In this blog, we take a closer look at Amazon HealthLake, how it works, and getting started with SourceFuse, an Amazon HealthLake Partner.

During the last decade, healthcare and life sciences have experienced a huge digital transformation with medical health record digitization and increasing HIPAA governance. The challenge comes when you consider that an estimated 80% of healthcare data is unstructured and therefore needs significant and time-consuming processing before it can be used for data analytics.

Unstructured healthcare data contains so much valuable information and yet it comes in many formats from different systems – clinical notes, medical images, electronic health record (EHR) free-form text fields, medications, transfer summaries, and – yes, even today – faxes. The ability to tap into and unlock insights from a pooled data lake is crucial for observing trends, predictive, descriptive and diagnostic analytics and requires a unique solution: introducing Amazon HealthLake.

What is Amazon HealthLake?

Amazon HealthLake is a HIPAA-eligible service from  Amazon Web Services   (AWS) that enables healthcare and life sciences organizations to securely store, transform, query, and analyze health data in minutes. 

A Connector Partner supports the conversion of structured and unstructured data to Fast Healthcare Interoperability Resources (FHIR) format. From there, HealthLake uses specialized machine learning (ML) models to structure, tag, and index the data in order to provide a complete patient history. Only then can meaningful insights be extracted, such as identifying trends and making predictions for individuals or entire patient populations.

How It Works


FHIR files* can be easily migrated from Amazon S3 to the HealthLake Data Store using its import API. (*An Amazon Web Services (AWS) Partner can convert your data to FHIR R4 industry standard, which HealthLake supports.)


Data Store continuously indexes all information chronologically for easy querying. Built-in data security, HIPAA and GDPR compliance, and stringent identity access management ensures protected health information (PHI) and personally identifiable information (PII) is secure and protected.


HealthLake leverages technological advances in medical natural language processing (NLP) algorithms and ML to decode clinical jargon, abbreviations, free-text, etc., and transforms unstructured data into meaningful information. It also automatically assigns ICD-10 codes for cost analysis and billing purposes.


Once the data is structured, normalized, tagged, and indexed, HealthLake enables powerful query and search capabilities, including use of predefined filters, supporting FHIR Create/Read/Update/Delete* search operations. (*Data hidden from search results, not deleted from the service).


Data can be exported to an S3 bucket from HealthLake Data Store, from where the normalized data can be analyzed using various tools. For example, viewing trends via dashboards with Amazon QuickSight, or using ML models for predictive analysis with Amazon SageMaker.

Unlocking Insights with SourceFuse

“SourceFuse’s expertise in the HCLS space and experience with AWS services, particularly Amazon HealthLake, makes them a natural choice for a Launch partner. As an Advanced Tier Partner with the Healthcare Competency, their technical qualifications raise the bar for customers in the healthcare provider space who want to solve the most challenging problems and have a positive impact in their communities. We look forward to partnering with SourceFuse to deliver results and build a compelling practice together,” said Tehsin Syed, HealthAI Lead from AWS.

As mentioned above, the first step to securely storing, transforming, and analyzing health data using HealthLake is to convert all that data into FHIR format. Once this is achieved, an Amazon Web Services Partner can further support data analytics to extract actionable insights from the FHIR data. And this is where we can help you get started.

As a leading cloud services provider of bespoke, modernized, and regulatory compliant healthcare solutions, SourceFuse is an Amazon HealthLake Partner, building on our catalog of  AWS Cloud services  specialized for healthcare and life sciences. The combination of our  AWS Healthcare Competency,  HIPAA Compliant and  ISO  27001  certifications, and team of HIPAA certified associates with deep domain expertise, ensures your data is in the safest hands.

With data security as our top priority, we help healthcare organizations realize the end-goal of extracting health population intelligence and monitor trends with Amazon QuickSight.


The ability to combine both structured and unstructured healthcare data in one platform provides a complete overview of a patient or cohort, which ultimately leads to improved clinical decisions and better patient outcomes. HealthLake scales on-demand and supports third-party applications so that data can be shared with other healthcare providers, plus patients have unrestricted access to their own PHI.

Contact SourceFuse today, to discover the full potential of data analytics with Amazon HealthLake.