SlideShare a Scribd company logo
Machine Learning and
Patient Engagement
@timgilchrist
Big Data
• Many data sources with different formats
• Data with missing values
• Text / Social Media
• Things that don’t fit in Excel
The term for a collection of data sets so large and
complex that they become difficult to process
Artificial Intelligence
3
“Pay no attention to the man behind the curtain”
Machine Learning
4
The construction and study of systems that can learn
from data
Where did it all Start? Bayes
Thomas Bayes (1701 – 7 April 1761)was an English mathematician
and Presbyterian minister, known for formulating the theorem
that bears his name: Bayes' theorem
• Bayes theorem uses prior probabilities, combined with new
observations to calculate the probability of a hypothesis being true or
false
• Bayes is a natural fit to health care due to the presence of hypothesis
(diagnosis) and events (tests / observations)
5
Bayes Example
6
33% 33% 33%10% 80% 10%
How can we Apply Machine Learning in
Healthcare?
7
Identify patterns that humans have trouble seeing
Population
Health
Care
Optimization
Precision
Medicine
R&D
Productivity
What Does this Mean To Patient
Engagement?
8
You are Here
Regression
9
Cost
ER Visits
Classification
10
Orthopedic
Chest Pain
Abdominal Pain
Cost
ER Visits
Example
Social Media Text Mining / Diabetes
11
Twitter Users Self-Described Diabetics
12
•What if you could identify “real” diabetics on twitter?
• You could engage them in diabetes education, etc.
• Cost = $0
• Know things that don’t show up in claims (latency)
• Possibly alert the undiagnosed
“Lets play a game called how many times
will my relatives ask about my diabetes.
#byyyyeeee”
Results
• 73.5% Accuracy (ability to identify self-
described diabetics from spam, people
mentioning other people’s diabetes,
retweets, bots, etc.)
•Variables in order of importance
• #times others favorited tweets
• #followers
• #user statues
13
Results / Decision Tree
14
# Favorites
# Followers
# Statuses
True (48% / 2%)
<=226 >226
True (44% / 21%)
<=1903 >1903
True (6% / 0%)
<=65.5
Example
MI Patients not Taking Beta Blockers
15
MI Patients not Taking Beta Blockers
16
•What patterns exist in this population?
• You had a heart attack but not taking beta
blockers
• What can we learn to effectively reach these
people
• Are they homogeneous or are there sub groups
• Preemptive activities?
Results
• 74% Accuracy (ability to predict
compliance with rule – take beta blockers)
•Variables in order of importance
• #primary diagnoses
• #Evaluation & Management visits
• Prior compliance with other rules
17
Results / Decision Tree
18
NC = 68%
SC = 25%
UC = 6%
100%
1,2 0
NC = 42%
SC = 46%
UC = 12%
35%
NC = 82%
SC = 14%
UC = 3%
64%
#primary diagnoses
< 1 >= 2
NC = 86%
SC = 13%
UC = 0%
8%
NC = 29%
SC = 55%
UC = 15%
8%
E&M Visits
NC = Never Compliant
SC = Sometimes Compliant
UC = Usually Compliant

More Related Content

Similar to Presentation to The Innovative Member Engagement Conference Oct 22 Las Vegas

Prof Mendel Singer Big Data Meets Public Health and Medicine 2018 12-22
Prof Mendel Singer Big Data Meets Public Health and Medicine 2018 12-22Prof Mendel Singer Big Data Meets Public Health and Medicine 2018 12-22
Prof Mendel Singer Big Data Meets Public Health and Medicine 2018 12-22
mjbinstitute
 
The Learning Health System: Thinking and Acting Across Scales
The Learning Health System: Thinking and Acting Across ScalesThe Learning Health System: Thinking and Acting Across Scales
The Learning Health System: Thinking and Acting Across Scales
Philip Payne
 
Power to the Patient
Power to the PatientPower to the Patient
Power to the Patient
Bastian Greshake
 
Big data chicago v2 5 14 14
Big data chicago v2 5 14 14Big data chicago v2 5 14 14
Big data chicago v2 5 14 14
Tim Gilchrist
 
Wake up Pharma and look into your Big data
Wake up Pharma and look into your Big data Wake up Pharma and look into your Big data
Wake up Pharma and look into your Big data
Yigal Aviv
 
Atul Butte NIPS 2017 ML4H
Atul Butte NIPS 2017 ML4HAtul Butte NIPS 2017 ML4H
Atul Butte NIPS 2017 ML4H
University of California, San Francisco
 
Presentation1a paul carpenter
Presentation1a paul carpenterPresentation1a paul carpenter
Presentation1a paul carpenter
YinglingV
 
Debunking Made Easy, AHCJ 2014
Debunking Made Easy, AHCJ 2014Debunking Made Easy, AHCJ 2014
Debunking Made Easy, AHCJ 2014
Ivan Oransky
 
Imogen Mitchell - Morphing the Recalcitrant Clinician
Imogen Mitchell - Morphing the Recalcitrant ClinicianImogen Mitchell - Morphing the Recalcitrant Clinician
Imogen Mitchell - Morphing the Recalcitrant Clinician
SMACC Conference
 
Utilizing Social Health Websites for Cognitive Computing and Clinical Decisio...
Utilizing Social Health Websites for Cognitive Computing and Clinical Decisio...Utilizing Social Health Websites for Cognitive Computing and Clinical Decisio...
Utilizing Social Health Websites for Cognitive Computing and Clinical Decisio...
CrowdTruth
 
Suzanne M. Rivera and Heide Aungst "What Specimen Donors Think (and Considera...
Suzanne M. Rivera and Heide Aungst "What Specimen Donors Think (and Considera...Suzanne M. Rivera and Heide Aungst "What Specimen Donors Think (and Considera...
Suzanne M. Rivera and Heide Aungst "What Specimen Donors Think (and Considera...
The Petrie-Flom Center for Health Law Policy, Biotechnology, and Bioethics
 
Sophia Zilber - Mito research and data webinar - June 3, 2021
Sophia Zilber - Mito research and data webinar - June 3, 2021Sophia Zilber - Mito research and data webinar - June 3, 2021
Sophia Zilber - Mito research and data webinar - June 3, 2021
SophiaZilber
 
Terms and Conditions for Trust in Learning Health Systems
Terms and Conditions for Trust in Learning Health SystemsTerms and Conditions for Trust in Learning Health Systems
Terms and Conditions for Trust in Learning Health Systems
Department of Learning Health Sciences, University of Michigan Medical School
 
Overview of Health IT
Overview of Health ITOverview of Health IT
Overview of Health IT
Nawanan Theera-Ampornpunt
 
5 Tips to Make you a Survey Measurement Rock Star
5 Tips to Make you a Survey Measurement Rock Star5 Tips to Make you a Survey Measurement Rock Star
5 Tips to Make you a Survey Measurement Rock Star
Wendy Preisman Turell, DrPH
 
Introduction to Health Informatics and Health Information Technology (Part 2)...
Introduction to Health Informatics and Health Information Technology (Part 2)...Introduction to Health Informatics and Health Information Technology (Part 2)...
Introduction to Health Informatics and Health Information Technology (Part 2)...
Nawanan Theera-Ampornpunt
 
Jon Tilburt, MD - Assessing Health Priorities of Tribal Health Directors with...
Jon Tilburt, MD - Assessing Health Priorities of Tribal Health Directors with...Jon Tilburt, MD - Assessing Health Priorities of Tribal Health Directors with...
Jon Tilburt, MD - Assessing Health Priorities of Tribal Health Directors with...
trainer2007
 
Approch note customer behavior towards Healthcare and Wellness
Approch note customer behavior towards Healthcare and WellnessApproch note customer behavior towards Healthcare and Wellness
Approch note customer behavior towards Healthcare and Wellness
Bang Design
 
Digital Health Transformation for Health Executives (January 18, 2022)
Digital Health Transformation for Health Executives (January 18, 2022)Digital Health Transformation for Health Executives (January 18, 2022)
Digital Health Transformation for Health Executives (January 18, 2022)
Nawanan Theera-Ampornpunt
 
Integrating Design Using the Native Language of Healthcare
Integrating Design Using the Native Language of HealthcareIntegrating Design Using the Native Language of Healthcare
Integrating Design Using the Native Language of Healthcare
Joyce Lee
 

Similar to Presentation to The Innovative Member Engagement Conference Oct 22 Las Vegas (20)

Prof Mendel Singer Big Data Meets Public Health and Medicine 2018 12-22
Prof Mendel Singer Big Data Meets Public Health and Medicine 2018 12-22Prof Mendel Singer Big Data Meets Public Health and Medicine 2018 12-22
Prof Mendel Singer Big Data Meets Public Health and Medicine 2018 12-22
 
The Learning Health System: Thinking and Acting Across Scales
The Learning Health System: Thinking and Acting Across ScalesThe Learning Health System: Thinking and Acting Across Scales
The Learning Health System: Thinking and Acting Across Scales
 
Power to the Patient
Power to the PatientPower to the Patient
Power to the Patient
 
Big data chicago v2 5 14 14
Big data chicago v2 5 14 14Big data chicago v2 5 14 14
Big data chicago v2 5 14 14
 
Wake up Pharma and look into your Big data
Wake up Pharma and look into your Big data Wake up Pharma and look into your Big data
Wake up Pharma and look into your Big data
 
Atul Butte NIPS 2017 ML4H
Atul Butte NIPS 2017 ML4HAtul Butte NIPS 2017 ML4H
Atul Butte NIPS 2017 ML4H
 
Presentation1a paul carpenter
Presentation1a paul carpenterPresentation1a paul carpenter
Presentation1a paul carpenter
 
Debunking Made Easy, AHCJ 2014
Debunking Made Easy, AHCJ 2014Debunking Made Easy, AHCJ 2014
Debunking Made Easy, AHCJ 2014
 
Imogen Mitchell - Morphing the Recalcitrant Clinician
Imogen Mitchell - Morphing the Recalcitrant ClinicianImogen Mitchell - Morphing the Recalcitrant Clinician
Imogen Mitchell - Morphing the Recalcitrant Clinician
 
Utilizing Social Health Websites for Cognitive Computing and Clinical Decisio...
Utilizing Social Health Websites for Cognitive Computing and Clinical Decisio...Utilizing Social Health Websites for Cognitive Computing and Clinical Decisio...
Utilizing Social Health Websites for Cognitive Computing and Clinical Decisio...
 
Suzanne M. Rivera and Heide Aungst "What Specimen Donors Think (and Considera...
Suzanne M. Rivera and Heide Aungst "What Specimen Donors Think (and Considera...Suzanne M. Rivera and Heide Aungst "What Specimen Donors Think (and Considera...
Suzanne M. Rivera and Heide Aungst "What Specimen Donors Think (and Considera...
 
Sophia Zilber - Mito research and data webinar - June 3, 2021
Sophia Zilber - Mito research and data webinar - June 3, 2021Sophia Zilber - Mito research and data webinar - June 3, 2021
Sophia Zilber - Mito research and data webinar - June 3, 2021
 
Terms and Conditions for Trust in Learning Health Systems
Terms and Conditions for Trust in Learning Health SystemsTerms and Conditions for Trust in Learning Health Systems
Terms and Conditions for Trust in Learning Health Systems
 
Overview of Health IT
Overview of Health ITOverview of Health IT
Overview of Health IT
 
5 Tips to Make you a Survey Measurement Rock Star
5 Tips to Make you a Survey Measurement Rock Star5 Tips to Make you a Survey Measurement Rock Star
5 Tips to Make you a Survey Measurement Rock Star
 
Introduction to Health Informatics and Health Information Technology (Part 2)...
Introduction to Health Informatics and Health Information Technology (Part 2)...Introduction to Health Informatics and Health Information Technology (Part 2)...
Introduction to Health Informatics and Health Information Technology (Part 2)...
 
Jon Tilburt, MD - Assessing Health Priorities of Tribal Health Directors with...
Jon Tilburt, MD - Assessing Health Priorities of Tribal Health Directors with...Jon Tilburt, MD - Assessing Health Priorities of Tribal Health Directors with...
Jon Tilburt, MD - Assessing Health Priorities of Tribal Health Directors with...
 
Approch note customer behavior towards Healthcare and Wellness
Approch note customer behavior towards Healthcare and WellnessApproch note customer behavior towards Healthcare and Wellness
Approch note customer behavior towards Healthcare and Wellness
 
Digital Health Transformation for Health Executives (January 18, 2022)
Digital Health Transformation for Health Executives (January 18, 2022)Digital Health Transformation for Health Executives (January 18, 2022)
Digital Health Transformation for Health Executives (January 18, 2022)
 
Integrating Design Using the Native Language of Healthcare
Integrating Design Using the Native Language of HealthcareIntegrating Design Using the Native Language of Healthcare
Integrating Design Using the Native Language of Healthcare
 

Recently uploaded

Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...
Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...
Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...
DrDevTaneja1
 
Hypotension and role of physiotherapy in it
Hypotension and role of physiotherapy in itHypotension and role of physiotherapy in it
Hypotension and role of physiotherapy in it
Vishal kr Thakur
 
Innovative Minds France's Most Impactful Healthcare Leaders.pdf
Innovative Minds France's Most Impactful Healthcare Leaders.pdfInnovative Minds France's Most Impactful Healthcare Leaders.pdf
Innovative Minds France's Most Impactful Healthcare Leaders.pdf
eurohealthleaders
 
Vicarious movements or trick movements_AB.pdf
Vicarious movements or trick movements_AB.pdfVicarious movements or trick movements_AB.pdf
Vicarious movements or trick movements_AB.pdf
Arunima620542
 
U Part Wigs_ A Natural Look with Minimal Effort Jokerwigs.in.pdf
U Part Wigs_ A Natural Look with Minimal Effort Jokerwigs.in.pdfU Part Wigs_ A Natural Look with Minimal Effort Jokerwigs.in.pdf
U Part Wigs_ A Natural Look with Minimal Effort Jokerwigs.in.pdf
Jokerwigs arts and craft
 
nurs fpx 4050 assessment 4 final care coordination plan.pdf
nurs fpx 4050 assessment 4 final care coordination plan.pdfnurs fpx 4050 assessment 4 final care coordination plan.pdf
nurs fpx 4050 assessment 4 final care coordination plan.pdf
Carolyn Harker
 
Michigan HealthTech Market Map 2024 with Policy Makers, Academic Innovation C...
Michigan HealthTech Market Map 2024 with Policy Makers, Academic Innovation C...Michigan HealthTech Market Map 2024 with Policy Makers, Academic Innovation C...
Michigan HealthTech Market Map 2024 with Policy Makers, Academic Innovation C...
Levi Shapiro
 
FACIAL NERVE
FACIAL NERVEFACIAL NERVE
FACIAL NERVE
aditigupta1117
 
Mental Health and Physical Wellbeing.pdf
Mental Health and Physical Wellbeing.pdfMental Health and Physical Wellbeing.pdf
Mental Health and Physical Wellbeing.pdf
shindesupriya013
 
Know Latest Hiranandani Hospital Powai News.pdf
Know Latest Hiranandani Hospital Powai News.pdfKnow Latest Hiranandani Hospital Powai News.pdf
Know Latest Hiranandani Hospital Powai News.pdf
Dr. Sujit Chatterjee CEO Hiranandani Hospital
 
DELIRIUM BY DR JAGMOHAN PRAJAPATI.......
DELIRIUM BY DR JAGMOHAN PRAJAPATI.......DELIRIUM BY DR JAGMOHAN PRAJAPATI.......
DELIRIUM BY DR JAGMOHAN PRAJAPATI.......
DR Jag Mohan Prajapati
 
NURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPT
NURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPTNURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPT
NURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPT
blessyjannu21
 
Management of Post Operative Pain: to make doctors conscious about the benefi...
Management of Post Operative Pain: to make doctors conscious about the benefi...Management of Post Operative Pain: to make doctors conscious about the benefi...
Management of Post Operative Pain: to make doctors conscious about the benefi...
Nilima65
 
1比1制作(uofm毕业证书)美国密歇根大学毕业证学位证书原版一模一样
1比1制作(uofm毕业证书)美国密歇根大学毕业证学位证书原版一模一样1比1制作(uofm毕业证书)美国密歇根大学毕业证学位证书原版一模一样
1比1制作(uofm毕业证书)美国密歇根大学毕业证学位证书原版一模一样
5sj7jxf7
 
TEST BANK FOR Health Assessment in Nursing 7th Edition by Weber Chapters 1 - ...
TEST BANK FOR Health Assessment in Nursing 7th Edition by Weber Chapters 1 - ...TEST BANK FOR Health Assessment in Nursing 7th Edition by Weber Chapters 1 - ...
TEST BANK FOR Health Assessment in Nursing 7th Edition by Weber Chapters 1 - ...
rightmanforbloodline
 
R3 Stem Cell Therapy: A New Hope for Women with Ovarian Failure
R3 Stem Cell Therapy: A New Hope for Women with Ovarian FailureR3 Stem Cell Therapy: A New Hope for Women with Ovarian Failure
R3 Stem Cell Therapy: A New Hope for Women with Ovarian Failure
R3 Stem Cell
 
English Drug and Alcohol Commissioners June 2024.pptx
English Drug and Alcohol Commissioners June 2024.pptxEnglish Drug and Alcohol Commissioners June 2024.pptx
English Drug and Alcohol Commissioners June 2024.pptx
MatSouthwell1
 
Fit to Fly PCR Covid Testing at our Clinic Near You
Fit to Fly PCR Covid Testing at our Clinic Near YouFit to Fly PCR Covid Testing at our Clinic Near You
Fit to Fly PCR Covid Testing at our Clinic Near You
NX Healthcare
 
muscluskeletal assessment...........pptx
muscluskeletal assessment...........pptxmuscluskeletal assessment...........pptx
muscluskeletal assessment...........pptx
RushikeshHange1
 
leprosy Case detection and diagnosis.pptx
leprosy Case detection and diagnosis.pptxleprosy Case detection and diagnosis.pptx
leprosy Case detection and diagnosis.pptx
habtegirma
 

Recently uploaded (20)

Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...
Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...
Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...
 
Hypotension and role of physiotherapy in it
Hypotension and role of physiotherapy in itHypotension and role of physiotherapy in it
Hypotension and role of physiotherapy in it
 
Innovative Minds France's Most Impactful Healthcare Leaders.pdf
Innovative Minds France's Most Impactful Healthcare Leaders.pdfInnovative Minds France's Most Impactful Healthcare Leaders.pdf
Innovative Minds France's Most Impactful Healthcare Leaders.pdf
 
Vicarious movements or trick movements_AB.pdf
Vicarious movements or trick movements_AB.pdfVicarious movements or trick movements_AB.pdf
Vicarious movements or trick movements_AB.pdf
 
U Part Wigs_ A Natural Look with Minimal Effort Jokerwigs.in.pdf
U Part Wigs_ A Natural Look with Minimal Effort Jokerwigs.in.pdfU Part Wigs_ A Natural Look with Minimal Effort Jokerwigs.in.pdf
U Part Wigs_ A Natural Look with Minimal Effort Jokerwigs.in.pdf
 
nurs fpx 4050 assessment 4 final care coordination plan.pdf
nurs fpx 4050 assessment 4 final care coordination plan.pdfnurs fpx 4050 assessment 4 final care coordination plan.pdf
nurs fpx 4050 assessment 4 final care coordination plan.pdf
 
Michigan HealthTech Market Map 2024 with Policy Makers, Academic Innovation C...
Michigan HealthTech Market Map 2024 with Policy Makers, Academic Innovation C...Michigan HealthTech Market Map 2024 with Policy Makers, Academic Innovation C...
Michigan HealthTech Market Map 2024 with Policy Makers, Academic Innovation C...
 
FACIAL NERVE
FACIAL NERVEFACIAL NERVE
FACIAL NERVE
 
Mental Health and Physical Wellbeing.pdf
Mental Health and Physical Wellbeing.pdfMental Health and Physical Wellbeing.pdf
Mental Health and Physical Wellbeing.pdf
 
Know Latest Hiranandani Hospital Powai News.pdf
Know Latest Hiranandani Hospital Powai News.pdfKnow Latest Hiranandani Hospital Powai News.pdf
Know Latest Hiranandani Hospital Powai News.pdf
 
DELIRIUM BY DR JAGMOHAN PRAJAPATI.......
DELIRIUM BY DR JAGMOHAN PRAJAPATI.......DELIRIUM BY DR JAGMOHAN PRAJAPATI.......
DELIRIUM BY DR JAGMOHAN PRAJAPATI.......
 
NURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPT
NURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPTNURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPT
NURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPT
 
Management of Post Operative Pain: to make doctors conscious about the benefi...
Management of Post Operative Pain: to make doctors conscious about the benefi...Management of Post Operative Pain: to make doctors conscious about the benefi...
Management of Post Operative Pain: to make doctors conscious about the benefi...
 
1比1制作(uofm毕业证书)美国密歇根大学毕业证学位证书原版一模一样
1比1制作(uofm毕业证书)美国密歇根大学毕业证学位证书原版一模一样1比1制作(uofm毕业证书)美国密歇根大学毕业证学位证书原版一模一样
1比1制作(uofm毕业证书)美国密歇根大学毕业证学位证书原版一模一样
 
TEST BANK FOR Health Assessment in Nursing 7th Edition by Weber Chapters 1 - ...
TEST BANK FOR Health Assessment in Nursing 7th Edition by Weber Chapters 1 - ...TEST BANK FOR Health Assessment in Nursing 7th Edition by Weber Chapters 1 - ...
TEST BANK FOR Health Assessment in Nursing 7th Edition by Weber Chapters 1 - ...
 
R3 Stem Cell Therapy: A New Hope for Women with Ovarian Failure
R3 Stem Cell Therapy: A New Hope for Women with Ovarian FailureR3 Stem Cell Therapy: A New Hope for Women with Ovarian Failure
R3 Stem Cell Therapy: A New Hope for Women with Ovarian Failure
 
English Drug and Alcohol Commissioners June 2024.pptx
English Drug and Alcohol Commissioners June 2024.pptxEnglish Drug and Alcohol Commissioners June 2024.pptx
English Drug and Alcohol Commissioners June 2024.pptx
 
Fit to Fly PCR Covid Testing at our Clinic Near You
Fit to Fly PCR Covid Testing at our Clinic Near YouFit to Fly PCR Covid Testing at our Clinic Near You
Fit to Fly PCR Covid Testing at our Clinic Near You
 
muscluskeletal assessment...........pptx
muscluskeletal assessment...........pptxmuscluskeletal assessment...........pptx
muscluskeletal assessment...........pptx
 
leprosy Case detection and diagnosis.pptx
leprosy Case detection and diagnosis.pptxleprosy Case detection and diagnosis.pptx
leprosy Case detection and diagnosis.pptx
 

Presentation to The Innovative Member Engagement Conference Oct 22 Las Vegas

  • 1. Machine Learning and Patient Engagement @timgilchrist
  • 2. Big Data • Many data sources with different formats • Data with missing values • Text / Social Media • Things that don’t fit in Excel The term for a collection of data sets so large and complex that they become difficult to process
  • 3. Artificial Intelligence 3 “Pay no attention to the man behind the curtain”
  • 4. Machine Learning 4 The construction and study of systems that can learn from data
  • 5. Where did it all Start? Bayes Thomas Bayes (1701 – 7 April 1761)was an English mathematician and Presbyterian minister, known for formulating the theorem that bears his name: Bayes' theorem • Bayes theorem uses prior probabilities, combined with new observations to calculate the probability of a hypothesis being true or false • Bayes is a natural fit to health care due to the presence of hypothesis (diagnosis) and events (tests / observations) 5
  • 6. Bayes Example 6 33% 33% 33%10% 80% 10%
  • 7. How can we Apply Machine Learning in Healthcare? 7 Identify patterns that humans have trouble seeing Population Health Care Optimization Precision Medicine R&D Productivity
  • 8. What Does this Mean To Patient Engagement? 8 You are Here
  • 11. Example Social Media Text Mining / Diabetes 11
  • 12. Twitter Users Self-Described Diabetics 12 •What if you could identify “real” diabetics on twitter? • You could engage them in diabetes education, etc. • Cost = $0 • Know things that don’t show up in claims (latency) • Possibly alert the undiagnosed “Lets play a game called how many times will my relatives ask about my diabetes. #byyyyeeee”
  • 13. Results • 73.5% Accuracy (ability to identify self- described diabetics from spam, people mentioning other people’s diabetes, retweets, bots, etc.) •Variables in order of importance • #times others favorited tweets • #followers • #user statues 13
  • 14. Results / Decision Tree 14 # Favorites # Followers # Statuses True (48% / 2%) <=226 >226 True (44% / 21%) <=1903 >1903 True (6% / 0%) <=65.5
  • 15. Example MI Patients not Taking Beta Blockers 15
  • 16. MI Patients not Taking Beta Blockers 16 •What patterns exist in this population? • You had a heart attack but not taking beta blockers • What can we learn to effectively reach these people • Are they homogeneous or are there sub groups • Preemptive activities?
  • 17. Results • 74% Accuracy (ability to predict compliance with rule – take beta blockers) •Variables in order of importance • #primary diagnoses • #Evaluation & Management visits • Prior compliance with other rules 17
  • 18. Results / Decision Tree 18 NC = 68% SC = 25% UC = 6% 100% 1,2 0 NC = 42% SC = 46% UC = 12% 35% NC = 82% SC = 14% UC = 3% 64% #primary diagnoses < 1 >= 2 NC = 86% SC = 13% UC = 0% 8% NC = 29% SC = 55% UC = 15% 8% E&M Visits NC = Never Compliant SC = Sometimes Compliant UC = Usually Compliant