Watson – Beyond Jeopardy

© 2012 International Business Machines Corporation

Watson – Beyond Jeopardy

University of Dayton – 3 April 2013

Follow us @IBMWatson

John M. Kundtz, Senior Principal Consultant

IBM Global Complex Opportunity Support

@JMKundtz

[email protected]

© 2012 International Business Machines Corporation2

Result of IBM Research “Grand Challenge”

On February 14, 2011, IBM Watson made history


Agenda

What is IBM Watson and why is it important?

How is IBM putting Watson to work?

What can we expect in the future?


Businesses are “dying of thirst in an ocean of data”

1 in 2business leaders don’t have access to data they need

83%of CIOs cited BI and analytics as part of their visionary plan

2.2Xmore likely that top

performers use business analytics

80%of the world’s data

today is unstructured

90% of the world’s data was created in the

last two years

1 Trillionconnected devices

generate 2.5 quintillion bytes

data / day


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


Big Data

Content Analytics

IBM Technology Depth

Business Analytics

Databases / Data Warehouses

2880 Processing Cores

16 Terabytes Memory (RAM) – 20TB Disk

System Specifications

90 IBM P750 Servers

80 Teraflops (80 trillion operations per second)

Workload Optimized Systems

In the past 5 years IBM has spent over $14B in analytical acquisitions and $6B in R&D annually

A look behind the scenes


Brief History of IBM Watson

R&D

Demonstration

Commercialization

Cross-industry Applications

IBMResearch Project (2006 – )

Jeopardy!Grand

Challenge(Feb 2011)

Watson for

Healthcare(Aug 2011 –)

Watson Industry

Solutions(2012 – )

Watson for Financial

Services(Mar 2012 – )

Expansion


Moving beyond Jeopardy! is a non-trivial challenge

Watson at Play Watson at Work

1 User

Max. input was two sentences

5+ days to retrain

Evidence not present

Text-only input

Q&A model

Basic security

10s of thousands concurrent users

Pages of input (e.g. medical record)

Dynamic content ingestion

Supporting evidence integral

Text, tables and images as input

Both Q&A + Conversation model

High security (e.g. HIPAA)


Informed decision making: search vs. Watson

Decision Maker

Search Engine

Finds Documents Containing KeywordsFinds Documents Containing Keywords

Delivers Documents Based on PopularityDelivers Documents Based on Popularity

Has QuestionHas Question

Distills to 2-3 KeywordsDistills to 2-3 Keywords

Reads Documents, Finds Answers

Reads Documents, Finds Answers

Finds & Analyzes EvidenceFinds & Analyzes Evidence WatsonUnderstands QuestionUnderstands Question

Produces Possible Answers & EvidenceProduces Possible Answers & Evidence

Delivers Response, Evidence & ConfidenceDelivers Response, Evidence & Confidence

Analyzes Evidence, Computes ConfidenceAnalyzes Evidence, Computes Confidence

Asks NL QuestionAsks NL Question

Considers Answer & EvidenceConsiders Answer & Evidence

Decision Maker


Where to put Watson to work

Watson Capabilities Best Fit for Watson

Natural language understanding

Hypothesis generation and confidence scoring

Iterative Question/Answering

Broad domain of unstructured data

Machinelearning

Problems that require the analysis of unstructured data

Critical questions that require decision support with prioritized recommendations and evidence

High value in decision support

Leverage scale to maximize machine learning and improve outcomes over time


“Medicine has become too complex. Only about 20% of the knowledge clinicians use today is evidence-based.”

Steven ShapiroChief Medical & Scientific Officer

University Pittsburgh Medical Center

Why Watson for healthcare?


Cancer is an insidious disease

Source: American Cancer Society, National Health Institute

X

1 in 4individuals will die from

cancer

3Xrate cancer cost climbs vs. std. health costs or

15-18% / yr.

20%of cancer cases

receive the wrong diagnosis initially with some as high as 44%

$263.8Boverall costs of cancer

in the US in 2010

$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$✔

✔

✔

IBM+ +

Working Together to Beat Cancer


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


Drug interactions New treatment

options

Diagnose & treat illness

Ask

Discover

Decide

Teach Practice Pay

Med student lookupPatient medication

inquiry

Find and preempt fraud

Patient outcomes are analyzed

Find treatment code anomalies

Pre-authorization

Watson empowers the healthcare worker

In Pilot/Production


Imagine if…

. . . new insights from medical research find their way to patient treatment programs in months instead of years?

That’s exactly what a global leader in cancer care is doing today.

DISCOVER

Medical information is doubling every 5 years

It can take 10 years+ to convert research to practice

$95B/yr. is spent in medical research, yet only 3 of 5 chronic patients benefit

“Watson will be an invaluable resource for our physicians and will dramatically enhance the quality and effectiveness of medical care.”

- Dr Sam Nussbaum, Chief Medical Officer, WellPoint


Imagine if…

… call center agents could find better answers to customer questions 50% faster.

That’s exactly what a major provider of financial management software did.

ASK

“Contact centers of the future will improve precision and personalization, transforming centers from a cost orientation to a strategic assets.”

- Leading Telco Supplier

271B calls come in to call centers annually costing $600B

50% of all incoming calls require escalation or go unresolved

61% of all unresolved calls could have been resolved with better access to information


Imagine if…

DECIDE

$263.8B was the overall cost of treating cancer in the US in 2010

3X is the rate cancer costs climb vs. std. health costs, or 15-18% / yr

20-44% of cancer cases receive the wrong diagnosis initially

. . . the 1.5M people diagnosed with cancer in the US last year had a better prognosis?

That’s exactly what a major health plan provider is working to accomplish.

“Watson can aggregate information and give probabilities that will enable (experts) to zero in on the most likely diagnosis.”

- Dr. Steven Nissen, Cleveland Clinic


Sy

mp

tom

s

UTI

Diabetes

Influenza

Hypokalemia

Renal Failure

no abdominal painno back painno coughno diarrhea

(Thyroid Autoimmune)

Esophagitis

pravastatinAlendronate

levothyroxinehydroxychloroquine

Diagnosis Models

frequent UTI

cutaneous lupus

hyperlipidemiaosteoporosis

hypothyroidism

Sym

ptoms

Fam

. History

Pat. H

istoryM

edicationsF

indings Confidence difficulty swallowing

dizziness

anorexia

fever dry mouththirst

frequent urination

Fa

mil

yH

isto

ry

Graves’ Disease

Oral cancerBladder cancerHemochromatosisPurpura

Pa

tie

nt

His

tory

Med

icat

ion

s

Fin

din

gs

supine 120/80 mm HG

urine dipstick: leukocyte esterase

urine culture: E. Coliheart rate: 88 bpm

SymptomsA 58-year-old woman complains of

dizziness, anorexia, dry mouth, increased thirst, and frequent

urination. She had also had a fever. She reported no pain in her abdomen,

back, and no cough, or diarrhea.

A 58-year-old woman presented to her primary care physician after several days

of dizziness, anorexia, dry mouth, increased thirst, and frequent urination.

She had also had a fever and reported that food would “get stuck” when she was

swallowing. She reported no pain in her abdomen, back, or flank and no cough,

shortness of breath, diarrhea, or dysuria

Family History

Her family history included oral and bladder cancer in her mother, Graves' disease in two sisters,

hemochromatosis in one sister, and idiopathic thrombocytopenic

purpura in one sister

Patient History

Her history was notable for cutaneous lupus, hyperlipidemia, osteoporosis,

frequent urinary tract infections, a left oophorectomy for a benign cyst, and primary hypothyroidism, diagnosed a

year earlier

Her medications were levothyroxine, hydroxychloroquine, pravastatin, and

alendronate.

MedicationsFindingsA urine dipstick was positive for

leukocyte esterase and nitrites. The patient was given a prescription for

ciprofloxacin for a urinary tract infection. 3 days later, patient

reported weakness and dizziness. Her supine blood pressure was

120/80 mm Hg, and pulse was 88.

• Extract Symptoms from record• Use paraphrasings mined from text to handle

alternate phrasings and variants• Perform broad search for possible diagnoses• Score Confidence in each diagnosis based on

evidence so far

• Identify negative Symptoms• Reason with mined relations to explain away

symptoms (thirst is consistent w/ UTI)

• Extract Family History• Use Medical Taxonomies to generalize medical

conditions to the granularity used by the models

• Extract Patient History• Extract Medications• Use database of drug side-effects• Together, multiple diagnoses may best explain

symptoms• Extract Findings: Confirms that UTI was present

Most Confident Diagnosis: DiabetesMost Confident Diagnosis: UTIMost Confident Diagnosis: EsophagitisMost Confident Diagnosis: Influenza

Putting the pieces together at point of impact can be life changing


We have only just begun to build a new era of computing powered by

cognitive systems

Transforming how organizations think, act, and operate

Learning through interactions

Delivering evidence based responses driving better outcomes


JOHN M. KUNDTZ – Data Center Optimization Executive

Mr. Kundtz has over two decades of experience as a Management Consultant and Business Development Executive with a focus on complex Enterprise Solutions within multiple industries including finance, healthcare, manufacturing, education, government, and not-for-profit. Recognized for innovative and creative problem solving with a proven track record of business development and outstanding engagement delivery that meet clients’ objectives.

John is currently a Senior Principal Consultant / Business Development Executive for IBM’s Global Complex Opportunity Support (GCOS), John is responsible for developing and closing large complex solutions across the globe. His, team of experienced Consultants, Architects, and Project Managers assist our clients with complex IT Transformation and Data Center Optimization engagements. We lead the development and creation of the methodologies and techniques required for successful IT Transformation and Data Center Optimization, including delivery transformation activities and the best tools to develop the best solution at the lowest cost.

Before joining GCOS, John lead a team of data center sales specialists working with clients throughout the Eastern United States, John and his team were responsible for helping clients identify requirements, assess current capabilities, and review best options for their data centers. This included consulting and implementation services to provide assessments and strategy input, updating and optimizing data center facilities, and consolidating and relocating I/T equipment and overall IT and data centers infrastructure optimization resulting in a reduction in costs and improved operations.

In 2010, John was honored by Northeast Ohio Inside Business Magazine as one of the region’s most influential technology people.

As a past member of the Faculty of IBM’s Executive Consulting Institute as a Methodology Instructor, during his tenure as an instructor, John worked in Japan, Ireland, and Belgium and as a result is well versed in cultural orientation and cognitive styles required to conduct business in today’s global marketplace.

Mr. Kundtz has spoken and published on a variety of topics relating to Data Center Optimization, Smarter Data Center, Analytics as well as Systems Management and Networking. He is well versed in the business and technical issues impacting today’s organizations as they seek to leverage their IT assets for competitive advantage.

Follow John on Twitter @jmkundtz or connect on LinkedIn http://www.linkedin.com/in/jkundtz

Watson – Beyond Jeopardy

Technology

Transcript of Watson – Beyond Jeopardy