Similar problem when collecting evidence for correct functioning and usefulness of the method - required for evidence based medicine (EBM) • How to reach this - especially for long term (months - years)? – Motivation of (many enough real) subjects to wear/use often bulky and error-prone prototypes – Ethics? – Practical and economical issues: prototype costs (many copies needed), maintenance costs (battery replacements, data transfer, calibration, etc.) • Result: few success stories so far… Source: Ilkka Korhonen 25

Slide 26: Example I ElderTech – Technologies for Elders 26

Slide 27: • Purpose – Self-care and independent living – Easy communication with clinical staff, relatives and peers – Continuous updated view on health status – Basis for pro-active clinical contingency management – Shared care – cooperation across clinical boundaries • Features – Monitoring – Blood Pressure and Weight (wireless) – Medication – administration and management – Communication & Coordination – “The Collaboration Book” • Deployment – 7 Homes, elders 70+ – Nursing staff, nurses and assistants – ~3 months – Qualitative data collection 27

Slide 28: Technical Setup 28

Slide 29: 29

Slide 30: 30

Slide 31: 31

Slide 32: 32

Slide 33: 33

Slide 34: 34

Slide 35: 35

Slide 36: 36

Slide 37: 37

Slide 38: 38

Slide 39: 39

Slide 40: Findings – Elders • Usability – Scale & BP monitor used frequently – The PC – 5 out of 7 did not use it • Communication – No changes experienced – But was not looking into the ‘collaboration book’ • Clinically, Self-care, Monitoring – Liked the monitoring – Increased their feeling of security/safety – Was trusting the staff to monitor their health data and react if necessary – Documentation of medicine intake was not considered relevant 40

Slide 41: 41

Slide 42: Findings – Healthcare Workers • Administration – Collaboration book – Integration with care system • Communication – Might improve communication with GP • Clinically – Felt uncomfortable – Responsibility of the GP – Extra work – felt not necessary • Remote monitoring and prevention – Indications – Specific groups of elders – diabetics, hypertension, … – Concerned about remote monitoring – “not the right picture” 42

Slide 43: Lessons learned about designing AT • Vital sign monitoring is ‘interesting’ – but introduces a huge responsibility for actually reading them • Communication and sharing seems to be just as interesting – between nurses/GP/hospital – between clinicians and citizens – between citizens • If “Information Technology” is part of the solution – then IT has to look considerable different that it does now! • Experimentation is essential in the design process – we actually do not know what we do – … what will work – … how to design it – … and how users will use it – hence, close-loop experimentation is essential 43

Slide 44: Example II The Interactive Hospital – Supporting Awareness in a Operating Ward 44

Slide 45: Whiteboards in Hospitals Source: J.E. Bardram, Temporal Coordination - On Time and Coordination of Collaborative Activities at a Surgical Department. Computer Supported Cooperative Work, 9(2):157-187, 2000. 45

Slide 46: 46

Slide 47: Affordances of Whiteboards • Core Roles of Whiteboards in Hospitals – Visibility – Overview – Status – Coordination – Communication – Handling contingencies • Research – Temporal Coordination [Bardram, JCSCW 2000] – Cog. Props of Whiteboards [Xiao et al, ECSCW 2001] – Inf. & Repres. [Reddy et al., ECSCW 2001] – Web of Artifacts [Bardram & Bossen, GROUP 2005] 47

Slide 48: Design of AwareMedia • ”Putting the schedule back on the wall” – Public and shared social awareness – Temporal awareness – Spatial awareness – Communication Source: J.E. Bardram, T.R. Hansen and M. Soegaard. AwareMedia: a shared interactive display supporting social, temporal, and spatial awareness in surgery. In Proceedings of ACM CSCW '06, p. 109-118, ACM Press, 2006. 48

Slide 49: AwareMedia User Interface 49

Slide 50: AwareMedia Technology & Architecture • Technologies – Media Spaces – Scheduling/Booking – Context-awareness – Instant Messaging • Builds upon – AWARE architecture • [CSCW 2004] – JCAF framework • [Pervasive 2005] 50

Slide 51: 1. Spatial Awareness • OR Space – Video – Status – People in the OR – Patient – Type of surgery & expected end time 51

Slide 52: 2. Temporal Awareness • OR Schedule – Operations – OR Teams – Timing – Delays – Cancellations 52

Slide 53: 3. Social Awareness • Context – Picture, Name & Initials – Location – Activity (e.g. surgery) – Tracking device – Role (e.g. replacement, coodinator, surgeon) 53

Slide 54: Deployment • Site – OR Ward, Bed Ward, Recovery – Supports 3 ORs, 30-50 people pr. day • Technology – Coordination central → 2 large interactive displays – 3 OR / Wards → 20’’ touch screens – Web cams – Location tracking based on Bluetooth • Tag • Mobile phones – ~20 AwarePhones • Deployed during 12 months 54

Slide 55: Hospital 55

Slide 56: Operating Ward 56

Slide 57: 57

Slide 58: 58

Slide 59: 59

Slide 60: AwareMedia in Use • Data collection – Observations, Interviews, Data Logging • Lessons learned – Increase Awareness and Communication • More efficiency in OR coordination • Fewer interruptions – Redundant information • Location, status, operations, … – Simple, stable, and predictable displays • Easy to learn, use, and navigate in a critical environment 60

Slide 61: Example III Context-aware Patient Safety in the Operating Room 61

Slide 62: Patient Safety • Institute of Medicine: “To err is Human” – 9% adverse events, 40% related to ‘errors’, 60% to complications – Danish studies confirm this • Utah and Colorado – Operative adverse events comprised 44.9% of all adverse events • Joint Commission – Universal Protocol for Preventing Wrong Site, Wrong Procedure, Wrong Person Surgery • Danish Recommendation – Improve communication and coordination – Improve patient identification Source: – … • Institute of Medicine • E J Thomas et al (2000). Incidence and types of adverse events and negligent care in Utah and Colorado. Med. Care., vol. 38, no. 3. 62

Slide 63: 63

Slide 64: A Context-aware Patient Safety System • Context-awareness – RFID sensor input + other input – Based on the Java Context-Awareness Framework (JCAF) – Extended with reasoning engine (JESS) • Features – Presenting relevant information during operation • PACS, EPR, Operation data – Monitors progress and fire warnings • Patient, Team, Blood, Patient Status, Equipment, … • Clinical Proof-of-Concept – Full functioning prototype – Deployed inside one OR with a full OR team – Used during one day (no real patients, however) – Qualitative evaluation 64

Slide 65: 65

Slide 66: 66

Slide 67: 67

Slide 68: 68

Slide 69: So what’s different? • ElderTech – Continuous Monitoring coupled with patient-clinician reliability and trust – Focus on Patient communication – not telemedicine – Methods are not clinically oriented • The Interactive Hospital – Social and Context Awareness – Focus on clinical collaboration and usability – not health informatics • Patient Safety in the OR – Context awareness and reasoning – Focus on ‘contextual’ and ‘procedural’ safety – not biological safety 69

Slide 70: Methodology 70

Slide 71: Evidence-Based Medicine – EBM • U.S. Preventive Services Task Force & UK National Health Service – Level I: Evidence obtained from at least one properly designed randomized controlled trial. – Level II-1: Evidence obtained from well-designed controlled trials without randomization. – Level II-2: Evidence obtained from well-designed cohort or case- control analytic studies, preferably from more than one center or research group. – Level II-3: Evidence obtained from multiple time series with or without the intervention. Dramatic results in uncontrolled trials might also be regarded as this type of evidence. – Level III: Opinions of respected authorities, based on clinical experience, descriptive studies, or reports of expert committees. Source: Wikipedia U.S. Preventive Services Task Force & UK National Health Service 71

Slide 72: Proof-of-Concept • “The construction of working prototypes of the necessary infrastructure in sufficient quality to debug the viability of the system in daily use; ourselves and a few colleagues serving as guinea pigs” Source: Marc Weiser. “Some Computer Science Issues in Ubiquitous Computing”, in Communications of the ACM, 36(7), 1993, ACM. 72

Slide 73: Clinical Proof-of-Concept 73

Slide 74: Clinical Proof of Concept – CPoC • Technology – Working prototype – Usable (but not necessarily user-friendly) – Stand alone – Focused on specific research questions • Deployment – Deployment in a real clinical environment – Used by real users (researchers are hands-off) – For a short, but sufficient time of period (1 day – 3 months) • Collecting ‘Evidence’ – Observations – Questionnaires Qualitative data – Perceived Usefulness and Usability – Measure – if possible Quantitative data 74

Slide 75: Examples of Clinical PoC • AwareMedia – Clinical PoC in a surgical ward for 4-5 months • Patient Safety – Clinical PoC in an OR during 1 day • Home based monitoring – Clinical PoC during ~3 months in 7 homes 75

Slide 76: Summing up 76

Slide 77: So – is Pervasive Healthcare new Wine? 77

Slide 78: Call for Action • Maintain focus on “pervasive” approach to healthcare – Supporting the move from a Mainframe to a Pervasive model of healthcare • Define and describe Pervasive Healthcare – Post it to Wikipedia – International Association of Pervasive Healthcare – IAPHC? • Define the research methods for Pervasive Healthcare – “Moving out of the lab” – Clinical Proof-of-Concept • Ensure research quality – Do not be an isolated group of researchers – Make profound research which can be published in well-established venues and journals – Ensure affiliation with IEEE and ACM 78

Slide 79: 79

Slide 80: 80

Slide 81: 81

Slide 82: 82

Slide 83: Contact details • Jakob E. Bardram – bardram@itu.dk – www.itu.dk/~bardram 83