AWS HealthLake features
Overview
Page topics
Import
Open allQuickly & easily ingest health data
Store
Open allStore health data in a secure, compliant, & auditable manner
Transact
Open allLeverage transactional FHIR server
Currently in preview, leverage FHIR APIs for standard resource validation, SMART on FHIR authorization, and Bulk data FHIR API export capabilities to support unifying and analyzing your data to reduce operational costs and improve decision making. AWS HealthLake supports customer conformity to the latest ONC and CMS regulatory standards including: HL7 FHIR API R4 v4.0.1, FHIR Bulk Data Access v2.0.0, US Core IG STU v3.1.1, HL7 SMART App Launch Framework IG v1.0.0, and integrate with OAuth 2.0 & OpenID Connect.
With AWS HealthLake’s fully managed support for SMART on FHIR and integration with OAuth 2.0 compliant authorization services, you can securely access your data. Additionally, you can access US Core, validate Carin BB IG profile, enhance read/search APIs, and access bulk data IG. ONC has a FHIR-based testing suite of tools called Inferno that helps you make sure FHIR standards are consistently implemented. AWS HealthLake has been tested with the Inferno test suite which makes it easier for EHR vendors to seek ONC certification.
Transform
Open allTransform unstructured medical data using NLP
Integrated medical natural language processing (NLP) transforms all raw medical text data in the Data Store to understand and extract meaningful information from unstructured healthcare data. With integrated medical NLP, you can automatically extract entities (e.g., medical procedures, medications), entity relationships (e.g., a medication and its dosage), entity traits (e.g., positive or negative test result, time of procedure), and Protected Health Information (PHI) data from your medical text. The NLP extracted entities are stored as native FHIR resources within the data store that can be accessed through FHIR APIs or through SQL from the Athena query engine. For example, AWS HealthLake can accurately identify patient information from an insurance claim, extract laboratory reports, and map to medical billing codes like ICD-10 in minutes, rather than hours or weeks. For a full list of entities supported, see our documentation .