Insights into patient health with
summary
Shows how to extract structured clinical facts and relationships from notes and images using Amazon Comprehend Medical (entity + relationship extraction, negation, diagnosis traits) and a separate detect PHI API for locating identifiers. Demonstrates synchronous APIs, asynchronous batch jobs that scale via S3/Lambda/Step Functions, and pipelines using Amazon Textract, Transcribe Medical and Rekognition. Describes mapping outputs to ontologies (SNOMED, RxNorm, ICD‑10), simple masking/tokenization workflows, and an open‑source AWS Solution that deploys redaction and storage in customer accounts.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 1:12Challenges in healthcare
- 8:23Architecture diagram
- 9:34Interoperability
- 16:33Batch
- 17:19SFTP
- 20:17AWS Batch
- 25:08Archive
- 26:31Data protection
- 27:49Detect Entities API
- 34:51Detect Entities Code
- 36:11General Idea
- 38:45Closing
related talks
26mEmpower your business use cases
18mUsing AI to automate clinical workflows
45mCreando soluciones inteligentes en el sector salud
26mAccelerating innovation in the healthcare and life sciences industry
42mExtract information accurately from documents using computer vision
35mAutomate your document pipeline with intelligent document processing
21mMake sense of health data with Amazon HealthLake
46mReimagining clinical engagement using Amazon Connect