Amazon Web Services (AWS) has announced the general availability of Amazon HealthLake, a Hipaa-eligible service for healthcare and life sciences organisations to ingest, store, query and analyse their health data at scale.

HealthLake lets healthcare organisations store, transform and query health data in the cloud using machine learning for a complete picture of patient and population health.

The service is part of AWS for Health, an initiative that provides healthcare, biopharma and genomics users with a set of cloud-based services to personalise patient care, quickly innovate and bring new therapies to market

Cortica, InterSystems, Redox and Rush University Medical Center are among those already using HealthLake.

HealthLake uses machine learning to understand and extract meaningful medical information from unstructured data, and then organises, indexes and stores that information in chronological order. The result provides a holistic view of patient health.

The service leverages the Fast Healthcare Interoperability Resources (FHIR) format to enable interoperability by facilitating the exchange of information across healthcare systems, pharmaceutical companies, clinical researchers, health insurers, patients and more.

AWS for Health provides proven and easily accessible capabilities that help organisations increase the pace of innovation, unlock the potential of health data and develop more personalised approaches to therapeutic development and care. As part of AWS for Health, HealthLake facilitates the application of analytics and machine learning on top of newly normalised and structured data. Doing so lets users examine trends such as disease progression at the individual or population health level over time, spot opportunities for early intervention, and deliver personalised medicine.

The healthcare industry is being transformed through the cloud and the use of data, helping organisations uncover insights and deliver improved patient care. Healthcare organisations are creating huge volumes of patient information every day, and most of these data are unstructured and contained in clinical notes, laboratory reports, insurance claims, medical images, recorded conversations and graphs that are in different formats and spread across disparate systems.

Before they can derive a single insight – for example flag high-risk diabetic patients predicted to develop further complications – they have to aggregate, structure and normalise these data. Then they must be tagged, indexed and put in chronological order. This is a time-consuming and error-prone process.

Some healthcare organisations use optical character recognition and build rule-based tools to automate the process of transforming unstructured data and extracting clinical information, for example diagnoses, medications and procedures. However, these are often inaccurate and can’t account for variations in spelling, typos or grammatical errors.

Even after organisations aggregate and structure their data, they still need to build their own analytics and machine-learning applications to reveal relationships in the data, discover trends and make precise predictions. The cost and operational complexity of this work can be prohibitive. As a result, most organisations cannot realise the full potential of their data to help improve the health of patients and communities.

HealthLake removes this heavy lifting by using machine learning to automate the extraction and transformation of unstructured health data so organisations can apply analytics and customised machine-learning models to their information. Using HealthLake, organizations can move their FHIR-formatted health data from on-premises systems to a secure data lake in the cloud.

Tuned machine-learning models that understand medical terminology identify and tag each piece of clinical information. The service then enriches data with standardised labels – medications, conditions, diagnoses and so on – so the data can be easily searched and analysed. It also indexes events such as patient visits into a timeline, giving medical professionals a holistic, chronological view of each patient’s medical history.

Once this heavy lifting is completed, users can apply analytics and machine learning on top of these normalised and structured data. For example, they can apply analytics using Amazon QuickSight to understand patient and population-level trends, as well as build machine-learning models with Amazon SageMaker to help make accurate predictions about the progression of disease, the efficacy of clinical trials, the eligibility of insurance claims and more.

HealthLake also stores data in the FHIR format to facilitate the exchange of information so it is easier for organisations, researchers and practitioners to collaborate and accelerate breakthroughs in treatments, deliver vaccines to market faster and discover health trends in patient populations.

“Data in the FHIR format facilitate the exchange of information so it is easy for organisations and practitioners to collaborate, accelerate breakthroughs in treatments, and discover health trends in patient populations,” said Taha Kass-Hout, director of machine learning at AWS.

Those who do not already have data in the FHIR format can work with AWS connector partners, such as Diameter Health, InterSystems, Redox and Health LX, who have built validated HealthLake connectors to transform existing healthcare data into FHIR format and move them to HealthLake.

“Diameter Health is excited to have been named a select connector partner for HealthLake to deliver FHIR-enabled and optimised data to AWS customers,” said Eric Rosow, CEO of Diameter Health. “By transforming the quality of clinical data using scalable technology, this approach will not only enable but also accelerate advanced analytics and, ultimately, improved patient care.”

HealthLake’s purpose-built analytics and machine-learning capabilities are also available under AWS for Health, a growing portfolio that simplifies how healthcare, biopharma and genomics organisations discover, assess and deploy the cloud to achieve better business and patient outcomes.

For example, features in AWS for Health are helping users create holistic electronic health records (EHRs) to help clinicians make data-driven care plans, accelerate research and discovery to bring new therapies to market faster, and powering population genomic initiatives to expand precision medicine accessibility.

“More and more of our customers in the healthcare and life sciences space are looking to organise and make sense of their reams of data, but are finding this process challenging and cumbersome,” said Swami Sivasubramanian, vice president at AWS. “We built HealthLake to remove this heavy lifting for healthcare organisations so they can transform health data in the cloud in minutes and begin analysing that information securely at scale. Alongside AWS for Health, we’re excited about how HealthLake can help medical providers, health insurers and pharmaceutical companies provide patients and populations with data-driven, personalised and predictive care.”

Rush University Medical Center is an academic medical centre that includes a 671-bed hospital serving adults and children, the 61-bed Johnston R Bowman Health Center and Rush University. For more than 180 years, the medical centre has been developing innovative treatments.

“Even while still in preview, HealthLake was an integral part of our Covid-19 response and our efforts to address health inequities,” said Bala Hota, chief analytics officer at Rush University Medical Center. “It has enabled us to quickly store disparate data from multiple data sources in FHIR format in order to gain critical insights in to the care of Covid-19 patients. We have also used HealthLake’s integrated natural language processing to extract information such as medication, diagnosis and previous conditions from doctors’ clinical notes and enrich patient records to examine barriers to healthcare access, providing our researchers additional data points for analytics. With the HealthLake API, we created a mobile app to provide insights into care gaps across the west side of Chicago. HealthLake enables us to accelerate insights and drive decisions faster to better serve the Chicago community.”

Cortica, a preview customer of HealthLake, provides healthcare services to children with autism and other brain conditions. The Cortica Care Model blends neurology, research-based therapies and technology into care programmes for children.

“At Cortica, we’re on a mission to revolutionise healthcare for children with autism and other developmental differences,” said Ernesto DiMarino from Cortica. “In a matter of weeks rather than months, HealthLake empowered us to create a centralised platform that securely stores patients’ medical history, medication history, behavioural assessments and lab reports. This platform gives our clinical team deeper insight into the care progression of our patients. Using predefined notebooks in SageMaker with data from HealthLake, we can apply machine-learning models to track and prognosticate each patient’s progression towards their goals in ways not otherwise possible. Through this technology, we can also share Hipaa-compliant data with our patients, researchers and healthcare partners in an interoperable manner, furthering important research into autism treatment.”

CureMatch is a digital health company focused on personalised medicine and combination therapy in oncology. CureMatch’s decision support system guides oncologists in the selection of cancer drugs that are customised for individual patients based on their molecular tumour profile, providing actionable intelligence to support cancer treatment options.

“With the use of the HealthShare message transformation service by InterSystems and HealthLake, we will be able to access and transform molecular profile data from the EHR into FHIR format to run advanced analytics and algorithms, providing clinical decision support and guidance to assist oncologists with personalised cancer treatment options,” said Philippe Faurie, vice president at CureMatch.

Medhost provides enterprise, departmental and healthcare engagement products to more than 1000 healthcare facilities. Its integrated product portfolio includes intuitive and cloud-based clinical, financial and operational options, including YourCare Everywhere, a health and wellness consumer engagement platform.

“The vast majority of Medhost’s more than 1000 healthcare facility customers want to develop solutions to standardise patient data in FHIR format and build dashboards and advanced analytics to improve patient care, but that is difficult and time consuming today,” said Pandian Velayutham, senior director of engineering at Medhost. “With HealthLake, we can meet our customers’ needs by creating a compliant FHIR data store in just days rather than weeks with integrated natural language processing and analytics to improve hospital operational efficiency and provide better patient care.”