SlideShare a Scribd company logo
1 of 64
Download to read offline
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Comprehend Medical
Arun Ravi
Sr. Product Manager
AWS AI/ML
Taha Kass-Hout, MD, MS
Amazon
Introducing
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Comprehend Medical
A new HIPAA eligible service that uses machine learning to extract medical information with high accuracy,
reducing the cost, time and effort of processing large amounts of unstructured medical text
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Agenda
The customer problem of analyzing unstructured text in healthcare
What is Amazon Comprehend Medical?
How does Amazon Comprehend Medical Work?
Where can I use Amazon Comprehend Medical?
Customer –1 (Fred Hutchinson Cancer Research Center)
Customer – 2 (Roche Diagnostics Information Solutions)
Call to action
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Customer Problems
1.2 B unstructured clinical documents created per year
Critical information “trapped” in these documents
Difficult to extract insights
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Comprehend Medical
Entities
• Medication
• Medical condition
• Test, Treatments and Procedures
• Anatomy
• Protected Health Information (PHI)
Relationship Extraction
• Medication and dosage
• Test and result
• Many more
Entity Traits
• Negation
• Diagnosis, Sign or
Symptom
Protected Health Information Identification
(PHId API)
Distill a complex process into a simple API call
Medical Named Entity and Relationship
Extraction (NERe API)
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Protected Health Information (PHI)
Mr. Smith: Name
63: Age
Comprehend Medical - NERe API
Mr. Smith is a 63-year-old gentleman with coronary
artery disease and hypertension. CURRENT
MEDICATIONS: taking a dose of LIPITOR 20 mg once
daily
aws comprehend-medical detect-entities --region us-
east-1 --text “<Insert Text Here>”
Named Entities
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Comprehend Medical – NERe API
CURRENT MEDICATIONS: taking a dose of LIPITOR 20
mg once daily
aws comprehend-medical detect-entities --region us-
east-1 --text “<Insert Text Here>”
Relationship Extraction
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Comprehend – NERe API
What are Entity Traits?
(1) Negation
(2) Diagnosis, sign or symptom
Rash
Discontinue Abraxane, patient denies taking
Tylenol 325 mg and is not taking calcium
carbonate, patient also stopped taking
cholecalciferol 1,000 units PO
Entity Traits
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Comprehend – PHId API
Mr. Smith is a 63-year-old gentleman with coronary
artery disease and hypertension. He currently lives in
Seattle and works as a teacher. His PCP, Dr. John,
works at the University of Washington
aws comprehend-medical detect-phi --region us-east-1 -
-text “<Insert Text Here>”
In addition to extracting PHI, the PHId
API identifies relevant patient identifiers
described in HIPAA Safe Harbor method
of de-identification
Protected Health Information
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Where is NLP leveraged in Healthcare?
Patient & population
health analytics
Clinical Trial
managementRevenue cycle
management (Medical
Coding)
Pharmacovigilance
PHI Compliance
What else?
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Patient & Population Health Analytics
Challenges Amazon Comprehend
Medical
Outcomes
Unstructured data is difficult to mine
Example: Clinical team in the ICU makes over
120 decisions about care per day, how do you
keep up?
Create ”single-lens” on a single
patient
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Revenue Cycle Management – Medical Coding
Challenges Amazon Comprehend
Medical
Outcomes
Process of coding or classifying patient
records according to the International
Classification of Diseases (ICD) is one of
the most complex transactions
Impact coding efficiency and
reduce burden on clinical staff
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Clinical Trial Management
Challenges Amazon Comprehend
Medical
Outcomes
Identify the right patients for
clinical trials quickly
Allow for quick and accurate
indexing across large
patient populations
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Pharmacovigilance
Challenges Amazon Comprehend
Medical
Outcomes
Multiple avenues of reporting
adverse drug reactions or
adverse events
Decreased burden on staff and
improved throughput
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
PHI Compliance
Challenges Amazon Comprehend
Medical
Outcomes
Difficult to maintain HIPAA
compliance and technical
requirements for PHI
Accurate way to create
inventory of sensitive PHI
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Fred Hutchinson Cancer Research Center
Hutch Data Commonwealth
Matthew Trunnell
Chief Information Officer and Vice President of Information Technology Executive
Director, Hutch Data Commonwealth
Customer Story
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
NAVIFY®:
Using NLP to enhance data quality
and enable Clinical Decision Support
Anish Kejariwal
Director of Engineering, Analytics
Roche Diagnostics Information Solutions (DIS)
Customer Story
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
Roche is positioned to deliver cutting-edge capabilities
Decision support software with 120 years of medical innovation rooted in science
• Leading provider of cancer treatments worldwide
• 137 million patients treated with Roche medicines
• Focused on major medical indications and disease areas
• #1 in biotechnology and in vitro diagnostics
• 19 billion+ diagnostic tests performed
• Advanced scientific knowledge and technology that
increases the medical value of diagnostic solutions
NAVIFY®
Decision Support Portfolio
Workflow + Data + Analytics
Diagnostics Pharmaceuticals
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
NAVIFY® Decision Support portfolio
A fully integrated portfolio of scalable, secure
workflow solutions and apps designed to
support care teams with analytics and
actionable insights.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
Unstructured healthcare data challenges for NAVIFY® Portfolio
• Diverse customers distributed across the world
• Multiple languages
• Different diseases*
• Different report formats (ex: pathology, radiology)
• Different terminologies
Must unlock unstructured data to build a comprehensive,
longitudinal view of the patient, and enable both
clinical decision support and population analytics
*In development
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
Sample TCGA
Pathology Report
• The Cancer Genome Atlas (TCGA) is a joint
effort of the NCI and the NHGRI to accelerate
our understanding of the molecular basis
of cancer
• Hosted on Amazon S3 and NCI’s Cancer
Genomics Cloud
• Pathology reports are very diverse
• Pathology reports often have tables,
key-value pairs, and hand-written notes
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
Manually curated
TCGA report
Manual curation is extremely time consuming,
expensive, and prone to error
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
Sample results from curation
Token (word) Entity Category
Mastectomy Procedure
Left Specimen Laterality
Upper outer quadrant Tumor Site
4.5 x 2.0 x 2.0 cm Size of Invasive Carcinoma
Medullary carcinoma Histologic Type
0 Number of Lymph nodes Involved in Tumor
5 Number of Lymph nodes examined
pT2 Primary Tumor (pT)
pN0(i-) Category (pN)
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
The NAVIFY® team identified two significant needs
NLP: specialized for medical data
• Minimizes time to train NLP models
Standard Criteria:
• Scalable (support 10 million
pathology reports per year)
• Low cost
• Compliant with applicable privacy laws
• Integrates easily with AWS services
• Serverless, when possible
Text and Structured Data Extraction: extract text from
scanned documents into a machine-readable format
• Retains document structure (e.g., tabular data) to provide
context for NLP
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
[] [] [] []
[] [] [] []
[] [] [] []
[] [] [] []
[] [] [] []
NAVIFY® Portfolio Architecture in Consideration
Support NAVIFY®
products and analytics
Raw PDFs Text Extraction
Machine Readable
Text
Structured
Data
Data Flow
Overview* Unstructured Text
Structured
Text
from EMR
NLP
H O S P I T A L S
*In Development
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche.
This presentation is for educational purposes.
The use of NLP will be a journey
• Initial goal of speeding up review of
pathology reports
• Will then automate extraction
of high confidence entities
and relationships
(low hanging fruit)
• Will keep increasing automation of
NLP over time
The release of Amazon Comprehend Medical and Amazon Textract is well timed to begin the journey
of structuring data to improve data quality and better enable clinical decision support
Automated
Manual
T I M E
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Thank you!
Anish Kejariwal
Director of Engineering, Analytics
Roche Diagnostics Information Solutions (DIS)
anish.kejariwal@roche.com
We are hiring! https://www.navify.com/careers/
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Call to Action
Webpage: aws.amazon.com/comprehend/medical
Blog: https://aws.amazon.com/blogs/aws/amazon-comprehend-medical-
continuously-trained-natural-language-processing-for-healthcare-customers
Email: ravarun@amazon.com
Thank you!
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.

More Related Content

What's hot

Capital One Delivers Risk Insights in Real Time with Stream Processing
Capital One Delivers Risk Insights in Real Time with Stream ProcessingCapital One Delivers Risk Insights in Real Time with Stream Processing
Capital One Delivers Risk Insights in Real Time with Stream Processingconfluent
 
Kafka for Real-Time Replication between Edge and Hybrid Cloud
Kafka for Real-Time Replication between Edge and Hybrid CloudKafka for Real-Time Replication between Edge and Hybrid Cloud
Kafka for Real-Time Replication between Edge and Hybrid CloudKai Wähner
 
How to Enhance your Application using Amazon Comprehend for NLP - AWS Online ...
How to Enhance your Application using Amazon Comprehend for NLP - AWS Online ...How to Enhance your Application using Amazon Comprehend for NLP - AWS Online ...
How to Enhance your Application using Amazon Comprehend for NLP - AWS Online ...Amazon Web Services
 
Top 5 Event Streaming Use Cases for 2021 with Apache Kafka
Top 5 Event Streaming Use Cases for 2021 with Apache KafkaTop 5 Event Streaming Use Cases for 2021 with Apache Kafka
Top 5 Event Streaming Use Cases for 2021 with Apache KafkaKai Wähner
 
Automated and Explainable Deep Learning for Clinical Language Understanding a...
Automated and Explainable Deep Learning for Clinical Language Understanding a...Automated and Explainable Deep Learning for Clinical Language Understanding a...
Automated and Explainable Deep Learning for Clinical Language Understanding a...Databricks
 
Insurance digital transformation - key challenges
Insurance   digital transformation - key challengesInsurance   digital transformation - key challenges
Insurance digital transformation - key challengesArif Mohammed
 
Amazon QuickSight First Call Deck
Amazon QuickSight First Call DeckAmazon QuickSight First Call Deck
Amazon QuickSight First Call DeckAmazon Web Services
 
Scaling a Core Banking Engine Using Apache Kafka | Peter Dudbridge, Thought M...
Scaling a Core Banking Engine Using Apache Kafka | Peter Dudbridge, Thought M...Scaling a Core Banking Engine Using Apache Kafka | Peter Dudbridge, Thought M...
Scaling a Core Banking Engine Using Apache Kafka | Peter Dudbridge, Thought M...HostedbyConfluent
 
Apache Kafka® Use Cases for Financial Services
Apache Kafka® Use Cases for Financial ServicesApache Kafka® Use Cases for Financial Services
Apache Kafka® Use Cases for Financial Servicesconfluent
 
Moving to the cloud: cloud strategies and roadmaps
Moving to the cloud: cloud strategies and roadmapsMoving to the cloud: cloud strategies and roadmaps
Moving to the cloud: cloud strategies and roadmapsJisc
 
Modern Data Platforms
Modern Data Platforms Modern Data Platforms
Modern Data Platforms Arne Roßmann
 
Using Knowledge Graphs to Predict Customer Needs and Improve Quality
Using Knowledge Graphs to Predict Customer Needs and Improve QualityUsing Knowledge Graphs to Predict Customer Needs and Improve Quality
Using Knowledge Graphs to Predict Customer Needs and Improve QualityNeo4j
 
The Zen of DataOps – AWS Lake Formation and the Data Supply Chain Pipeline
The Zen of DataOps – AWS Lake Formation and the Data Supply Chain PipelineThe Zen of DataOps – AWS Lake Formation and the Data Supply Chain Pipeline
The Zen of DataOps – AWS Lake Formation and the Data Supply Chain PipelineAmazon Web Services
 
Transforming Financial Services with Event Streaming Data
Transforming Financial Services with Event Streaming DataTransforming Financial Services with Event Streaming Data
Transforming Financial Services with Event Streaming Dataconfluent
 

What's hot (20)

Capital One Delivers Risk Insights in Real Time with Stream Processing
Capital One Delivers Risk Insights in Real Time with Stream ProcessingCapital One Delivers Risk Insights in Real Time with Stream Processing
Capital One Delivers Risk Insights in Real Time with Stream Processing
 
Kafka for Real-Time Replication between Edge and Hybrid Cloud
Kafka for Real-Time Replication between Edge and Hybrid CloudKafka for Real-Time Replication between Edge and Hybrid Cloud
Kafka for Real-Time Replication between Edge and Hybrid Cloud
 
How to Enhance your Application using Amazon Comprehend for NLP - AWS Online ...
How to Enhance your Application using Amazon Comprehend for NLP - AWS Online ...How to Enhance your Application using Amazon Comprehend for NLP - AWS Online ...
How to Enhance your Application using Amazon Comprehend for NLP - AWS Online ...
 
Top 5 Event Streaming Use Cases for 2021 with Apache Kafka
Top 5 Event Streaming Use Cases for 2021 with Apache KafkaTop 5 Event Streaming Use Cases for 2021 with Apache Kafka
Top 5 Event Streaming Use Cases for 2021 with Apache Kafka
 
AWS view of Financial Services Industry
AWS view of Financial Services IndustryAWS view of Financial Services Industry
AWS view of Financial Services Industry
 
Automated and Explainable Deep Learning for Clinical Language Understanding a...
Automated and Explainable Deep Learning for Clinical Language Understanding a...Automated and Explainable Deep Learning for Clinical Language Understanding a...
Automated and Explainable Deep Learning for Clinical Language Understanding a...
 
Insurance digital transformation - key challenges
Insurance   digital transformation - key challengesInsurance   digital transformation - key challenges
Insurance digital transformation - key challenges
 
App Modernization
App ModernizationApp Modernization
App Modernization
 
Oracle Cloud Infrastructure
Oracle Cloud InfrastructureOracle Cloud Infrastructure
Oracle Cloud Infrastructure
 
Amazon QuickSight First Call Deck
Amazon QuickSight First Call DeckAmazon QuickSight First Call Deck
Amazon QuickSight First Call Deck
 
Scaling a Core Banking Engine Using Apache Kafka | Peter Dudbridge, Thought M...
Scaling a Core Banking Engine Using Apache Kafka | Peter Dudbridge, Thought M...Scaling a Core Banking Engine Using Apache Kafka | Peter Dudbridge, Thought M...
Scaling a Core Banking Engine Using Apache Kafka | Peter Dudbridge, Thought M...
 
Apache Kafka® Use Cases for Financial Services
Apache Kafka® Use Cases for Financial ServicesApache Kafka® Use Cases for Financial Services
Apache Kafka® Use Cases for Financial Services
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Migrating Oracle to PostgreSQL
Migrating Oracle to PostgreSQLMigrating Oracle to PostgreSQL
Migrating Oracle to PostgreSQL
 
Moving to the cloud: cloud strategies and roadmaps
Moving to the cloud: cloud strategies and roadmapsMoving to the cloud: cloud strategies and roadmaps
Moving to the cloud: cloud strategies and roadmaps
 
Modern Data Platforms
Modern Data Platforms Modern Data Platforms
Modern Data Platforms
 
Using Knowledge Graphs to Predict Customer Needs and Improve Quality
Using Knowledge Graphs to Predict Customer Needs and Improve QualityUsing Knowledge Graphs to Predict Customer Needs and Improve Quality
Using Knowledge Graphs to Predict Customer Needs and Improve Quality
 
Cloud Migration: A How-To Guide
Cloud Migration: A How-To GuideCloud Migration: A How-To Guide
Cloud Migration: A How-To Guide
 
The Zen of DataOps – AWS Lake Formation and the Data Supply Chain Pipeline
The Zen of DataOps – AWS Lake Formation and the Data Supply Chain PipelineThe Zen of DataOps – AWS Lake Formation and the Data Supply Chain Pipeline
The Zen of DataOps – AWS Lake Formation and the Data Supply Chain Pipeline
 
Transforming Financial Services with Event Streaming Data
Transforming Financial Services with Event Streaming DataTransforming Financial Services with Event Streaming Data
Transforming Financial Services with Event Streaming Data
 

Similar to Amazon Comprehend Medical: Extracting Medical Insights from Unstructured Text

Leadership Session: Innovation-Driven Healthcare (HLC201-iL) - AWS re:Invent ...
Leadership Session: Innovation-Driven Healthcare (HLC201-iL) - AWS re:Invent ...Leadership Session: Innovation-Driven Healthcare (HLC201-iL) - AWS re:Invent ...
Leadership Session: Innovation-Driven Healthcare (HLC201-iL) - AWS re:Invent ...Amazon Web Services
 
Leadership Session: Accelerating Transformation in the Life Sciences (LFS201-...
Leadership Session: Accelerating Transformation in the Life Sciences (LFS201-...Leadership Session: Accelerating Transformation in the Life Sciences (LFS201-...
Leadership Session: Accelerating Transformation in the Life Sciences (LFS201-...Amazon Web Services
 
AI/ML in Life Sciences: Predictive Modeling with Amazon SageMaker (LFS303) - ...
AI/ML in Life Sciences: Predictive Modeling with Amazon SageMaker (LFS303) - ...AI/ML in Life Sciences: Predictive Modeling with Amazon SageMaker (LFS303) - ...
AI/ML in Life Sciences: Predictive Modeling with Amazon SageMaker (LFS303) - ...Amazon Web Services
 
Building AI Services to Sell to Enterprises: AWS Startup Day - New York 2018
Building AI Services to Sell to Enterprises: AWS Startup Day - New York 2018Building AI Services to Sell to Enterprises: AWS Startup Day - New York 2018
Building AI Services to Sell to Enterprises: AWS Startup Day - New York 2018Amazon Web Services
 
Global AI seattle How AI will Reinvent Healthcare
Global AI seattle   How AI will Reinvent HealthcareGlobal AI seattle   How AI will Reinvent Healthcare
Global AI seattle How AI will Reinvent HealthcareAlex Ermolaev
 
Building and deploying AI/ML models on AWS for Biosciences professionals
Building and deploying AI/ML models on AWS for Biosciences professionalsBuilding and deploying AI/ML models on AWS for Biosciences professionals
Building and deploying AI/ML models on AWS for Biosciences professionalsjavier ramirez
 
IOT206_A Cloud-Based IoT Platform Purposefully Built For Healthcare
IOT206_A Cloud-Based IoT Platform Purposefully Built For HealthcareIOT206_A Cloud-Based IoT Platform Purposefully Built For Healthcare
IOT206_A Cloud-Based IoT Platform Purposefully Built For HealthcareAmazon Web Services
 
Enabling patient-centricity-pfizer
Enabling patient-centricity-pfizerEnabling patient-centricity-pfizer
Enabling patient-centricity-pfizerDavid Teszler
 
Enabling Patient Centricity for Pfizer through AWS Cloud (LFS301-S-i) - AWS r...
Enabling Patient Centricity for Pfizer through AWS Cloud (LFS301-S-i) - AWS r...Enabling Patient Centricity for Pfizer through AWS Cloud (LFS301-S-i) - AWS r...
Enabling Patient Centricity for Pfizer through AWS Cloud (LFS301-S-i) - AWS r...Amazon Web Services
 
Re-Work DL Summit - Can AI Understand Doctor's Notes
Re-Work DL Summit - Can AI Understand Doctor's NotesRe-Work DL Summit - Can AI Understand Doctor's Notes
Re-Work DL Summit - Can AI Understand Doctor's NotesAlex Ermolaev
 
Cloud computing in healthcare & life sciences
Cloud computing  in healthcare & life sciencesCloud computing  in healthcare & life sciences
Cloud computing in healthcare & life sciencesSusant Mallick
 
Drug Discovery Innovation in a Precompetitive Cloud Platform (LFS302-S) - AWS...
Drug Discovery Innovation in a Precompetitive Cloud Platform (LFS302-S) - AWS...Drug Discovery Innovation in a Precompetitive Cloud Platform (LFS302-S) - AWS...
Drug Discovery Innovation in a Precompetitive Cloud Platform (LFS302-S) - AWS...Amazon Web Services
 
Keynote: What Transformation Really Means for the Enterprise - Virtual Transf...
Keynote: What Transformation Really Means for the Enterprise - Virtual Transf...Keynote: What Transformation Really Means for the Enterprise - Virtual Transf...
Keynote: What Transformation Really Means for the Enterprise - Virtual Transf...Amazon Web Services
 
Pivot to the Patient
Pivot to the PatientPivot to the Patient
Pivot to the Patientaccenture
 
AWS Transformation Day 2018 - Charlotte NC
AWS Transformation Day 2018 - Charlotte NCAWS Transformation Day 2018 - Charlotte NC
AWS Transformation Day 2018 - Charlotte NCAmazon Web Services
 
5 Powerful Real World Examples Of How AI Is Being Used In Healthcare
5 Powerful Real World Examples Of How AI Is Being Used In Healthcare5 Powerful Real World Examples Of How AI Is Being Used In Healthcare
5 Powerful Real World Examples Of How AI Is Being Used In HealthcareBernard Marr
 
Amazon, awsreinvent2018, Artificial Intelligence & Machine Learning, AIM422, ...
Amazon, awsreinvent2018, Artificial Intelligence & Machine Learning, AIM422, ...Amazon, awsreinvent2018, Artificial Intelligence & Machine Learning, AIM422, ...
Amazon, awsreinvent2018, Artificial Intelligence & Machine Learning, AIM422, ...Amazon Web Services
 

Similar to Amazon Comprehend Medical: Extracting Medical Insights from Unstructured Text (20)

Leadership Session: Innovation-Driven Healthcare (HLC201-iL) - AWS re:Invent ...
Leadership Session: Innovation-Driven Healthcare (HLC201-iL) - AWS re:Invent ...Leadership Session: Innovation-Driven Healthcare (HLC201-iL) - AWS re:Invent ...
Leadership Session: Innovation-Driven Healthcare (HLC201-iL) - AWS re:Invent ...
 
Leadership Session: Accelerating Transformation in the Life Sciences (LFS201-...
Leadership Session: Accelerating Transformation in the Life Sciences (LFS201-...Leadership Session: Accelerating Transformation in the Life Sciences (LFS201-...
Leadership Session: Accelerating Transformation in the Life Sciences (LFS201-...
 
AI/ML in Life Sciences: Predictive Modeling with Amazon SageMaker (LFS303) - ...
AI/ML in Life Sciences: Predictive Modeling with Amazon SageMaker (LFS303) - ...AI/ML in Life Sciences: Predictive Modeling with Amazon SageMaker (LFS303) - ...
AI/ML in Life Sciences: Predictive Modeling with Amazon SageMaker (LFS303) - ...
 
Building AI Services to Sell to Enterprises: AWS Startup Day - New York 2018
Building AI Services to Sell to Enterprises: AWS Startup Day - New York 2018Building AI Services to Sell to Enterprises: AWS Startup Day - New York 2018
Building AI Services to Sell to Enterprises: AWS Startup Day - New York 2018
 
Global AI seattle How AI will Reinvent Healthcare
Global AI seattle   How AI will Reinvent HealthcareGlobal AI seattle   How AI will Reinvent Healthcare
Global AI seattle How AI will Reinvent Healthcare
 
Building and deploying AI/ML models on AWS for Biosciences professionals
Building and deploying AI/ML models on AWS for Biosciences professionalsBuilding and deploying AI/ML models on AWS for Biosciences professionals
Building and deploying AI/ML models on AWS for Biosciences professionals
 
Precision Medicine on the Cloud
Precision Medicine on the CloudPrecision Medicine on the Cloud
Precision Medicine on the Cloud
 
IOT206_A Cloud-Based IoT Platform Purposefully Built For Healthcare
IOT206_A Cloud-Based IoT Platform Purposefully Built For HealthcareIOT206_A Cloud-Based IoT Platform Purposefully Built For Healthcare
IOT206_A Cloud-Based IoT Platform Purposefully Built For Healthcare
 
Enabling patient-centricity-pfizer
Enabling patient-centricity-pfizerEnabling patient-centricity-pfizer
Enabling patient-centricity-pfizer
 
Enabling Patient Centricity for Pfizer through AWS Cloud (LFS301-S-i) - AWS r...
Enabling Patient Centricity for Pfizer through AWS Cloud (LFS301-S-i) - AWS r...Enabling Patient Centricity for Pfizer through AWS Cloud (LFS301-S-i) - AWS r...
Enabling Patient Centricity for Pfizer through AWS Cloud (LFS301-S-i) - AWS r...
 
Re-Work DL Summit - Can AI Understand Doctor's Notes
Re-Work DL Summit - Can AI Understand Doctor's NotesRe-Work DL Summit - Can AI Understand Doctor's Notes
Re-Work DL Summit - Can AI Understand Doctor's Notes
 
Cloud computing in healthcare & life sciences
Cloud computing  in healthcare & life sciencesCloud computing  in healthcare & life sciences
Cloud computing in healthcare & life sciences
 
Drug Discovery Innovation in a Precompetitive Cloud Platform (LFS302-S) - AWS...
Drug Discovery Innovation in a Precompetitive Cloud Platform (LFS302-S) - AWS...Drug Discovery Innovation in a Precompetitive Cloud Platform (LFS302-S) - AWS...
Drug Discovery Innovation in a Precompetitive Cloud Platform (LFS302-S) - AWS...
 
Keynote: What Transformation Really Means for the Enterprise - Virtual Transf...
Keynote: What Transformation Really Means for the Enterprise - Virtual Transf...Keynote: What Transformation Really Means for the Enterprise - Virtual Transf...
Keynote: What Transformation Really Means for the Enterprise - Virtual Transf...
 
Pivot to the Patient
Pivot to the PatientPivot to the Patient
Pivot to the Patient
 
AWS Transformation Day 2018 - Charlotte NC
AWS Transformation Day 2018 - Charlotte NCAWS Transformation Day 2018 - Charlotte NC
AWS Transformation Day 2018 - Charlotte NC
 
Industrial Transformation
Industrial TransformationIndustrial Transformation
Industrial Transformation
 
India Home Healthcare Report 2016
India Home Healthcare Report 2016India Home Healthcare Report 2016
India Home Healthcare Report 2016
 
5 Powerful Real World Examples Of How AI Is Being Used In Healthcare
5 Powerful Real World Examples Of How AI Is Being Used In Healthcare5 Powerful Real World Examples Of How AI Is Being Used In Healthcare
5 Powerful Real World Examples Of How AI Is Being Used In Healthcare
 
Amazon, awsreinvent2018, Artificial Intelligence & Machine Learning, AIM422, ...
Amazon, awsreinvent2018, Artificial Intelligence & Machine Learning, AIM422, ...Amazon, awsreinvent2018, Artificial Intelligence & Machine Learning, AIM422, ...
Amazon, awsreinvent2018, Artificial Intelligence & Machine Learning, AIM422, ...
 

More from Amazon Web Services

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Amazon Web Services
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Amazon Web Services
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateAmazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSAmazon Web Services
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Amazon Web Services
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Amazon Web Services
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...Amazon Web Services
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsAmazon Web Services
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareAmazon Web Services
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSAmazon Web Services
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAmazon Web Services
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareAmazon Web Services
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWSAmazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckAmazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without serversAmazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...Amazon Web Services
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceAmazon Web Services
 
Come costruire un'architettura Serverless nel Cloud AWS
Come costruire un'architettura Serverless nel Cloud AWSCome costruire un'architettura Serverless nel Cloud AWS
Come costruire un'architettura Serverless nel Cloud AWSAmazon Web Services
 

More from Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 
Come costruire un'architettura Serverless nel Cloud AWS
Come costruire un'architettura Serverless nel Cloud AWSCome costruire un'architettura Serverless nel Cloud AWS
Come costruire un'architettura Serverless nel Cloud AWS
 

Amazon Comprehend Medical: Extracting Medical Insights from Unstructured Text

  • 1.
  • 2. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Comprehend Medical Arun Ravi Sr. Product Manager AWS AI/ML Taha Kass-Hout, MD, MS Amazon Introducing
  • 3. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 4. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Comprehend Medical A new HIPAA eligible service that uses machine learning to extract medical information with high accuracy, reducing the cost, time and effort of processing large amounts of unstructured medical text
  • 5. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Agenda The customer problem of analyzing unstructured text in healthcare What is Amazon Comprehend Medical? How does Amazon Comprehend Medical Work? Where can I use Amazon Comprehend Medical? Customer –1 (Fred Hutchinson Cancer Research Center) Customer – 2 (Roche Diagnostics Information Solutions) Call to action
  • 6. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Customer Problems 1.2 B unstructured clinical documents created per year Critical information “trapped” in these documents Difficult to extract insights
  • 7. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Comprehend Medical Entities • Medication • Medical condition • Test, Treatments and Procedures • Anatomy • Protected Health Information (PHI) Relationship Extraction • Medication and dosage • Test and result • Many more Entity Traits • Negation • Diagnosis, Sign or Symptom Protected Health Information Identification (PHId API) Distill a complex process into a simple API call Medical Named Entity and Relationship Extraction (NERe API)
  • 8. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Protected Health Information (PHI) Mr. Smith: Name 63: Age Comprehend Medical - NERe API Mr. Smith is a 63-year-old gentleman with coronary artery disease and hypertension. CURRENT MEDICATIONS: taking a dose of LIPITOR 20 mg once daily aws comprehend-medical detect-entities --region us- east-1 --text “<Insert Text Here>” Named Entities
  • 9. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Comprehend Medical – NERe API CURRENT MEDICATIONS: taking a dose of LIPITOR 20 mg once daily aws comprehend-medical detect-entities --region us- east-1 --text “<Insert Text Here>” Relationship Extraction
  • 10. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Comprehend – NERe API What are Entity Traits? (1) Negation (2) Diagnosis, sign or symptom Rash Discontinue Abraxane, patient denies taking Tylenol 325 mg and is not taking calcium carbonate, patient also stopped taking cholecalciferol 1,000 units PO Entity Traits
  • 11. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Comprehend – PHId API Mr. Smith is a 63-year-old gentleman with coronary artery disease and hypertension. He currently lives in Seattle and works as a teacher. His PCP, Dr. John, works at the University of Washington aws comprehend-medical detect-phi --region us-east-1 - -text “<Insert Text Here>” In addition to extracting PHI, the PHId API identifies relevant patient identifiers described in HIPAA Safe Harbor method of de-identification Protected Health Information
  • 12. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 13. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Where is NLP leveraged in Healthcare? Patient & population health analytics Clinical Trial managementRevenue cycle management (Medical Coding) Pharmacovigilance PHI Compliance What else?
  • 14. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Patient & Population Health Analytics Challenges Amazon Comprehend Medical Outcomes Unstructured data is difficult to mine Example: Clinical team in the ICU makes over 120 decisions about care per day, how do you keep up? Create ”single-lens” on a single patient
  • 15. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Revenue Cycle Management – Medical Coding Challenges Amazon Comprehend Medical Outcomes Process of coding or classifying patient records according to the International Classification of Diseases (ICD) is one of the most complex transactions Impact coding efficiency and reduce burden on clinical staff
  • 16. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Clinical Trial Management Challenges Amazon Comprehend Medical Outcomes Identify the right patients for clinical trials quickly Allow for quick and accurate indexing across large patient populations
  • 17. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Pharmacovigilance Challenges Amazon Comprehend Medical Outcomes Multiple avenues of reporting adverse drug reactions or adverse events Decreased burden on staff and improved throughput
  • 18. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. PHI Compliance Challenges Amazon Comprehend Medical Outcomes Difficult to maintain HIPAA compliance and technical requirements for PHI Accurate way to create inventory of sensitive PHI
  • 19. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Fred Hutchinson Cancer Research Center Hutch Data Commonwealth Matthew Trunnell Chief Information Officer and Vice President of Information Technology Executive Director, Hutch Data Commonwealth Customer Story
  • 20. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 21. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 22. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 23. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 24. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 26. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 27. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 28. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 29. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 30. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 31. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 32. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 33. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 34. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 35. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 36. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 37. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 38. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 39. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 40. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 41. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 42. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 43. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 44. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 45. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 46. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 47. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 48. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 49. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 50. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 51. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. NAVIFY®: Using NLP to enhance data quality and enable Clinical Decision Support Anish Kejariwal Director of Engineering, Analytics Roche Diagnostics Information Solutions (DIS) Customer Story
  • 52. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. Roche is positioned to deliver cutting-edge capabilities Decision support software with 120 years of medical innovation rooted in science • Leading provider of cancer treatments worldwide • 137 million patients treated with Roche medicines • Focused on major medical indications and disease areas • #1 in biotechnology and in vitro diagnostics • 19 billion+ diagnostic tests performed • Advanced scientific knowledge and technology that increases the medical value of diagnostic solutions NAVIFY® Decision Support Portfolio Workflow + Data + Analytics Diagnostics Pharmaceuticals
  • 53. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. NAVIFY® Decision Support portfolio A fully integrated portfolio of scalable, secure workflow solutions and apps designed to support care teams with analytics and actionable insights.
  • 54. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. Unstructured healthcare data challenges for NAVIFY® Portfolio • Diverse customers distributed across the world • Multiple languages • Different diseases* • Different report formats (ex: pathology, radiology) • Different terminologies Must unlock unstructured data to build a comprehensive, longitudinal view of the patient, and enable both clinical decision support and population analytics *In development
  • 55. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. Sample TCGA Pathology Report • The Cancer Genome Atlas (TCGA) is a joint effort of the NCI and the NHGRI to accelerate our understanding of the molecular basis of cancer • Hosted on Amazon S3 and NCI’s Cancer Genomics Cloud • Pathology reports are very diverse • Pathology reports often have tables, key-value pairs, and hand-written notes
  • 56. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. Manually curated TCGA report Manual curation is extremely time consuming, expensive, and prone to error
  • 57. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. Sample results from curation Token (word) Entity Category Mastectomy Procedure Left Specimen Laterality Upper outer quadrant Tumor Site 4.5 x 2.0 x 2.0 cm Size of Invasive Carcinoma Medullary carcinoma Histologic Type 0 Number of Lymph nodes Involved in Tumor 5 Number of Lymph nodes examined pT2 Primary Tumor (pT) pN0(i-) Category (pN)
  • 58. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. The NAVIFY® team identified two significant needs NLP: specialized for medical data • Minimizes time to train NLP models Standard Criteria: • Scalable (support 10 million pathology reports per year) • Low cost • Compliant with applicable privacy laws • Integrates easily with AWS services • Serverless, when possible Text and Structured Data Extraction: extract text from scanned documents into a machine-readable format • Retains document structure (e.g., tabular data) to provide context for NLP
  • 59. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. [] [] [] [] [] [] [] [] [] [] [] [] [] [] [] [] [] [] [] [] NAVIFY® Portfolio Architecture in Consideration Support NAVIFY® products and analytics Raw PDFs Text Extraction Machine Readable Text Structured Data Data Flow Overview* Unstructured Text Structured Text from EMR NLP H O S P I T A L S *In Development
  • 60. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2018 F. Hoffmann-La Roche, Ltd. NAVIFY is a trademark of Roche. This presentation is for educational purposes. The use of NLP will be a journey • Initial goal of speeding up review of pathology reports • Will then automate extraction of high confidence entities and relationships (low hanging fruit) • Will keep increasing automation of NLP over time The release of Amazon Comprehend Medical and Amazon Textract is well timed to begin the journey of structuring data to improve data quality and better enable clinical decision support Automated Manual T I M E
  • 61. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Thank you! Anish Kejariwal Director of Engineering, Analytics Roche Diagnostics Information Solutions (DIS) anish.kejariwal@roche.com We are hiring! https://www.navify.com/careers/
  • 62. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Call to Action Webpage: aws.amazon.com/comprehend/medical Blog: https://aws.amazon.com/blogs/aws/amazon-comprehend-medical- continuously-trained-natural-language-processing-for-healthcare-customers Email: ravarun@amazon.com
  • 63. Thank you! © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 64. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.