What is AWS HealthLake?
AWS HealthLake is a HIPAA eligible service for clinical data ingestion, storage, and analysis utilizing the Healthcare Interoperability FHIR (R4) specification.
Note
After February 20, 2023, HealthLake data stores do not use integrated natural language processing (NLP) by default. If you are interested in turning on this feature on your data store, see How do I turn on HealthLake's integrated natural language processing feature? in the Troubleshooting chapter.
Health data is frequently incomplete and inconsistent. It's also often unstructured, with information contained in clinical notes, lab reports, insurance claims, medical images, recorded conversations, and time-series data (for example, heart ECG or brain EEG traces).
Healthcare providers can use HealthLake to store, transform, query, and analyze data in the AWS Cloud. Using the HealthLake integrated medical natural language processing (NLP) capabilities, you can analyze unstructured clinical text from diverse sources. HealthLake transforms unstructured data using natural language processing models, and provides powerful query and search capabilities. You can use HealthLake to organize, index, and structure patient information in a way that is secure, compliant, and can be audited.
HealthLake is also integrated with Amazon Athena and AWS Lake Formation. You can use this integration to query your data store using SQL.
Benefits of AWS HealthLake
With AWS HealthLake, you can:
-
Quickly and easily ingest health data – You can bulk import on-premises Fast Healthcare Interoperability Resources (FHIR) files, including clinical notes, lab reports, insurance claims, and more, to an Amazon Simple Storage Service (Amazon S3) bucket. You can then use the data in downstream applications or workflows.
-
Use the FHIR REST API operations – HealthLake supports using the FHIR REST API operations to perform CRUD (Create/Read/Update/Delete) operations on your data store. FHIR search is also supported.
-
Store your data in the AWS Cloud in a secure, HIPAA-eligibile manner that can be audited – You can store data in the FHIR format, so it can be easily queried. HealthLake creates a complete, chronological view of each patient’s medical history, and structures it in the R4 FHIR standard format.
-
Athena integration – HealthLake's integration with Athena means you can create powerful SQL-based queries that you can use to create and save complex filter criteria. Then, you can use this data in downstream applications such as SageMaker to train a machine learning model or Amazon QuickSight to create dashboards and data visualizations.
-
Transform unstructured data using specialized machine learning (ML) models – HealthLake provides integrated medical natural language processing (NLP) using Amazon Comprehend Medical. Raw medical text data is transformed using specialized ML models. These models have been trained to understand and extract meaningful information from unstructured healthcare data. With integrated medical NLP, you can automatically extract entities (for example, medical procedures and medications), entity relationships (for example, a medication and its dosage), and entity traits (for example, positive or negative test result or time of procedure) data from your medical text. HealthLake then creates new resources based on the traits sign, symptom, and condition. These are added as new Condition, Observation, and MedicationStatement resource types.
HealthLake use cases
You can use HealthLake for the following healthcare applications:
-
Population health management – HealthLake helps healthcare organizations analyze population health trends, outcomes, and costs. This helps organizations to identify the most appropriate intervention for a patient population and choose better care management options.
-
Improving quality of care – HealthLake aids hospitals, health insurance companies, and life sciences organizations close gaps in care, improve quality of care, and reduce cost by compiling a complete view of a patient’s medical history.
-
Optimizing hospital efficiency – HealthLake offers hospitals key analytics and machine learning tools to improve efficiency and reduce hospital waste.
Accessing HealthLake
You can access HealthLake through the AWS Management Console, AWS Command Line Interface (AWS CLI), or the AWS SDKs.
-
AWS Management Console – Provides a web interface that you can use to access HealthLake.
-
AWS Command Line Interface (AWS CLI) – Provides commands for a broad set of AWS services, including HealthLake, and is supported on Windows, macOS, and Linux. For more information about installing the AWS CLI, see AWS Command Line Interface.
-
AWS SDKs – AWS provides SDKs (software development kits) that consist of libraries and sample code for various programming languages and platforms (Java, Python, Ruby, .NET, iOS, Android, and so on). The SDKs provide a convenient way to create programmatic access to HealthLake and AWS. For more information, see the AWS SDK for Python
.
HIPAA eligibility and data security
This is a HIPAA Eligible Service. For more information about AWS, U.S. Health Insurance Portability and Accountability Act of 1996 (HIPAA), and using AWS services to process, store, and transmit protected health information (PHI), see HIPAA Overview
Connections to HealthLake containing Personally identifiable information (PII) must be encrypted. By default, all connections to HealthLake use HTTPS over TLS. HealthLake stores encrypted customer content and operates by the AWS Shared Responsibility principle.
Pricing
For information about HealthLake pricing, see the AWS HealthLake pricing page
