Amazon 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 copy 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. HealthLake uses machine learning (ML) models to automatically understand and extract meaningful medical information from the raw data, such as medications, procedures, and diagnoses. 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.
Import: Quickly & easily ingest health data
With the Amazon HealthLake import API you can easily migrate FHIR files from Amazon S3 to the Amazon HealthLake Data Store including clinical notes, lab reports, insurance claims, and more. 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 FHIR.
Store: Store health data in a secure, compliant, & auditable manner
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. Amazon 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.
Transform: Transform 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. For example, Amazon 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.
Query: Powerful query & search capabilities
Amazon HealthLake supports FHIR Create/Read/Update/Delete (CRUD) and FHIR Search operations. You can query 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. As per the FHIR specification, deleted data is only hidden from analysis and search results; it is not deleted from the service, only versioned. You can also search with predefined filters to find all the information on a patient.
Analyze: Identify trends & make predictions
Amazon HealthLake supports the bulk export of FHIR data from the HealthLake Data Store to an S3 bucket. With Amazon QuickSight, you can create dashboards on the exported and normalized 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 Amazon 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.