AWS HealthLake features

AWS HealthLake is a HIPAA-eligible service enabling healthcare and life sciences companies to securely store and transform their data into a consistent and queryable fashion. Using the HealthLake APIs, healthcare organizations can easily ingest health data, such as medical reports or patient notes, from on-premises systems to a secure data lake in the cloud, and analyze it at petabyte scale. AWS HealthLake provides Fast Healthcare Interoperability Resources (FHIR) APIs to help you build interoperability applications that conform to ONC and CMS patient access rules. Currently in preview, HealthLake supports SMART on FHIR support, patient access API, and Bulk data FHIR API export capabilities to help you unify and analyze your data to reduce operational costs and improve decision making. AWS HealthLake uses machine learning (ML) models to automatically understand and extract meaningful medical information from the raw data, such as medications, procedures, and diagnoses. AWS HealthLake organizes and indexes all the information and stores it in the Fast Healthcare Interoperability Resources (FHIR) industry standard format to provide a complete view of each patient's medical history. Organizations can build ML models with Amazon SageMaker and use advanced Amazon QuickSight analytics to understand relationships, identify trends, and make predictions from the newly normalized and structured data.


With the AWS HealthLake import API you can easily migrate FHIR files from Amazon S3 to the AWS HealthLake Data Store including clinical notes, lab reports, insurance claims, and more. You can also import data synchronously using create/update APIs. AWS HealthLake supports data in the FHIR R4 industry standard. If your data is not in this format, you can work with an AWS partner to convert your health data to FHIR format.


Data Store helps index all information so it can be easily queried. The Data Store creates a complete view of each patient’s medical history in chronological order and facilitates information exchange using the V4 FHIR specification. The Data Store is always running to keep your index up-to-date, offering you the ability to query the information anytime using the standard FHIR Operations with durable primary storage and index scaling. AWS HealthLake meets rigorous security and access controls to ensure patients’ sensitive health data is protected and meets regulatory compliance. With customer-managed keys, GDPR compliance, and HIPAA eligibility, customers can be confident their patients’ data remains secure and their privacy is protected.


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.


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.


AWS HealthLake supports FHIR Create/Read/Update/Delete (CRUD) and FHIR Search operations. You can add new records by performing a Create Operation for adding new patients and their information, like medications. You can read the most recent version of that record by performing a Read Operation. You can update a previously created record by performing an Update Operation. On delete, records are soft deleted and hidden from search results.. You can also search with predefined filters to find all the information on a patient.


AWS  HealthLake Analytics supports Athena SQL queries on HealthLake data that enables users to analyze without needing to export the data. With Amazon QuickSight, you can create dashboards on HealthLake data to quickly explore patient trends. Here is an example of a population health dashboard created using Amazon QuickSight. You can also build, train, and deploy your own predictive analytics using machine learning models with Amazon SageMaker. Here is how to build a number of predictive chronic or acute disease models using Amazon SageMaker with AWS HealthLake normalized data. Here is an example of building an ML-enabled cognitive search application where every clinical evidence is tagged, indexed, and structured to provide evidence-based topics on things like transmission, risk factors, therapeutics, and incubation. This particular functionality is tremendously valuable for clinicians or scientists, who can quickly ask questions to validate their clinical decisions or advance their research.