Mie2014 workshop: Gap Analysis of Personalized Health Services through Patient-Controlled Devices

Gap Analysis of Insight-Driven Personalized Health Services through Patient-Controlled Devices
Gap Analysis of Insight-Driven
Personalized Health Services through
Patient-Controlled Devices
MIE 2014 Workshop 510 W17 25
TUESDAY 17:00 - 18:30
Pei-Yun Sabrina Hsueh, Michael Marschollek, Yardena Peres, Stefan Von Cavallar,
Fernando Martin Sanchez

Logistics
• 17:00-17:15 Opening Remark
• Key drivers and problems being addressed (Dr, Hsueh, IBM T.J. Watson Research)
• 17:15-18:10 Presentations
• Overview of service classes for health-enabling technologies for elderly and a physician’s view
in relevant applications in the future (Prof. Marschollek, Hanover Medical School).
• Enablers for successful development of mobile health solution– mobile health solution
requirements and challenges for scaling up and realizing its full potential (Mr. von Cavallar,
IBM Research Australia)
• Enablers for applications in research and potential clinical use – the need for standardised
reporting guidelines in self-monitoring experiments (Prof. Martin-Sanchez, Melbourne
Medical School)
• Business aspects of insight-driven Personalized Health Services through Patient-Controlled
Devices (Dr. Peres, IBM Research Haifa)
• Development of Temporal Context-based Feature Abstractions for Enabling Monitoring and
Managing of Interventions (Dr. Hsueh)
• 18:10-18:30 Workshop discussion (gap analysis, requirement
gathering)/audience Q&A
• 1. Implications and lessons learned from the case studies -- especially the gaps you perceived
as barriers of entry
• 2. Requirements for successful redesign of healthcare systems to accommodate patient-generated
information (with a sub-goal of identifying the areas where such information can
make most impacts).
Please leave your email and questions (if any)….

Pei-Yun (Sabrina) Hsueh, PhD
Wellness Analytics Lead
Global Technology Outlook Healthcare Topic co-Lead
Health Informatics Research Group
IBM T. J. Watson Research Center
• Research focus: Insight-driven Healthcare service design via
wearables and biosensor devices/implants, Patient-generation info,
Personalization analytics, Patient engagement & Adherence risk
mitigation

Elder population and care costs are growing annually, but no reliable
solutions for early detection and efficacy monitoring
4 IBM Confidential
4
Elderly population expected
to double by 2030 in US
Annual per capita healthcare costs
grows significantly with age
Early detection and efficacy
monitoring are key
Cognitive health is imperiled by the
lack of reliable solutions
1 in 3 seniors dies with
Alzheimer’s or other
dementia. Up to 72%
of cases are
misdiagnosed at the
PCP level
In 2013, Alzheimer’s will
cost US $203 billion.
This number is
expected to rise to
$1.2 trillion by 2050.

Holistic View of Determinants of Health to Personalized Services
Endogenous determinant
(e.g., genetics predisposition)
Clinical determinant
(e.g., care flow, care delivery)
Exogenous determinant
(e,g, environment, behavioral
social factors)
30%
10%
60%
SA Schroder. We can do better - Improving the Health of the Amarican People. NEJM 2007;357:1221-8.
Cardiovascul
ar disease
(73-83%)
(NHS, NEJM 2000)
Type II Diabetes
(58-91%)
(Finland DPS, NEJM 2001, 2007)
(US NHS, 2000; CDC DPP,
2002)(China Da-Qing, 2001)
Cancer
(60-69%)
(HALE, JAMA 2004;
de lorgeril Arch
Intern Med, 1998)
Personalized Medicine
Personalized Care
Personalized Prevention and
Disease Management
Cardiovascular
complication (42-57%)
(UKPDS, US EDIC)
Eye complication
(76%), Kidney
complication (50%),
Nerve complication
(60%)
(UKPDS, US DCCT)
Huge opportunity space for risk reduction:
Progress impeded by the lack of granular data capturing tools!

Technology barriers are lower than ever.
A whole array of patient-controlled devices are on the rise….
fall sensor in a pocket
adhesive vitals sensor
6 IBM Confidential
stretch sensors
gait analysis in a pocket
vitals sensor in t-shirt
insole sensors
e-textile wireless ECG
Cardiac monitoring systems
Requires ultra-low power adaptive
circuits, non-intrusive form factors
OpenBCI

7
Wearable/IOT computing is the new mobile
“Three medical technology stories to watch
in these areas will be wearable technologies
for fitness, aging-in-place technologies, and
real-time monitoring. ”
—Forbes, “Medical technology stories to
watch in CES 2014” (Jan 2, 2014)
“Wearable tech will be as big as the
smartphone.”
—Wired, Cover story (Dec 17, 2013)
• Quantified self (27% of US users) - IDC Report, 2014
• From IOT to “Internet of Everything” (IOE): 30-50 bn devices in 2020
- Gartners Report, 2014
• IoT enabled “Connected Life” market forecast in 2020: Clinical Remote Monitoring
and Assisted Living to be the 2nd and 3rd largest mkt
- IDC Report, 2014

Healthcare is being re-imagined by bringing together high-growth,
high-value patient generated information and EMR data

Healthcare becoming both Personal and Collaborative
The Creative Destruction of Medicine: How Digital Revolution will Create Better
Healthcare (Eric Topol, 2012)
(1) What are the implications and lessons? What are the gaps as barriers of entry?
(2) What are the Requirements for successful redesign of healthcare systems to
accommodate patient-generated information? What are the areas where such
information can make most impacts?
1990 Empirical Medicine
Intuitive Medicine
Personalized Service
Patient-Centric
Service
Disease-Centric
Guideline
Century of
behavior change
Precision Medicine
Degree of personalization
Degree of collaboration
(data dimension)
Data-Driven
Evidence

Workshop Theme
• 1. Implications and lessons learned from the case
studies -- especially the gaps you perceived as
barriers of entry
• 2. Requirements for successful redesign of
healthcare systems to accommodate patient-generated
information (with a sub-goal of identifying
the areas where such information can make most
impacts).

INTRODUCTION
Medical School)
gathering)/audience Q&A
make most impacts).

Service classes of health-enabling technologies –
relevant applications in the future
Michael Marschollek

Wearables – just nice toys?
? ? ? ?
Good medicine and good healthcare
demand good information

Wearables – just nice toys?
more data, (hopefully) more information
more accurate diagnoses
early detection of subtle changes, disease onset
better, targeted treatment
• Niilo Saranummis‘s 3 ‚P‘s:
– pervasive technologies
shall enable semantically interoperable platforms to communicate and store health data
– personal services
using sensor technologies for continuously measuring health-related data of an
individual; to support her or him at specific health problems
– personalized decision support
adapted, ‘tuned’ to the individual’s norm, not to averages in populations (not one-size-fits-
all)
Saranummi N. IT applications for pervasive, personal, and
personalized health. IEEE Trans Inf Technol Biomed. 2008; 12: 1-4.

Haux R et al.. Inform Health Soc Care. 2010 Sep-Dec;35(3-
4):92-103. PubMed PMID: 21133766.

Service classes
• Basic services:
– Emergency detection and alarm
– Disease management (chronic diseases)
– Health status feedback and advice
• Other services:
– Communication and social interaction
– Support for daily life and activities
– Entertainment, information and communication
S. Koch et al. Methods Inf Med, 2009.
Ludwig W et al. Comput Methods Programs Biomed. 2012,
May;106(2):70-8.

Example: emergency detection – falls
• Feldwieser F, Gietzelt M, Goevercin M, Marschollek M, Meis M, Winkelbach S, et al.
Multimodal sensor-based fall detection within the domestic environment of elderly
people. Z Gerontol Geriatr. 2014 Aug 12. PubMed PMID: 25112402.
• Kangas M, Korpelainen R, Vikman I, Nyberg L, Jämsä T. Sensitivity and False Alarm Rate
of a Fall Sensor in Long-Term Fall Detection in the Elderly. Gerontology. 2014 Aug 13.

Example: disease management
• Whole System Demonstrator (WSD) study (UK):
– Different chronic diseases (e.g. heart failure)
– ‚Telehealth‘ intervention (oximeters, scales, glucometers, …)
– Lower mortality and admission rates, higher cost
– Steventon et al. BMJ 2012; 444:e3874
• NATARS study (Germany):
– Geriatric home rehabilitation after mobility-impairing
fractures
– Wearable sensor, smart home sensors
– Marschollek et al. Inform Health Soc Care. 2014 Sep;39(3-
4):262-71.

Example: early detection/ diagn., prevention
• Fall risk assessment/ fall prediction:
– medium-scale prospective studies, e.g. Greene et al, 2012,
Gerontology; Marschollek et al, 2012, Meth Inf Med; Gietzelt
et al, 2014, Inf Health Soc Care
• Rehabilitation Monitoring/ relapse identification:
– Steventon et al. BMJ 2012 (WSD study)
– Marschollek M et al. Inform Health Soc Care. 2014
– Calliess et al. Sensors, 2014
• Physical activity promotion (Plischke et al. 2008)
• Aftercare, paediatric liver TX patients (Marschollek et al. 2013)
• …

Epidemiologic perspective: future diseases
• increase of chronic diseases
• increase of “age-related deficits”
• decrease of health professionals
• application areas:
– cardiovascular diseases (e.g. congestive heart disease)
– neuropsychiatric disorders (dementia, uni-/bipolar
depressive disorders, anxiety disorder)
– diabetes (and follow-up conditions)
– musculoskeletal diseases (arthritis and esp. follow-up
conditions (e.g. post-implant rehabilitation))
• but: this is only secondary/ tertiary source: Institute for Hea plthr eMveterincst iaondn E!valuation,
healthmetricsandevaluation.org

Gaps and Pitfalls (subjective!)
• Translating (diagnostic) knowledge into action
• Lack of integration into health information systems,
especially on semantic level (modeling)
– E.g. Marschollek M. Inform Health Soc Care. 2009
• Psychological:
– the right not to know
– trust, security
• and still: Device interoperability

join our IMIA WG: www.wearable-sensors.org

Stefan von Cavallar Advisory Software Engineer, IBM Research Australia

The title of Stefan von Cavallar’s Presentation
will be:
Mobile health: Solution requirements and challenges
for scale-up

Mobile Health
Benefits
•Unprecedented opportunities
•High growth usage in developing countries = health
service delivery in regions where otherwise limited
•Improved access to health services
•Improved patient communication, ie. Reminders, Care
plans
•Monitoring of treatment compliance
•And MORE… !

Mobile Health Solution Considerations
• Health information privacy
• Health information security
• Standardization
• Interoperability
• Device fragmentation
• Data fragmentation
• Geography
• Budgets $

Specifically...
The exchange and collection of data from different
systems and platforms will be…
*Essential for users with multiple clinical
requirements
*Key to preventing further fragmentation between
health programs

What are we trying to solve?
Consider this use case:
•Mother, with daughter
•Daughter sick for several days with lots of fluid loss
•They know nearest medical health center is 60Km away, they have no
transport
•Both walk to health center, and wait for a further 24 hours until seen due to
understaffing and high patient numbers
•Assessment made, treatment given and returned home
•Mother has no care plan or guidance on next steps
What happens next?

What do we want to do?
1. Improve health!
How about the previous use-case becomes:
• Mother, with daughter
• Daughter sick for several days with lots of fluid loss
• They know nearest medical health center is 60Km away, they have no transport
• Mother uses mobile health credits to send message to a Cognitive Healthcare
Hub where it is analyzed. Identify open questions to determine severity
• Message sent back requesting additional information and includes guidance on
how to gain that information (e.g. how to perform a pinch test)
• Mother carries out tests and responds. Guidance is given to seek medical
assistance in the nearest healthcare center. Details for the center are different
to what the mother knows, its closer (8Km), but in a different direction…

• Details of daughters condition are recorded and monitored via the Cognitive
Healthcare Hub
• At the health center social worked collect biometric data of waiting patients
• Information collected and presented to physician for accelerated diagnosis
• Information fed into Cognitive Healthcare Hub
• Diagnosis and treatment options presented through the Cognitive Healthcare Hub
to the healthcare worker. Support diagnosis by checking guidelines, hilight
treatment options and assemble care plan
• Daughter is being treated for diarrhea and dehydration
• The Cognitive Healthcare Hub allows healthcare worker or physician to select a
recommended care plan that the Hub has personalized for the daughters
conditions
• The mother is sent the care plan via wifi
• Mother and daughter are discharged, complete with a take-home plan for on-going
treatment
• At points of time afterwards, the Hub sends out reminders and short enquiries to
follow up and if necessary request that a health worker check on them

Solution Requirements
The solution must engage:
•A unified data view
•Health information privacy
•Health information security
•Standardized
•Interoperable
•Defined device and data structure
•The users and fulfil their use cases

Solution Requirements
• Provide information collecting, learning and sharing infrastructure (ie,
cognitive healthcare hub)
• Include historical disease, climate and population data
• Include continuous disease surveillance and drug consumption data
• Learn from historical and continuous data
• Two-way information flow
• Mobile sensing (eg, occurrence of certain symptoms in a region) and multi-casting
• Practitioner support (eg, recent weather condition and high number of reported
infections with same symptoms in the region suggest particular diagnosis)
• Value proposition
• Support health workers and the need for diagnosis
• Provide visibility and forecasting of disease outbreaks and drug demand supply
• Enable macro-level priority setting and investment support
• Monitor the ROI of health investments
• Provide sustainable infrastructure for data collection and dissemination

Cognitive Healthcare Hub
Interface Gateway
Governments
Interaction Communication Visualisation
Mobile Internet Community Radio TV
Statistics
Modelling
Cognitive Computing Analytics
Machine Learning
Simulation
Prediction
Business Intelligence
Unified Data View
Security Access Quality
Environment Mobile Social
Media
Indigenous
Knowledge
Guidelines
Publications
Remote
Sensors
Registries

Watson: Question Answer
Hospitals
Deep Thunder: Climate Modeling
Cognitive Healthcare
Pharmacies
Health
Workers
Community
Health
Centers
Patients
Prepare for patient
increase
Hub
Optimized drug distribution
Support untrained
Advice for rare conditions
STEM: Epidemiological Modeling
Public
Health
Boards
Optimized Resource Allocation

GPS Healthcare worker entry Sensors
Dehydration
*Healthcare/trained worker only
Visual
inspection
Skin pinch
timer; App
Blood viscosity;
Infra-red sensors;
camera modified*
Image analytics on
lips, eyes; camera;
MMS
Community
General
questioning
Tests
Diagnosis
Aftercare
Oral Zinc supplements Rehydration Salts
Rehydration schedule
Tracking; how? Reminders
Local Push
Treatment
Calculate therapy
Public Health
Water supply analysis
Pathogen outbreak Pathogen identification
Individual
App;
decision
tree
Intravenous fluids

Challenges for Scale Up
• Data Fragmentation/Distribution
• Data inconsistencies
• Education/Training i.e. Hardware, software
• Differing working practices
• Infrastructure, i.e. Easily no data reception
• Costs, incentives and funding $$$$$
• Not everyone has the same level of access to
technology

Summary – Implications and lessons learnt
from this case study
• Assume nothing… i.e. users with smartphones
• While countries want the same thing, how they get
there varies greatly…
• Technology uptake is not always as easy or advanced
as one might think
• Infrastructure is not as mature as required
• Limited funding/incentives available for adopting
these technologies/infrastructures
• Integrating the fragmented data

Summary – Requirements for successful
redesign of healthcare systems
• Everyone to want to contribute
• Analytics engines using structured and unstructured
data
• A system that enables contributors and provides
tailored data to consumers
• Data consumption and feedback for improved
analytics
• Education and “buy-in”

Enablers for applications in research and
potential clinical use:
Standardised reporting guidelines in self-monitoring
experiments
Prof. Martin-Sanchez
Melbourne Medical School

41
Manager, Mobile Big Data Solutions
IBM Research - Haifa
B.A., M.Sc., Technion – Israel Institute of Technology
Senior Researcher, IBM Research – Haifa
Focus on leveraging state-of-the-art IT to solve industry
pain points
Mobile, Cloud, Big Data, Analytics
Standards Interoperability
HC/Wellness, Retail
Prolific EU FP6, FP7 and H2020 research activities
Yardena Peres

Research project funded by the
EU (Nov 2013 - Oct 2016)
• DAPHNE Consortium:
– Sensor partners: Evalan, UPM
– IT partners: IBM Research – Haifa, TreeLogic, Atos, SilverCloud
– HC partners: Nevet, Bambino Gesu, University of Leeds, IASO
• DAPHNE Objective:
– Develop a novel IT platform for delivering personalized guidance
services for lifestyle management (focused on reducing
sedentariness) to the citizen/patient by means of:
• Advanced sensors and mobile phones to acquire and store data on
lifestyle aspects, behavior and surrounding environment
• Individual models to monitor health and fitness status
• Intelligent data processing for the recognition of behavioral trends
and services for personalized guidance on healthy lifestyle and
disease prevention
• Use Case:
– The system receives clinical parameters from the selected
sensors, stores health markers, learns personal preferences, and
generates feedback and recommendations.
42

Business aspects of insight-driven Personalized Health
Services through Patient-Controlled Devices
• Patient-Controlled Devices are generating large
amounts of new data
• This poses several IT challenges
– Cope with large amounts of varied data while maintaining
data quality
– Connect with existing Healthcare Systems (e.g., EHR, HIS)
– Handle security, privacy and consent management

Business aspects of insight-driven Personalized Health
Services through Patient-Controlled Devices
• Monetize data, e.g. Data as a
Service (DaaS) Model
– Patients generate new data
– IT companies manage it
– HC providers, Pharma, Payers,
Retailers, Governments,
Scientific Research, etc.
consume it
– All stakeholders are part of the
same value-chain

Development of Temporal Context-based
Feature Abstractions for Enabling Monitoring
and Managing of Interventions
MIE 2014
Pei-Yun Sabrina Hsueh
Ke Yu
Marina Akushevich
Shweta Shama
Peter Mooiweer
Sreeram Ramakrishnan
IBM GBS BAO/Watson Research

Technology barriers are lower than ever.
A whole array of patient-controlled devices are on the rise….
fall sensor in a pocket
adhesive vitals sensor
46 IBM Confidential
stretch sensors
gait analysis in a pocket
vitals sensor in t-shirt
insole sensors
e-textile wireless ECG
Cardiac monitoring systems
Requires ultra-low power adaptive
circuits, non-intrusive form factors
OpenBCI

Significant growth in exogenous data poses challenges to existing BigData
storage and analytics solutions
Determinants of Health
Outcomes
Exogenous
(Behavior, Socio-economic,
60
Environmental, ....)
% Fitness/WellnessPatient-controlled medical
devices
Affinity (digital)Affinity
(retail)
Employ
ment
Socio-econo
mic
databa
ses
Data Sources
Endogenous
(-omics) 30
%
Clinical
(EMR)
10
%
Exogenous Data Growing Fast
1240
PB
1800
PB
6800
PB
(annu
al)
Episodic; care
pathways in
controlled
settings
Mostly static
data, but
critical for
personalized
medicine
Significant volume
(every step, heart
rate, meals,….) and
variety
(physiological,
psychological,
socio-economic)
and dynamic
Data generation ~
uncontrolled
environment
!

A perfect storm awaits…..
Data Deluge from Patient-generated information

49
Patient generated information are effective for self-management
and personalized intervention/adaptation
Increase awareness to self-monitoring
(Prestwich et al., 09; Burke et al., 05)
Promoting behavioral change
(Dietary intake: Burke et al., 05;
Physical activity: Prestwich et al., 09; Michie et al., 09)
Triggering reminders to care plans
(Consolvo et al. 09; Hurling et al., 07)
Personalizing communication
messages and education materials
(Thaler and Sustein, ‘08)
Nudge: Improving Decisions About Health

Existing tools lack capabilities to determine appropriate
metrics most sensitive to individuals
• Especially true for those require artful interpretation of the
temporal context of measurement
– E.g., Hypertension = blood pressure; Diabetes = SMBG; Metabolic
syndrome = weight, cholesterol level
• Need new capability to calibrate intra-individual variability
– E.g., Heart rate variability (HRV) detect abnormal symptoms of
autonomic nervous system that are correlated with lethal arrhythmias
– E.g., The variability of B-type natriuretic peptide (BNP)  detect cardiac
ischemia
• Barriers:
– (1) No unifying theoretical models exists for enabling such interpretations
– (2) The process from feature abstraction to individualized prognosis is
non-trivial.

Data-driven Calibration and Personalization Process:
From Population-based evidence to individualized alerting/adaptatio
Population Data-driven Insight
Feature
Abstraction
(Candidate feature
generation)
Complete feature set
Feature
Optimization
1
2
(Optimal set construction)
Construction of features
based on variance over
time
Analyze and select
variance features from
the complete set of
constructed features
Optimized Feature subset
Identify input data
sources from the optimal
feature set and configure
the input of data sources
Feature
3
Population (data
source configuration)
Individual Data-driven Personalization
Individual data captured based on input configuration
Alert Setting
(individual-based
calibration)
Individual-based alert
Learning for
Adaptation
Slide 51 IBM CONFIDENTIAL
Monitoring biomarker/patient-generated
info operational DB
EHR/PHR
Repository
Learn from baseline to understand
normal variance and use the info to
determine when to send alerts
Verify if the selected abstraction is the
right one for the individual according to
the KPI. Create time gates events,
triggers to check if the selected feature
is the optimal one.
Individually adapted
plan (alert and
intervention)
4
5
Verified feature set for the target individual

Enabling personalized temporal context interpretation
by data-driven calibration and personalization
• Need to streamline the process from population-based feature abstraction
to individualization
• Enable more effective monitoring and management of interventions
Monitoring
device
Intra-individual
variability calibration
(evidence-based)
• Service Scenarios:
Input for monitoring
feedback generation
and
diagnosis/intervention
– 1. Development of adherence programs for patient self-management
– 2. Enablement of intervention design for care coordinators/care givers
– 3. Understanding efficacy for care givers to adapt suggested
interventions for an individual
– 4. Evidence-generation for intervention efficacy (population data)

Summary: Gaps observed in Service Design
• The lack of reliable means to capture granular patient-generated data in non-clinical
settings (user’s daily life contexts)
– Leads to unreliable detection of inflection points, habit formation cycles and assessments of
treatment efficacy.
• Need for a framework to integrate analytical insights with feasible service models.
– Progress impeded by the lack of modular design and data standardization in existing
healthcare systems
53 IBM Confidential
Customer/
Patient
Adherence
Theme
#1
Theme
#2
Theme
#3
Personalization for
risk stratification
(from population to
individual evidence)
Personalization for in-context
recommendation
(from disease-centric to
patient-centric)
Personalization for
adherence risk
mitigation
(from status-insensitive
to status-sensitive)

Summary: New requirement of a modular framework to
accelerate personalized service design
Technologies to enhance wellness services
– Guide the identification of customization points in clinical workflow and
deployment of the Analytics and IM offerings
– Create new tools and infrastructure for client engagements
– Explore light-weight approach to connect the components (to prepare for future
cloud offerings)
New solutions and services
– Bring together clients and researchers to understand clinical touch points
– Demonstrate how to leverage customization points to engage users and possibly
improve health literacy and outcomes
Replicable patterns for patient engagement deployment
– Create ETL procedures to be repeatedly use in other provider settings
– Explore both hosted and internal deployment possibilities
Plug-in for other tools
– Create a recipe from data collection to summarization to customization to
engagement to outcome measurement
– Each component can be singled out as a standalone process for other tools

Logistics
Medical School)
gathering)/audience QA
make most impacts).
Please leave your email and questions (if any)….

Workshop Theme
1. Implications and lessons
learned from the case
studies -- especially the
gaps you perceived as
barriers of entry
2. Requirements for
successful redesign of
healthcare systems to
accommodate patient-generated
information
(with a sub-goal of
identifying the areas
where such information
can make most impacts).
• Workflow
– Knowledge actionable?
– Integration
– Lack of modular design
• User
– Right not to know, trust, security,
consent management
• Data
– Fragmented, lack of EHR interoperability
– Beyond big data, uncontrolled env.
• Device
– Interoperability, infrastructure
• Service
• Resource

Summary:
Gap analysis and HC re-design requirement
• Workflow
– Lack of integration into health information systems, especially on semantic level (modeling)
– Lack of modular design of existing healthcare system
• User
– Manage the right not to know, trust, security, consent
– Assume nothing from the start
– Country/Cultural differences
• Device
– Fragmentation ; Lack of interoperability
– Immature infrastructure
• Data
– Fragmented data sources (need to integrate with EHR / HIS)
– Ecosystem platform (enabling contributors, tailoring data to consumers)
– Need to create personalization analytics framework (and engine) (data consumption feedback)
– BigData: large amounts of varied data while maintaining data quality
– Beyond Bigdata storage and processing, in uncontrolled env.
– Beyond Bigdata analytics, in uncontrolled env.
• Service
– Touchpoint redesign to integrated Clinical/Wellness Service
• Resource
– Lack of funding/incentives

More questions to think Suggestions on next
step?
• Do provider beliefs and support of these technologies and approaches affect
patient usage?
• Will patient interactive reported data improve provider and patient
communications, reduce risks and increase early interventions?
• Can adherence to care plans for patients with chronic health conditions be
increased through technology-mediated techniques?
• Can analytics based on patient characteristics and adherence behavior be used to
identify patients at risk for adverse health events, as well as identify “model”
adherers who are more effective than the average patient at remaining healthy?
• Can dynamically configured software improve health outcomes for the patient
and help control costs?
• How will real time patient reported data shift communications, culture, care
processes and the patient – provider partnership?
Consider publishing our summary report in MEDINFO 2015? (any other venue?)
A follow-up workshop/panel with a more focused theme on the gap and
requirement perceived as priority?

Suggestions on next step?
Traditional Chinese
Thank You
Merci
Grazie
Gracias
Obrigado
Danke
English
Japanese
French
Russian
German
Italian
Spanish
Arabic Brazilian Portuguese
Simplified Chinese
Hindi
Tamil
Thai
Korean
Hebrew

Questions?

Mie2014 workshop: Gap Analysis of Personalized Health Services through Patient-Controlled Devices

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Mie2014 workshop: Gap Analysis of Personalized Health Services through Patient-Controlled Devices

Similar to Mie2014 workshop: Gap Analysis of Personalized Health Services through Patient-Controlled Devices (20)

Recently uploaded

Recently uploaded (20)

Mie2014 workshop: Gap Analysis of Personalized Health Services through Patient-Controlled Devices