HIMSS Clinical & Business Intelligence Community CBI Community... · 2018. 1. 25. · Shelley...
Transcript of HIMSS Clinical & Business Intelligence Community CBI Community... · 2018. 1. 25. · Shelley...
January 2018 Event
HIMSS Clinical & Business IntelligenceCommunity
#PutData2Work | #PopHealthIT | #PrecisionHIT
Shelley Price, MS, FHIMSS
C&BI Community Organizer
Director, Payer & Life Sciences
HIMSS | Arlington, VA
Arthur Panov, MPH, CPHIMS
C&BI Community Co-Chair
Healthcare and Life Sciences Architecture
IBM Watson Health
Mike Berger, PE, CPHIMS
C&BI Community Co-Chair
Vice President, Population Health Informatics &
Data Science, Mount Sinai Health System
Welcome
Joanne Bartley, CAE
C&BI Community Organizer
Manager, Health Business Solutions
HIMSS | Chicago, IL
• Welcome
• HIMSS C&BI Community Updates / Announcements
• Presentation & Discussion:
“Building and Deploying Healthcare IoT Solutions with
Personalized Learning ”
Deepak S. Turaga, MS, PhD, Distinguished Research Staff Member
| IBM Research AI
• Wrap-Up / Next Steps
Agenda
Updates / Announcements
March 5 – 9, 2018
Venetian – Palazzo – Sands Expo Center
Remember! Pattern change to Monday – Friday
Welcome to HIMSS18!
C&BI Activities & Events – Education
• Preconference
• General Education
• Specialty Education
• Specialty Exhibitions & Sessions
1. AMDIS/HIMSS Physician Executive
Symposium: Shifting from Computer
Care to Patient Care
2. Business of Healthcare Symposium:
Going from Good to Great in a Value-
Based World
3. Compliance Symposium: Mastering
Compliance - What You Must Know
4. Coordinated and Connected Care
Symposium: Tackling the Challenge of
Connected and Coordinated Care
5. Innovation Symposium: Innovation As
a Strategic Imperative
6. HIMSS/SHIEC Interoperability & HIE
Symposium: Facilitating Person-
Centered Interoperable HIE to Manage
Complex Populations
7. Long-Term and Post-Acute Care
Symposium: Digital Health in and with
LTPAC Settings
8. Nursing Informatics Symposium:
Demonstrating Nursing Value Through
Health IT
9. Population Health Symposium: Chasing
One Medicine – The Next Generation of
Consumer- and Community-Centric
Healthcare
10. Precision Medicine Symposium: Journey
to the Summit Using Clinical and Business
Intelligence
Preconference Plus Pass
CME or CNE credit not available for this program and is not part of Preconference Plus benefit
C&BI Activities & Events – Education
• Precision Medicine Forum: From Promise to Reality –
Integrating Precision Medicine into Clinical Care
Wednesday, March 7, 2018 | Galileo 901
– Session #98 | Separating Hype from Reality
– Session #114 | Applying Genomic Intelligence and
Decision Support at the Point of Care
– Session #130 | Genomics Nursing and the EHR
C&BI Activities & Events – Networking
• C&BI and PopHealth Reception | Tuesday, March 6 | 6-7pm
– Solutions Lab | Casanova Meeting Room | 1st Floor
– Complimentary; by invite only
We would like to thank our supporter:
C&BI Activities & Events – Exhibition
Solution Lab
Population Health
Business Administration
• Where: Casanova Meeting Room | 1st Floor
• When: during Exhibit Hall Hours
– Tuesday, March 6, 9:30am-6:00pm
– Wednesday, March 7, 9:30am-6:00pm
– Thursday, March 8, 9:30am-4:00pm
• What: interactive, one-stop shop dedicated to showcasing practical solutions that use IT to improve population health and healthcare administration. Features include education sessions, fireside chats, Meeting Pods, Solutions Bar and a special session each day with experts answering attendees’ questions
C&BI Community PresentationGuest Speaker(s)
We will take
questions at the
end of the
presentation…
…Please type your
questions into the
Q&A box.
#PutData2Work | #PopHealthIT | #PrecisionHIT
© 2018 IBM Corporation
Building and Deploying Healthcare IoT Solutions with Personalized Learning Sugar.IQ
C. Aggarwal, L. Cao, Y.-C Chang, T. Dinger, M. Ng, R. Pavuluri, R. Saccone, S. Sathe, D. Sow, D. S. Turaga, L. Vu
© 2018 IBM Corporation
17
Outline
Motivation
– Remote Diabetes Monitoring
– Initial Data Analysis
Building the Sugar.IQ Solution
– Application Design
– Distributed Stream Processing
Personalized Machine Learning
– Operationalizing Adaptive Modeling
– ML Lifecycle Management
– Need for Automation – CADS
Discussion
© 2018 IBM Corporation
Complexity of Diabetes Disease Management
>95% of diabetes care comes from patients themselvesSignificant benefits and cost savings can be realized
A reduction of 5 hypo episodes for a patient per year results in ~700$ in emergency services and 9000$ in in-patient services per year
PATIENT
HEALTHY EATING
BE ACTIVE
MONITOR
TAKE MEDICATION
SOLVE PROBLEM
REDUCE RISK
COPE WELL
1 HbA1c300 meals 700 MBGs
1000 alarms25,000 CGM’s
1 HbA1c300 meals 700 MBGs
1000 alarms25,000 CGM’s
DOCTOR’S VISITDOCTOR’S VISIT
18
© 2018 IBM Corporation
HOW HAVE I DONE?Important glucose management information
HOW AM I DOING?Real-time blood glucose and insulin information
A personalized solution that combines patient data from multiple sources to provide insights and advice to patients and help them effortlessly stay ahead.
WHAT SHOULD I DO?Predictive recommendations to help avoid incidents and stay ahead
Activity
Pump &
CGM
CGM Only
Food & Nutrition
Other(bio)metric
sensors
Contextual Data
FUTURE
PRESENT
PAST
Personalized Assistant for Diabetes Management
19
© 2018 IBM Corporation
Goal: Can Watson predict Hypoglycemia in patients, post bolus?Base prediction rate – across all patients ~80% accuracy
Approach: Identify “insulin profiles” and patient groups to improve prediction
Data (100 patients)
Sensor Glucose
Bolus Wizard Settings (Insulin
Sensitivity, Carb Ratio, Insulin
Action Curve)
Bolus Wizard Entries
(Carbs, Correction BG, Active
Insulin)
Blood Glucose Bolus Delivered Basal Rate Setting
Hypos determined mainly by
Why is this important?
• “Personalized” prediction with significantly improved accuracy• Improved outcomes with real-time insulin and behavior recommendations
IBM Analytics – feature selection and clustering to generate patient groups
Sensor Glucose
+ Bolus Wizard
Settings + Blood
Glucose
Sensor
Glucose +
Carbs
Sensor
Glucose +
Bolus Wizard
Settings
Sensor Glucose
+ Bolus Wizard
Settings + Bolus
Wizard Entries
Sensor Glucose +
Day-of-the-week
Bolus Type +
Sensor
Glucose
Group 1 Group 2 Group 3 Group 4 Group 5 Group 6
Hypoglycemic event prediction for each group ~90%* accurate with 3 hour lead timeImproves significantly over base prediction rate
*Results preliminary – based on very small dataset
Initial PoC Results: Predicting Hypoglycemia with MLMedtronic Watson Health Engagement
20
© 2018 IBM Corporation
Prediction Results: Example of PersonalizationBased on Usage of Device
21
0
0.2
0.4
0.6
0.8
1
1.2
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39 41 43 45
Sensor, Wizard, BolusAmount, Type
HYPO HYPER NORM UNORM
HYPO 172 13 9 0
HYPER 15 46 0 0
NORM 1 0 262 0
UNORM 0 0 0 0
Classified as
List of Attributes
List of Attributes
0
0.2
0.4
0.6
0.8
1
1.2
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39 41 43 45
Sensor, Day of the Week
HYPO HYPER NORM UNORM
HYPO 944 41 0 0
HYPER 29 106 0 0
NORM 3 0 23 0
UNORM 0 0 0 1
© 2018 IBM Corporation
Need for Personalized Machine Learning
Unlike monitoring hurricanes or tsunami, our monitoring and early warning
actually changes the behavior of the monitored subject
–Different users behave differently to these alerts
Such behavior change leads to fewer and fewer predictive signals
–Not all behavior changes explicitly observed
22
© 2018 IBM Corporation
23
Outline
Motivation
– Remote Diabetes Monitoring
– Initial Data Analysis
Building the Sugar.IQ Solution
– Application Design
– Distributed Stream Processing
Personalized Machine Learning
– Operationalizing Adaptive Modeling
– ML Lifecycle Management
– Need for Automation – CADS
Discussion
© 2018 IBM Corporation
Sugar.IQ: Remote Diabetes Monitoring
24
MiniMed Connect
Watson Health Cloud
Develop models of Patient insulin regimen, Activity and wellness, and Patient Context
Apply models against streaming data to create real-time insights and provide the user with: Insulin Recommendations, Behavior Recommendations, and identified deviations and patterns
Doctor prescriptions and
Updates
Medtronic Store(Supplies, Accessories…)
Capture live streaming data and context from the devices
© 2018 IBM Corporation2
5
Search and log meals -Keep diabetes data in one
place
Review device data and glucose metrics from the past
to learn how to act in the future
Remembers patterns and displays marked food or activity
FOODDIARY
CGM & INSULINDATA REVIEW
Reminds users for better adherence and outcome
ADHERENCEINSIGHTS
GLUCOSEINSIGHTS
MOTIVATIONALINSIGHTS
Uncover behaviors associated with glucose
patterns
Encouragement to sustain positive outcomes
GLYCEMIC ASSIST
Comprehensive Platform Real Time Insights
Sugar.IQ Features for Generation 1
25
© 2018 IBM Corporation
Sugar.IQ R1.0 Data Flow
26
Site-to-Site VPN DB2-to-DB2 CDC Replication
CRMGE
Centricity SalesForce SAP
WHC
Connect
Connect+
Sensor, Pump and Minimed Connect
Medtronic Infrastructure
DB2 for IBM
AWS
Mobile First Backend
NutrinoSensor and CRM Data
Streaming Analytics
Offline Analytics
Insights and Alerts
Nutrino
Other Sources of Data (e.g. Weather)
This is a generalizable template for AI based IoT Applications
© 2018 IBM Corporation
Low Latency, Personalized Analytics
App users are accustomed to “instant” gratification
–Glucose threshold change needs to be reflected on screen quickly
–Need to deliver insights in a “timely” manner, such as when a user is
having chicken alfredo, what happened previously with eating alfredo
–Degree of personalization goes beyond Google, Facebook
Live data arrives with every 5 mins
–Round trip latency of calculating and delivering insights, < 5 mins
–1 KB per user every 5 mins, ~500 KB per user per day
– In-memory data kept for at least 3 months, ~50 MB per user
–Historical data retained for multiple years
Active users ramps from 300 to reach 10,000 by 2018 year end
27
© 2018 IBM Corporation
Sugar.IQ Application:Functional Blocks for Pattern based Insights
28
Live Data
Data Cleaning
MyData
Glycemic Features
Motivational Insights
Trigger Logic
Glycemic Insights
Insight Prioritization
Batch Data
Meal Data
User Feedback
© 2018 IBM Corporation
Happening Behind the Scenes
29
Mobile First Backend Streams (cached histogram) DB2 MQ
Mobile First Backend
MQ
4-6 seconds round-trip latency
© 2018 IBM Corporation
30
Outline
Motivation
– Remote Diabetes Monitoring
– Initial Data Analysis
Building the Sugar.IQ Solution
– Application Design
– Distributed Stream Processing
Personalized Machine Learning
– Operationalizing Adaptive Modeling
– ML Lifecycle Management
– Need for Automation – CADS
Discussion
© 2018 IBM Corporation
Requirements on Streaming Analysis
Velocity: Streaming Data and Analysis
– Range of data rates: low decision latency
Velocity: Loss Tolerant Analysis
– Highly noisy and lossy data, graceful degradation under failure
Variety: Multimodal Data Analysis
– Correlated primary sources, Structured or Unstructured
Variety: Dynamic and Adaptive Analysis
– Source, data, analysis and resource variability
Volume: Distributed Analysis
– Decomposable into flowgraphs, distributed data, processing
Volume: High Performance
– Real-time, Low-latency, high throughput, scaling
31
© 2018 IBM Corporation
The Evolution of Stream Computing
32
Persistent Data
StreamingData
TraditionalData
Non-TraditionalData
Stream Processing
Map-reduce
Databases, Data Warehouses
Complex Event Processing
Active Databases
Continuous Query
Publish-Subscribe
Velocity
Va
rie
ty
In-memory Cluster Computing
© 2018 IBM Corporation
Introduction to Stream Processing
Incremental tuple by tuple processing
FX rate
Internal Crossing
Weather
Exchange
Value
Added
Feed
Stream
Tuple
Operator
© 2018 IBM Corporation
Introduction to Stream Processing
FX rate
Internal Crossing
Weather
Exchange
Value
Added
Feed
Supports Naturally Distributed Applications
Stream
Tuple
Operator
© 2018 IBM Corporation
Streaming System: Streams Overview
35
Integrated Development Environment
Scale-Out Runtime Analytic Toolkits
Development and Management Functional and OptimizedFlexibility and Scalability
Cloud and on premise available for flexible deployment
© 2018 IBM Corporation
Development Environment
36
Integrated Development Environment
Development and Management
Streams Processing Language
Visual Composition Tools
Wrappers for legacy code written in Java, C++, Python, R, and Matlab
© 2018 IBM Corporation
Monitoring and Debugging Support
37
Integrated Development Environment
Development and Management
Web based Monitoring Console
© 2018 IBM Corporation
Runtime
38
Scale-Out Runtime
Flexibility and Scalability
•High-performance clustered runtime
•Large scale deployment
•RHEL, CentOS, SUSE Linux Enterprise Server
•X86 and Power multicore hardware
•InfiniBand support
•Ethernet support
© 2018 IBM Corporation
Runtime: Advanced Features
39
Scale-Out Runtime
Flexibility and Scalability User Defined ParallelismApplication Resiliency
System High Availability
© 2018 IBM Corporation
Runtime Scaling
40
Scale-Out Runtime
Flexibility and Scalability
~200B records/day
Application for Service Quality Monitoring
© 2018 IBM Corporation
41
Streams Processing for Sugar.IQ
Glycemic Features
Motivational Insights
Over 40000 lines of Streams SPL code
Glycemic Insights
MyData
Data Ingest, Parsing
Data Cleaning
© 2018 IBM Corporation
42
Streams Live Graph for Sugar.IQ (scaled up/out to 10x parallel)
Continuous scaling to 2000 users at 100x real-time (200,000 equivalent users)3496 Streams operators, 4796 data streams
© 2018 IBM Corporation
43
Outline
Motivation
– Remote Diabetes Monitoring
– Initial Data Analysis
Building the Sugar.IQ Solution
– Application Design
– Distributed Stream Processing
Personalized Machine Learning
– Operationalizing Adaptive Modeling
– ML Lifecycle Management
– Need for Automation – CADS
Discussion
© 2018 IBM Corporation
Hypoglycemia Prediction: Modeling and Data Analysis
44
Dataset: 10000 patients spanning 4 years– Limited to sensor-only readings, for broad applicability across sensor
only as well as pump + sensor and sensor only patients
Novel Modeling Approach: – Users grouped based on their observed temporal behavior, characterized
by several first of a kind features. Per-group predictive models
developed.
– Individualized predictions achieved with user-specific ensembles across
per-group models
Results: 85-89% accuracy# at multiple horizons (2hr and 3hr)– Significantly higher than any other reported results in literature
– Multiple patent disclosures, and publications
81.8
87.1
72.6
83.2
74.3
80.8
84.5
88.5
80.4
84.7
79.681.9
88.289.8
85.9 86.4 85.882.8
70
75
80
85
90
95
2Hr,2K(old) 2Hr,10K(new) 3Hr,2K(old) 3Hr,10K(new) 4Hr,2K(old) 4Hr,10K(new)
MinAUC
MeanAUC
MaxAUC
First of a kind features* that capture short-term, long-term, glucose and insulin measurements
*Invention disclosures filed#Measured as Area under the curve (AUC)
Groupings capture patient temporal behavior
81.8
87.1
72.6
83.2
74.3
80.8
84.5
88.5
80.4
84.7
79.681.9
88.289.8
85.9 86.4 85.882.8
70
75
80
85
90
95
2Hr,2K(old) 2Hr,10K(new) 3Hr,2K(old) 3Hr,10K(new) 4Hr,2K(old) 4Hr,10K(new)
MinAUC
MeanAUC
MaxAUC
Prediction Horizon, Patient Population Size
AU
C (
%) Low-variance, high quality models that are
temporally stable
© 2018 IBM Corporation
Analytic EcosystemOperationalizing Analytic Models: From Offline to Online
45
Data mining
Business logic
• Data representation
• Raw data preprocessing
• Aggregation, filtering
Stream mining
Scoring
operator
SPSS, SAS
Hadoop, Big Insights
Connect
Connect+
Sensor, Pump and Minimed Connect
© 2018 IBM Corporation
Hypoglycemia Prediction: Need for self-learning models
Unlike monitoring hurricanes or tsunami, our monitoring and early
warning actually changes the behavior of the monitored subject
–Such behavior change leads to fewer and fewer predictive signals
–We have evidence showing negative correlation between pump’s
low glucose alert and hypoglycemia for some users
Three layer predictive model allows for continuous learning and
adaptation
–Bottom layer: Bolus driven segments can be refreshed periodically
–Middle layer: Predictive model per segment built adaptively based
on measured model quality
–User personalized model: Ensemble across segment models with
weights specific to user
46
© 2018 IBM Corporation
Business logic
Data mining
Trigger generation
of new model
Ensemble of models
Model
Scoring
operatorModel
Scoring
operator
ii
• Data representation
• Raw data preprocessing
• Aggregation, filtering
SPSS, SAS
Hadoop, Big Insights
Analytic EcosystemOperationalizing Analytic Models: From Offline to Online Learning
Connect
Connect+
Sensor, Pump and Minimed Connect
47
© 2018 IBM Corporation
Operationalizing Self-Learning Models at ScaleHow do we retrain 100s of thousands of personalized models
48
Business logic
Trigger generation
of new model
Ensemble of models
Model
Scoring
operatorModel
Scoring
operator
ii
• Data representation
• Raw data preprocessing
• Aggregation, filtering
Connect
Connect+
Sensor, Pump and Minimed Connect
Integrate CADS into Machine Learning Model Lifecycle
© 2018 IBM Corporation
49
Outline
Overview
– Business Case
– Timeline
Show and Tell: Sugar.IQ Solution
– Behavioral Insights
– Hypoglycemia Prediction
– Demo
Glimpse of Analytics behind Pretty Pictures
Close the Loop - Analytic Lifecycle Management
– From Data Analysis to Operational Models
– Need for Automation – CADS
Discussion
© 2018 IBM Corporation
50
Questions?
Deepak S. Turaga, MS, PhD
Distinguished Research Staff Member
IBM Research AI
• Want to get involved?
Topic or Speaker ideas
Key Note Presenter
Blogger | Tweeting
• Community Website
Visit the ‘Session Recordings’ tab at
www.himss.org/ClinBusIntelCommunity for
a copy of this or previous presentations
Wrap-Up / Next Steps
Contact
Shelley Price or
Joanne Bartley
#PutData2Work | #PopHealthIT | #PrecisionHIT
Earn CAHIMS & CPHIMS credit!
The HIMSS C&BI Community is pleased to offer webinar attendees
up to one continuing education (CE) hour for use in fulfilling the CE
requirements of the Certified Professional in Healthcare Information &
Management Systems (CPHIMS) and the Certified Associate in
Healthcare Information & Management Systems (CAHIMS) programs.
Visit the C&BI Community website for more information.
Wrap-Up / Next Steps
Wrap-Up / Next Steps
JOIN US!
Next meeting: Tuesday, February 6, 2018
SPECIAL JOINT EVENT WITH THE HIMSS
INNOVATION COMMUNITY!
Innovative uses of analytics to improve
outpatient primary care delivery
Speaker(s):
Dr. Danielle Oryn, DO, MPH, Chief Medical
Informatics Officer | Petaluma Health Center
Shaun Nelson, MPH, Senior Data Analyst |
Petaluma Health Center
#PutData2Work | #PopHealthIT | #PrecisionHIT
Co-Chairs:
Mike Berger, PE, CPHIMS Vice President, Population Health Informatics & Data Science Mount Sinai Health [email protected]
Arthur Panov, MPH, CPHIMS Healthcare and Life Sciences ArchitectureIBM Watson [email protected]
HIMSS Community Organizers:
Shelley Price, MS, FHIMSS Joanne Bartley, CAEDirector, Payer and Life Sciences Manager, Health Business SolutionsHIMSS [email protected] | @SPriceHIMSS [email protected]
FY18 Leadership & Contact Information
#PutData2Work | #PopHealthIT | #PrecisionHIT
Thank you!!!
#PutData2Work | #PopHealthIT | #PrecisionHIT
APPENDIX
Ellen Harper, DNP, RN-BC, MBA, FAAN*FY18 C&BI Committee Chair
Adjunct Faculty, U of Minnesota School of Nursing
President, CEO, Blue Water Informatics, LLC
Claudine Beron, PMPFY18 C&BI Committee Vice-Chair
CEO
Initiate Government Solutions, LLC
Meg Broderick, MBA, MPA, CPHIMS*Consultant
Sharon Davis, CPHIMS, PMPSr. Project Manager
VIZIENT
Jeff Fuller, MS, FACHE*
Executive Director, Analytical Solutions
U of North Carolina (UNC) Healthcare System
Kevin Gormley, PhD, MEPrincipal Data Scientist
MITRE
Mitch KwiatkowskiSr. Director, Informatics
Gateway Health
Raj Lakhanpal, MD, FACEP*CEO
Spectramedix
Anne Park, MPH, MSMIS*Sr. Business Systems Analyst
MD Anderson Cancer Center
Anthony C Villanueva, CPHIMSCIO, Vice President of IT/IS
Neighborhood Health
Anthony T. Williams, MBA*Chief Information Officer
American Family Care, Inc.
Amber Zimmermann, BSN, MBA, RN-BCSr Manager, Health Data Analytics
Philips Healthcare
* Indicates a returning
committee member
About Us: FY2018 C&BI Committee Members
Community Co-Chairs
Mike Berger, PE, CPHIMS
Vice President, Population Health
Informatics and Data Science
Mount Sinai Health
Arthur Panov, MPH, CPHIMS
Healthcare and Life Sciences Architecture
IBM Watson Health
C&BI for Population Health
Task Force Co-Chairs
Marius Petruc, MD, MS
President
Informatics Solutions, LLC
Michelle Vislosky, M.B.A., FACHE
Director of Health System
Partnerships
Syapse
About Us: FY18 C&BI Community, Task Force, Workgroup Leadership
Precision Medicine Workgroup ChairBG Jones
SVP - Business Development
PierianDX
About Us: C&BI Community
Looking to better leverage clinical & business intelligence tools, technologies,
and strategies to help you and your organization meet patient care delivery,
clinical and health outcome, and business operation goals? Our community
supports activities that promote peer-to-peer networking, problem solving,
solution sharing, and education.
HIMSS C&BI Community webinars let members dig into pertinent subjects
throughout the year. Our ongoing web-based programs cover topics such as:
Data aggregation and access through EDW and cloud solutions
Data management, validation, quality, and integration
Descriptive, retrospective, predictive, and prescriptive analytics
Governance – data and program
Population health management – including attribution and risk stratification
Precision medicine
Predictive modeling
Reporting, dashboards, and visualization techniques
Resource management
Skills sets and staffing
www.himss.org/ClinBusIntelCommunity
About Us: C&BI Community
• Open to all HIMSS members (current membership: approx 7,800 people). Join the
C&BI Community today:
1. Login into your HIMSS account in the Member Center
2. Click the tab "My Involvement" | select "Participation" dropdown
3. Click on "Edit Participations"
4. Check the “Clinical & Business Intelligence Community” box
5. Click "Save"
• Will meet virtually 6 times/year
• Agenda for the meetings may include:
News you can use! New content and events
2-Minute Drills presented by various Community members
Topical discussion with key note presenter
The ‘2-Minute Drill’ is based loosely on the sports analogy, and in this case
is a fast-paced (short in length) presentation on a hot, emerging, or timely topic, news event (e.g. research paper, game-changing market or technology news), or recent and relevant event (e.g., federal public meeting, legislative/federal/judicial news, critical conference or educational event).
2-Minute Drills foster greater peer-to-peer networking, member engagement, problem solving, solution sharing, and education. If you are interested in presenting any drills,
please contact Shelley Price.
About Us: Task Force
C&BI for Population Health Task Force
CO-CHAIR: Marius Petruc, MD, MS | President | Informatics Solutions, LLC
CO-CHAIR: Michelle Vislosky, MBA, FACHE | Director of Health System Partnerships
| Syapse
This group creates resources and tools that employ practical guidance and
unbiased information to help healthcare organizations (providers, hospitals,
integrated delivery networks, health plans and other stakeholders) use C&BI to
harness, use and analyze data captured in the healthcare setting to execute
population health management initiatives and improve care and health
outcomes.
Meeting times: 3rd Tuesday of the month, 4:00-5:00pm ET