the green button project - himss365 · 2019. 2. 8. · the green button project physician symposium...
TRANSCRIPT
![Page 1: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/1.jpg)
1
The Green Button ProjectPhysician Symposium Session #3, February 11 2019
Alison Callahan MISt PhD, Research Scientist, Stanford University
![Page 2: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/2.jpg)
2
Alison Callahan, PhD, has no real or apparent conflicts of interest to report.
Conflict of interest
![Page 3: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/3.jpg)
3
• The Green Button origin story
• Anatomy of the consult service
• Methods and challenges
• Learning from the first 100 consults
• Deploying the service at a new site
• Ongoing efforts
Agenda
![Page 4: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/4.jpg)
4
• Define use cases for an informatics consult service
• Describe requirements for setting up an informatics consult service
• Plan deployment of an informatics consult service at a new site
Learning objectives
![Page 5: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/5.jpg)
5
Informatics Consult team
Acknowledgements
Funding: NLM, NIGMS, Stanford School of Medicine, Department of Medicine, Department of
Biomedical Data Science, Center for Population Health Sciences, an anonymous donor
Stanford Health Care partners
David Entwistle Tip Kim
Christopher SharpNigam Shah
Saurabh Gombar
Robert Harrington
Alison Callahan Vladimir Polony
Rob Tibshirani
Ken Jung
Trevor Hastie
![Page 6: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/6.jpg)
6
A teenager with systemic lupus erythematosus
• proteinuria
• antiphospholipid antibodies
• pancreatitis
Meet Laura
Source: Mayo Foundation for Medical Education and Research
![Page 7: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/7.jpg)
7
Managing Laura’s care
Source: Mayo Foundation for Medical Education and Research
![Page 8: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/8.jpg)
8
The Origin of the Green Button
![Page 9: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/9.jpg)
9
Finding patients with
“X”
2-3 weeks to
generate a cohort
![Page 10: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/10.jpg)
10
![Page 11: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/11.jpg)
11
Given a specific case, provide a report with a descriptive summaryof similar patients in Stanford’s clinical data warehouse, thecommon treatment choices made, and the observed outcomes afterspecific treatment choices.
An institutional review board approved study (IRB # 39709) overone year.
The Informatics Consult Service
http://greenbutton.stanford.edu
![Page 12: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/12.jpg)
12
An example report
![Page 13: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/13.jpg)
13
The process
Requesting
physician
Informatics
physician
EHR data
specialist
Data
scientist
Request
consultRefine
clinical
question
Create
definitions
for
exposures
and
outcomesBuild
patient
cohorts
Perform
statistical
analysis
Write
consult
report
Review
results
Apply
evidence
to clinical
decision
24 to 72 hours
![Page 14: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/14.jpg)
14
• Building patient cohorts accurately and quickly
• Asking the right question
• Controlling for confounding
• Ensuring quick turnaround
Methods and challenges
![Page 15: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/15.jpg)
15
1 0 -1
1 0 -1
1 0 -1
Building patient cohorts
1. How will you handle time?2. What features will you use?3. How will you state your phenotype definition?
From timelines to data frames
Phenoty
pin
g
P
ers
on
s
Features
1 0 -1
ProceduresDevicesDiseasesDrugs
1 • cost
• utility
![Page 16: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/16.jpg)
16
The search engine
• Diagnosis and procedure
codes
• Clinical notes
• Lab results
• Vital signs
• Inpatient and outpatient visits
www.tinyurl.com/search-ehr
![Page 17: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/17.jpg)
17
Asking the right question
![Page 18: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/18.jpg)
18
• Identify subsets of patient cohorts that are “similar”
– Matching on age, gender, record length, year
– Using propensity score matching
Controlling for confounding
Pj
Pi
Pk
![Page 19: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/19.jpg)
19
• Use negative controls for empirical calibration
• E-values to quantify the degree of confounding that can produce the observed effect
• Ask the question using multiple datasets
• Schedule an in-person debrief
What we do to not be wrong
![Page 20: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/20.jpg)
20
• Search engine API available in CRAN
• R library for data pre-processing
• Semi-automated pipeline for survival and causal analyses, report generation
Ensuring quick turnaround
![Page 21: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/21.jpg)
21
Guideline
available?
Use level A
guideline
Yes
No
Use
Green
Button
Large cohort of patients
present?
Yes
Use
professional
judgementNo
Analysis + Report
• The question as posed
• How we asked the question
• Our interpretation
• Research walkthrough
List of clinical
situations
Candidates for further
study
Point of care randomization/
large simple trial
Useful
byproduct
High
priority
Increment
priority
![Page 22: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/22.jpg)
22
Learning from the first 100 consults
• How many? 55%
• Which treatment? 30%
• How long? 15%
![Page 23: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/23.jpg)
23
Learning from the first 100 consults
![Page 24: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/24.jpg)
24
“likely to recommend” was 100%
Learning from the first 100 consults
![Page 25: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/25.jpg)
25
• Institutional support
• Data science expertise
• Marketing
• A process to sanity-check the data and consult findings
Deploying the service at your site
![Page 26: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/26.jpg)
26
We’re not the first to provide an on-demand informatics consult service
![Page 27: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/27.jpg)
27
![Page 28: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/28.jpg)
28
![Page 29: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/29.jpg)
29
Stanford: 3 million
Optum: 55 million
Truven: 126
million
Now versus then
![Page 30: The Green Button Project - HIMSS365 · 2019. 2. 8. · The Green Button Project Physician Symposium Session #3, February 11 2019 Alison Callahan MISt PhD, Research Scientist, Stanford](https://reader034.vdocuments.mx/reader034/viewer/2022051607/602add3309dcb1735d6c7d6d/html5/thumbnails/30.jpg)
30
• What is really useful?
– Description of what happened
– Estimation: Population or Individual level
– Patient level prediction
• Financial viability – who can pay for this “test”?
• Informatics research
– Phenotyping (how do I know the patient had X)
– Representation learning
– Matching, and population level inference
– Personalized effect estimates
• Deploying as a hospital-side service at Stanford Health Care
Open questions and ongoing efforts