Amazon Launches Service for Big Data Analytics in Healthcare
Amazon HealthLake is designed to standardize patient information and facilitate big data analytics in healthcare.
Source: Thinkstock
By Jessica Kent
- Amazon Web Services (AWS) has announced Amazon HealthLake, a HIPAA-eligible service that aims to support interoperability standards and further drive the use of big data analytics in healthcare.
Healthcare data is often incomplete and unstructured. Information is stored in disparate formats and systems, including clinical notes, lab reports, insurance claims, medical images, recorded conversations, and time series data. Structuring this data can help organizations make more informed care decisions, design more comprehensive clinical trials, and complete tasks more efficiently.
While some healthcare organizations build rule-based tools to automate the process of converting unstructured data and tagging clinical information, these solutions often fail because the data needs to be normalized across disparate systems. Additionally, the tools often can’t account for every potential variation in spelling, unintended typos, and grammatical errors.
Even if organizations are able to gather and structure their data, they still need to build their own analytics applications to discover relationships in the data, notice trends, and make accurate predictions. These processes are costly and complex, leaving the vast majority of organizations without beneficial insights from their big data resources.
Amazon HealthLake aims to collect an organization’s complete data across different siloes and varying formats into a centralized data lake, automatically standardizing the data using machine learning techniques. The service allows organizations to store, tag, index, standardize, query, and apply machine learning techniques to analyze data in the cloud.
“There has been an explosion of digitized health data in recent years with the advent of electronic medical records, but organizations are telling us that unlocking the value from this information using technology like machine learning is still challenging and riddled with barriers,” said Swami Sivasubramanian, Vice President of Amazon Machine Learning for AWS.
“With Amazon HealthLake, healthcare organizations can reduce the time it takes to transform health data in the cloud from weeks to minutes so that it can be analyzed securely, even at petabyte scale. This completely reinvents what’s possible with healthcare and brings us that much closer to everyone’s goal of providing patients with more personalized and predictive treatment for individuals and across entire populations.”
HealthLake uses machine learning trained to understand medical terminology to identify and tag each piece of clinical information, index events into a timeline view, and enhance the data with standardized labels so that providers can easily search all of this information.
The service also automatically structures all of an organization’s data into the FHIR format, so that the information can be easily and securely shared between health systems and with third-party applications. This will allow providers to effectively collaborate and giving patients unlimited access to their medical information.
Organizations can use Amazon HealthLake to improve population health management, quality of care, and hospital efficiency.
"At Cerner we are committed to transforming the future of healthcare through cloud delivery, machine learning, and AI. Working alongside AWS, we are in a position to accelerate innovation in healthcare. That starts with data,” said Ryan Hamilton, SVP, Population Health, Cerner.
“We are excited about the launch of Amazon HealthLake and its potential to quickly ingest patient data from various diverse sources and transform the data to perform advanced analytics to unlock new insights and serve many of our initiatives across population health.”
Other tech giants have developed solutions to help healthcare organizations make sense of their big data resources. In July 2020, Google launched BigQuery Omni, a multi-cloud analytics platform designed to help customers analyze data stored in Google Cloud, AWS, and Microsoft Azure.
“For our customers, data is no longer one room in the house — it’s the foundation. However, moving data across different clouds is both cumbersome and expensive,” Debanjan Saha, general manager and vice president of engineering, Google Cloud, said in a statement.
“With BigQuery Omni, customers will get a multi-cloud analytics solution that enables them to gain critical data insights, in one unified experience.”
