IBM Watson in Healthcare

Presentation given by chief medical scientist, Dr. Med. Martin Kohn, IBM , Copenhagen May 3, 2013

1. © 2012 International Business Machines Corporation
Putting IBM Watson to
Work In Healthcare
Martin S. Kohn, MD, MS, FACEP, FACPE
Chief Medical Scientist, Care Delivery Systems
IBM Research
[email protected]

2. © 2010 IBM Corporation
IBM Research
Watson Jeopardy!

3. © 2010 IBM Corporation
IBM Research






Health Plans / Payers
Private – BCBS plans, large
national plans, mid-sized regional
plans
Government / National Plans,
Medicare Medicaid
Pharmacies
Pharmacy Benefit Management
Retail Clinics
Drug Developers
Large Pharma, Integrated
Biotech, Research Biotech
Medical Devices
Imaging
Archiving & Retention
Solution Providers
IT Infrastructure and Service
Providers, Application Providers
Patient Education
Healthy Lifestyles
Transaction Services
Claims Processing
Banks / Health Savings
Healthcare Providers
Integrated Delivery Networks,
Large University Medical Centers,
Independent Community Hospitals,
Physician Private Practices
Public Health
Pandemic readiness
Vaccine inventory & distribution
Sanitation & public safety
We approach HCLS as an ecosystem of constituents centered
around the needs of patients and consumers
Patients /
Consumers
Health Clubs
Health & Wellness Programs
Government Agencies
Regulatory & Research
Agencies, FDA, WHO, DHHSS,
CDC, NIH, Health Ministries

4. © 2012 International Business Machines Corporation 5
90% of the
world’s data was
created in the
last two years
80% of data in the
world is
unstructured
making decisions
more complex
200% data growth,
in the next two years
fed by 1T connected
devices
1 in 5
diagnoses are
estimated to be
inaccurate or
incomplete
Volume
Variety
Velocity
Veracity
75
new clinical trials start
every day in the US
alone
2X
medical information
is doubling every 4
years
$750B
or 30 cents of every
dollar spent on
healthcare in the US
is wasted
Healthcare is “dying of thirst in an ocean of data”

5. © 2012 International Business Machines Corporation 6
Personalized Medicine
Evidence-based Medicine
Why Watson for healthcare?
! Shift from Fee-for-
Service to ACOs
! Focus on Wellness
and Prevention
! Universal coverage
! Costs are 18% of
US GDP
! 34% of $2.3T US
spend is waste
! Costs can vary
up to 10x
! Diagnosis and
treatment errors
! Shortage of MDs
! Demand for remote
medicine
! Medical data
doubles every 5 years
! Detailed patient
biomedical markers
! Targeted therapies
Complexity
Policy Changes
Costs
Info Overload

6. © 2012 International Business Machines Corporation 8
Person Organization
L. Gerstner IBM
J. Welch GE
W. Gates Microsoft
“If leadership is an art
then surely Jack Welch
has proved himself a
master painter during his
tenure at GE.
Welch ran
this?
! Noses that run and feet that smell?
! How can a house burn up as it burns down?
! Does CPD represent a complex comorbidity of lung cancer?
! What mix of zero-coupon, non-callable, A+ munis fit my risk tolerance?
Why is it so hard for computers to understand us?

7. © 2012 International Business Machines Corporation 9
Understands
natural language
and human
communication
Adapts and learns
from user
selections and
responses
Generates and
evaluates
evidence-based
hypothesis
…built on a massively parallel
architecture optimized for IBM POWER7
IBM Watson combines transformational technologies
1
2
3

8. © 2012 International Business Machines Corporation 10
Watson enables three classes of cognitive services
Decide

• Ingest and analyze domain sources, info models
• Generate evidence based decisions with confidence
• Learn with new outcomes and actions
• e.g. - Next generation Apps " Probabilistic Apps
Ask

• Leverage vast amounts of data
• Ask questions for greater insights
• Natural language inquiries
• e.g. - Next generation Chat


Discover
• Find the rationale for given answers
• Prompt for inputs to yield improved responses
• Inspire considerations of new ideas
• e.g. - Next generation Search " Discovery

9. © 2012 International Business Machines Corporation 11
Baseline 12/06
v0.1 12/07
v0.3 08/08
v0.5 05/09
v0.6 10/09
v0.8 11/10
v0.4 12/08
Watson made incremental progress in precision and confidence
v0.2 05/08
V0.7 04/10
Precision
IBM Watson
Playing in the Winners Cloud

10. © 2012 International Business Machines Corporation 12
Informed decision making: search vs. Watson
Decision Maker
Search Engine
Finds Documents Containing Keywords
Delivers Documents Based on Popularity
Has Question
Distills to 2-3 Keywords
Reads Documents, Finds
Answers
Finds & Analyzes Evidence Watson
Understands Question
Produces Possible Answers & Evidence
Delivers Response, Evidence & Confidence
Analyzes Evidence, Computes Confidence
Asks NL Question
Considers Answer & Evidence
Decision Maker

11. © 2012 International Business Machines Corporation 13
Medical journal concept annotations
Medications
Symptoms Diseases
Modifiers

12. © 2012 International Business Machines Corporation 14
Inquiry
Decomposition
Answer
Scoring
Models
Responses with
Confidence
Inquiry
Evidence
Sources
Models
Models
Models
Models
Models
Primary
Search
Candidate
Answer
Generation
Hypothesis
Generation
Hypothesis and Evidence
Scoring
Final Confidence
Merging & Ranking
Synthesis
Answer
Sources
Inquiry/Topic
Analysis
Evidence
Retrieval
Deep
Evidence
Scoring
Learned Models
help combine and
weigh the Evidence
Hypothesis
Generation
Hypothesis and Evidence
Scoring
How Watson works: DeepQA Architecture
1000s of
Pieces of Evidence
Multiple
Interpretations
of a question
100,000s Scores from
many Deep Analysis
Algorithms
100s
sources
100s Possible
Answers
Balance
& Combine

13. © 2012 International Business Machines Corporation 15
Patient’s Story
Data Acquisition
Accurate Problem
Representation
Generation of Hypothesis
Search for & Selection of
Illness Script
Diagnosis
Key Elements of the Clinical Diagnostic Reasoning Process
Dr. Martin S. Kohn | Clinical Decision Support: DeepQA
Knowledge
Context
Experience
Bowen J. N Engl J Med 2006;355:2217-2225

14. © 2013 IBM Corporation
Solution
Use Case: Oncology Diagnosis &
Treatment (ODT)
• Clinical support for patient assessment based on
objective evidence – patient data, medical info,
research, studies, articles, best practices,
guidelines, etc.
• Evidence panel identifying key information used
to support diagnosis, recommendations (e.g.
suggested tests) and treatment options
• Systematic applied learning based on action
taken and outcome derived
• Initial focus on lung, breast, prostate and
colorectal cancers
Goal
• Create individualized cancer
diagnostic and treatment plans
• Enhance clinical confidence with
greater access and
understanding of information
• Speed time to evidence-based
treatment
• Reduce diagnostic and
administrative errors
• Accelerate the dissemination of
practice-changing research
Assisting physicians with the diagnosis
and treatment of cancer
IBM Confidential: References to potential future products are subject to the Important Disclaimer provided later in the presentation
IBM Watson goes to work in healthcare

15. © 2012 International Business Machines Corporation 17
Watson’s Reasoning
• “Shallower” reasoning over large volumes of data
• Delivers weighted responses to clinicians to assist in making
a informed evidence based decison
‒ Considers large amounts of data (e.g. EMR, Literature)
‒ Unbiased
‒ Learns
• Hits sweet spot of human judgment (e.g. problems with bias,
Big Data)
• Identifies missing information
• Watson’s interactive process helps clinician vector in on the
appropriate decisions
• Not limited by database structure
17 Dr. Martin S. Kohn | Clinical Decision Support: DeepQA 14 Feb. 2012

16. © 2012 International Business Machines Corporation 18