Call Doctor Cloud! Amazon HealthLake officially launched

At Amazon re:Invent 2020, we previewed Amazon HealthLake , a fully managed, HIPAA compliant service. Healthcare and life sciences customers can leverage this service to aggregate health information from disparate silos and formats into a structured, centralized Amazon Cloud Technology data lake and derive insights from this data through analytics and machine learning (ML). Today, I am very excited to announce the Amazon HealthLake , available to all Amazon Cloud Technologies customers.

Being able to quickly store, transform, and analyze health data of any scale is critical to making sound health decisions. In daily practice, physicians need to follow a chronological view of a patient's medical history to determine the best course of treatment. In the event of an emergency, providing the right information to the healthcare team at the right time can significantly improve patient outcomes. Likewise, healthcare and life sciences researchers need high-quality normalized data to analyze and build models to identify population health trends or drug trial receptors.

Traditionally, most health data has been locked in unstructured text such as clinical notes and stored in IT silos. Heterogeneous applications, infrastructure, and data formats make it difficult for practitioners to access and gain insights from patient data. We built Amazon HealthLake to solve this problem.

If you can't wait to get started with the service, you can jump right over to Amazon HealthLake's Amazon Cloud Tech Console.

Introduces Amazon HealthLake

Amazon HealthLake powered by a fully managed Amazon cloud technology infrastructure. You don't have to procure, provision or manage a single piece of IT equipment. Just create a new data store and it only takes a few minutes. Once the data store is ready, you can immediately create, read, update, delete, and query data. HealthLake discloses a simple REST application programming interface (API), to most common language offer, customers and partners can easily integrate it into their business applications.

Ensuring security is a top priority for Amazon Cloud Technologies. By default, Amazon HealthLake uses Amazon Key Management Service (KMS) to encrypt data at rest. You can use keys managed by Amazon Cloud or use your own keys. Amazon KMS is designed so that no one, including Amazon Cloud Technologies employees, can retrieve your cleartext keys from the service. For data in transit, Amazon HealthLake uses industry-standard TLS 1.2 end-to-end encryption.

At launch, Amazon HealthLake supports structured and unstructured text data, which can often be found in clinical notes, lab reports, insurance claims, and more. The service Fast Healthcare Interoperability Resource (FHIR, pronounced "fire") format, a standard designed to support the exchange of health data. Amazon HealthLake is compatible with the latest revision (R4) and currently supports 71 FHIR resource types with more to come.

If your data is already in FHIR format, great! If it is not already in this format, you can convert it or use partner solutions available in 161ea6f0fa79e2 Amazon Marketplace At launch, Amazon HealthLake includes validated for 161ea6f0fa79e4 Redox, HealthLX, Diameter Health and InterSystems applications. They can easily convert HL7v2, CCDA, and flat file data to FHIR format and upload it to Amazon HealthLake.

When uploading data, Amazon HealthLake uses integrated natural language processing to extract entities present in the document and store the corresponding metadata. These entities include anatomy, medical conditions, medications, protected health information, tests, treatments and procedures. They also match the industry standard ICD-10-CM and RxNorm entities.

After uploading the data, you can start querying the data by assigning parameter values to FHIR resources and extracted entities. Whether you need access to one patient's information, or want to export many documents to build a research dataset, it only takes a single API call.

FHIR data in Amazon

Open Amazon HealthLake's Cloud Technology Console , and click "Create a Data Store". Then I just choose a name for my data store and decide to encrypt it with a key managed by Amazon Cloud. I also tick the checkbox for preloaded sample synthetic data, which is a great way to get started with the service quickly without uploading my own data.

After a few minutes, the datastore is active and I can send queries to its HTTPS endpoint. In the example below, I look for clinical notes (and only clinical notes) that contain the ICD-CM-10 "Hypertension" entity with a confidence score of 99% or higher. Behind the scenes, the Amazon Cloud Console sends HTTP GET requests to the endpoint. I highlighted the corresponding query string.

The query only takes a few seconds to run. When checking the JSON response in my browser, I see that there are two documents. For each document, I see a lot of information: when it was created, the organization it belongs to, who the author is, etc. I've also seen Amazon HealthLake automatically extract a long list of entities, including name, description, and confidence score, and add it to the document.

The document is appended to the response in base64 format.

Saving the string to a text file and decoding it with a command line tool, I see the following:

Mr. Nesser, a 52-year-old Caucasian male with numerous past medical histories, including coronary artery disease, atrial fibrillation, hypertension, and hyperlipidemia, presented to the North Emergency Department complaining of chills, nausea, acute left abdominal pain, and left Legs are numb

This documentation is absolutely correct. As you can see, querying and retrieving data stored in Amazon HealthLake is very simple.

data stored in Amazon

You can export data from Amazon HealthLake , store it in the Amazon Simple Storage Service (Amazon S3) bucket, and use it for analytics and machine learning (ML) tasks. For example, you can use Amazon Glue transform data, Amazon Athena query data, and Amazon QuickSight visualize data. You can also use this data to build, train, and deploy machine learning (ML) models Amazon SageMaker

The following blog post shows you an end-to-end analytics and machine learning (ML) workflow based on data stored in Amazon HealthLake:

• Population health applications with Amazon HealthLake: Analytics and monitoring using Amazon QuickSight
• Building predictive disease models using Amazon SageMaker with Amazon HealthLake normalized data
• Build patient outcome prediction applications using Amazon HealthLake and Amazon SageMaker
• Build a cognitive search and a health knowledge graph using Amazon AI services

Last but not least, this self-paced workshop will show you how to import and export data with Amazon HealthLake, how to process data with Amazon Glue and Amazon Athena, and how to build an Amazon QuickSight dashboard.

Now, let's take a look at the results our customers have achieved with Amazon HealthLake.

already using Amazon HealthLake

Headquartered in Chicago's Rush University Medical Center is Amazon HealthLake early adopters. They used this service to build a public health analytics platform on behalf of the Chicago Department of Public Health. The platform aggregates, consolidates and analyzes data related to patient admissions, discharges, and transfers from multiple hospitals, electronic laboratory reports, hospital capacity, and clinical care documentation for COVID-19 patients treated at Chicago hospitals. Seventeen of Chicago's 32 hospitals are currently submitting data, and Rush plans to integrate all 32 by this summer.

More recently, Rush launched another project aimed at identifying communities at highest risk for hypertension, understanding social determinants of health, and improving healthcare delivery. To do this, they collect a variety of data, such as clinical notes, ambulatory blood pressure measurements in the community, and health insurance claims data. This data is then ingested into Amazon HealthLake and stored in FHIR format for further analysis.

Dr. Bala

Vice President and Chief Analytics Officer, Rush University Medical Center

"We don't need to spend time building unrelated items or rebuilding items that already exist," he said. "This allows us to get to the analysis stage faster. Amazon HealthLake really speeds up the insights we need to deliver results to the masses. We don't want to spend all our time Used to build infrastructure. We want to provide insight."

Ernesto DiMarino 

Cortica Enterprise Applications and Data Lead

Cortica's mission is to revolutionize healthcare for children with autism and other developmental disabilities. "In just weeks, not months, Amazon HealthLake has helped us create a centralized platform for securely storing patient medical histories, medication histories, behavioral assessments, and lab reports. The platform allows us to of clinical teams can gain greater insight into patient care progress. Using predefined notebooks in Amazon SageMaker and data from Amazon HealthLake, we can apply machine learning models to track and predict each patient's progress toward achieving their goals, This is not possible using other methods. With this technology, we are also able to share HIPAA-compliant data with our patients, researchers and healthcare partners in an interoperable manner, further advancing the important aspects of autism care Research."

Pandian Velayutham

Senior Director of Engineering at MEDHOST

MEDHOST provides products and services to more than 1,000 healthcare organizations of all types and sizes. "With Amazon HealthLake, we can create a compliant FHIR data store in days instead of weeks, and integrate natural language processing and analytics to improve hospital operational efficiency, provide better patient care, and satisfy customers needs.”