Getting to a Learning Health System through Learning Health Units: - - PowerPoint PPT Presentation

▶
getting to a learning health system through learning
SMART_READER_LITE
LIVE PREVIEW

Getting to a Learning Health System through Learning Health Units: - - PowerPoint PPT Presentation

Jun 23, 2023 174 likes •756 views

Getting to a Learning Health System through Learning Health Units: Opportunities and Challenges DUKE UNIVERSITY DUKE HEALTH Adrian F. Hernandez, MD Vice Dean for Clinical Research LEARNING HEALTH Key questions: Are we achieving our

slide-1
SLIDE 1

Getting to a Learning Health System through Learning Health Units: Opportunities and Challenges

Adrian F. Hernandez, MD Vice Dean for Clinical Research

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

slide-2
SLIDE 2

Key questions:

  • Are we achieving our goals of a learning

health system?

  • Based on your experience so far, what are

the key attributes for a learning health system?

  • If you wanted to get real, high quality results,

really fast…how would you design it?

2

slide-3
SLIDE 3

Agenda

  • Origins of the learning health system
  • Getting answers:

– The patient? – The clinician? – The data scientist?

  • Designing a learning health unit

3

slide-4
SLIDE 4

Revisiting the concept of a learning health system

4 AMIA 2017 | amia.org

Aspiration: bring timely, accurate, and current clinical information to the point of care to help patients and clinicians make

  • ptimal healthcare choices

Evidence is iteratively applied and developed as a natural part of the care delivery process Entails engagement of a range of stakeholders: health system leaders, front line clinical practitioners, patients, payers, policymakers Deep reliance on data, rapid analytics, and supportive culture

Courtesy: Eric Larson

slide-5
SLIDE 5

Remember when….

5

slide-6
SLIDE 6

Enormous ideas…

6

slide-7
SLIDE 7

7

Giving an honest grade on achieving the vision…

The Institute of Medicine’s (NAM) vision:

 Research happens closer to clinical practice than in traditional university settings.  Scientists, clinicians, and administrators work together.  Studies occur in everyday practice settings.  Electronic medical records are linked and mined for research.  Recognition that clinical and health system data exist for the public good.

Summary: Evidence informs practice and practice informs evidence.

slide-8
SLIDE 8

Selective Reflections

8

slide-9
SLIDE 9

9

Selective Reflections

slide-10
SLIDE 10

Agenda

  • Origins of the learning health system
  • Getting answers:

– The patient? – The clinician? – The data scientist?

  • Designing a learning health unit

10

slide-11
SLIDE 11

If you had a health question, what would you do?

slide-12
SLIDE 12
slide-13
SLIDE 13

MAYO (& NOT DUKE) ??

slide-14
SLIDE 14

Willingness to join learning health systems

Surveys say… Reality is…

2-3%

slide-15
SLIDE 15

Agenda

  • Origins of the learning health system
  • Getting answers:

– The patient? – The clinician? – The data scientist?

  • Designing a learning health unit

15

slide-16
SLIDE 16

What would a clinician want?

  • ZDoggMD http://zdoggmd.com/ehr-state-of-mind/
slide-17
SLIDE 17
slide-18
SLIDE 18

Evolving Health Data EcoSystem

  • JAMA. 2014;311(24):2479-2480.

doi:10.1001/jama.2014.4228 Setting:

  • Individual
  • Health system
  • National

Type:

  • Biological
  • Clinical
  • Behavioral
  • Social
  • Environmental

Solutions:

  • Integration
  • Cultural
  • Regulatory
  • Legal
slide-19
SLIDE 19

Patient….. EMR......Big Data.... Big Answers

Data are necessary but not always sufficient

slide-20
SLIDE 20

Patient….. EMR......Big Data.... Big Answers

Data are necessary but not always sufficient

slide-21
SLIDE 21

Patient….. EMR......Big Data.... Big Answers

Data are necessary but not always sufficient

slide-22
SLIDE 22

Patient….. EMR......Big Data.... Big Answers

Data are necessary but not always sufficient

slide-23
SLIDE 23

Patient….. EMR......Big Data.... Big Answers

Data are necessary but not always sufficient

Clinicians may be important too

slide-24
SLIDE 24

Data Deluge for Clinicians

Bloss CS, et al. PeerJ, 2016

slide-25
SLIDE 25
slide-26
SLIDE 26

Doing the right thing for the right patient

Extreme Phenotyping

slide-27
SLIDE 27
slide-28
SLIDE 28

3 HFpEF “Pheno-Groups” Identified

  • Younger patients with lower BNP elevations
  • Obese patients with sleep apnea and DM
  • Older patients with CKD
slide-29
SLIDE 29

3 HFpEF “Pheno-Groups” Identified

  • Younger patients with lower BNP elevations
  • Obese patients with sleep apnea and DM
  • Older patients with CKD

Only one small issue: What’s the treatment?

slide-30
SLIDE 30

Agenda

  • Origins of the learning health system
  • Getting answers:

– The patient? – The clinician? – The data scientist?

  • Designing a learning health unit

30

slide-31
SLIDE 31

What would a data scientist want?

slide-32
SLIDE 32

Multi-Dimensional Research Platforms

slide-33
SLIDE 33

Automated, reliable, high quality data? Common Data Models

  • Content coverage
  • Integrity
  • Flexibility
  • Queriability
  • Integration/Standards
  • Implementability

Garza M et al. Journal of Biomedical Informatics 2016

slide-34
SLIDE 34

Predicting Sepsis

Pythia’s surgical complications risk prediction calculator: A fully-functioning prototype application

An institute-specific, open-access, automated database used to build healthcare research, QI and decision- support tools using best-in-class methodologies featuring innovative and original technology

  • Courtesy Suresh Balu
slide-35
SLIDE 35

Quality Assurance:

Using machine learning to advance imaging

slide-36
SLIDE 36 BEGINNING OF MONTH

REGISTRY

Of interventions,
  • utcomes, model
versions, patient-level prediction history

MODEL

Probability of Unplanned Admissions for:

  • Any Cause
  • 31 Diagnostic Categories
  • Absolute and Percentile Rank

6 MONTH PREDICTION WINDOW CARE MANAGEMENT WORKFLOW

10 YEAR RETROSPECTIVE HER (COMMON DATA MODEL) DATA 12-MONTH RETROSPECTIVE CMS CLAIMS DATA

  • Weekly rounding on high risk patients

by PHMO care managers

  • High risk patient list distributed to

primary care practices

  • Care redesign efforts around

intensive case management and management of serious illness including patient, provider, and practice engagement

  • Foundational work around population

health management for value based contracts

Monthly Data Refresh Monthly Predictive Model Retraining

”Lego” Building Blocks for Data Science: Snap together components to be leveraged for other LHU projects

USING MACHINE LEARNING TO ADVANCE CARE

Deep Care Management in Duke Connected Care

Courtesy Erich Huang, MD

slide-37
SLIDE 37

Can you imagine a world that you simply had a conversation with a patient …and didn’t type a note?

slide-38
SLIDE 38
slide-39
SLIDE 39

Agenda

  • Origins of the learning health system
  • Getting answers:

– The patient? – The clinician? – The data scientist?

  • Designing a learning health units

39

slide-40
SLIDE 40

750,000

  • Imagine you are the CEO of a health system

responsible for the care and outcomes of this population..

  • And you are tied (anchored) to an academic

health system

  • And you have to be fiscally responsible
  • What would you do with the data generated every

day to improve the heath of the next person?

Hypothetical Situation

slide-41
SLIDE 41

Choices on your desk

41

What’s the net present value?

A

(6 months)

C

(??)

B

(2 years)

slide-42
SLIDE 42

Choices on your desk

42

What’s the net present value?

D

(7 years)

slide-43
SLIDE 43

Quality

Flipping the Model: New Environment, Different Expectations

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

Clinical/Population

4 3

Science

slide-44
SLIDE 44

Transition to Value-based Care

2019 2020 2018 2021 & Beyond 2014

Fee-For-Service

Pre- 2013

44

Value-based Care

2017 2015 2016

slide-45
SLIDE 45

45

Use Case: Transitions for Cardiovascular Care

  • Historically designed to improve access to highly reimbursed care
  • Now, that is not enough…

Cost/Margin

High $ Low $

Low High

Clinical Evidence High Cost No Evidence Stop Doing It Study Low/No Cost High Evidence YES! Keeping doing it. Population Health Potential for Value

slide-46
SLIDE 46

A Typical Health System: How Supply Tries to Meet Demand Today

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

4 6 DCRI/CPM Margolis Engineering AI ACE/PORT/ DART DOCR

Crucible

CTSI/BERD PHMO IT ORI DIHI Statistics/ Computer Science Performance Services B&B/PHS Forge Finance Maestro/DHTS

Payer Departments & Clinical Research Units Outcomes & Operations Finance Physician Practice Safety & Quality Primary Care Others

Clinical, Business & Operations

slide-47
SLIDE 47

Learning Health Units: Transforming Health in One Duke

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

4 7

slide-48
SLIDE 48

Learning Health Units: Transforming Health in One Duke

Patients Clinicians Researchers Community Engagement

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

4 8

slide-49
SLIDE 49

Learning Health Units: Transforming Health in One Duke

Patients Clinicians Researchers Community Informatics Curation Infrastructure Health Technology Engagement Data Liquidity

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

4 9

slide-50
SLIDE 50

Learning Health Units: Transforming Health in One Duke

Patients Clinicians Researchers Community Informatics Curation Infrastructure Health Technology Engagement Data Liquidity

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

5

Practice Process Payment Policy

slide-51
SLIDE 51

Learning Health Units: Transforming Health in One Duke

Patients Clinicians Researchers Community Artificial Intelligence Statistics Rapid Analytics Embedded Trials Practice Process Payment Policy Informatics Curation Infrastructure Health Technology Implementation & Evaluation Research Engagement Data Liquidity

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

5 1

slide-52
SLIDE 52

Learning Health Units: Transforming Health in One Duke

Patients Clinicians Researchers Community Artificial Intelligence Statistics Rapid Analytics Embedded Trials Practice Process Payment Policy Informatics Curation Infrastructure Health Technology Implementation & Evaluation Research

L H U

Engagement Data Liquidity

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

5 2

slide-53
SLIDE 53

Learning Health Unit

Essential Question Data Liquidity Data Curation Science Answer Impact

LHU: Uniting Clinicians, Researchers, and Data Scientists

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

5 3 Derivatives:

  • Curated cohorts

for research

  • Workforce

development

  • Academic

advances RESEARCH & DEVELOPMENT Derivatives:

  • Embedded

data science

  • Implementation

science

  • Clinical

innovation IMPLEMENTATION & EVALUATION

slide-54
SLIDE 54

Learning Health Unit

Clinicians Service Line VPs Data Engineers

Solutions Engineers

Data Scientists

User Experience Specialists Imple- mentation Specialists

LHU: Uniting Clinicians, Researchers, and Data Scientists

DUKE UNIVERSITY DUKE HEALTH LEARNING HEALTH

5 4 IMPLEMENTATION & EVALUATION RESEARCH & DEVELOPMENT

slide-55
SLIDE 55

Value-Based Care Demands Integrated Responses

5 5

Questions

How can we improve 30-day mortality? How can we prevent unnecessary readmissions? How can we increase appropriate use and accuracy of diagnostic testing?

Improved Health Better Quality Value- Based Care

Informatics Curation Infrastructure Health Technology AI Statistics Rapid Analytics Embedded Trials Practice Process Payment Policy

slide-56
SLIDE 56

LHU Focus

Complexity

High Low

Low High

Immediate Clinical Value Low Immediacy, High Complexity Research Low Immediacy, Low Complexity High Immediacy, Low Complexity Health System Improvement High Immediacy, High Complexity

LHUs

slide-57
SLIDE 57

Summary:

  • Are we achieving our goals of a learning health

system?

– Not yet

  • Based on your experience so far, what are the key

key attributes for a learning health system?

– Culture, investment, data, research, results…

  • If you wanted to get real results, really fast…how

would you design it?

– That’s the question

57