Health

Google Releases FHIR Data Aggregation and Mapping Toolkit

Loading...

Google’s cloud division on Thursday unveiled a new product designed to aggregate and standardize data for healthcare and life sciences organizations.

The tool, dubbed the Google Cloud Medical Data Engine, is joining the growing market for tools that technology companies are releasing under the Fast Healthcare Interoperability Resources standard, better known as FHIR.

Amazon published last week the general availability of HealthLake, a tool that healthcare and biology organizations can use to aggregate and analyze data in the cloud; it also indexes unstructured data from clinical notes and medical images. Amazon Web Services, the company’s cloud division, has partnered with external companies that customers will work with to bring data to FHIR before moving it to HealthLake.

FHIR gained momentum in the healthcare industry last year when two HHS agencies issued regulations requiring some healthcare software developers and insurers to implement application programming interfaces – protocols that allow different applications to communicate with each other – that are FHIR-compliant.

The regulations, first proposed by CMS and the Office of the National Health Information Technology Coordinator, HHS in 2019, have received the backing of tech giants.

Microsoft, which also released a tool that collects and stores health data using FHIR through its Azure cloud division in 2019, wrote to CMS and ONC when their rules were proposed for voice support. Apple, which offers a proprietary tool that allows patients to download health data from hospitals and clinics via FHIR-based APIs, has also supported the rules.

Google’s latest cloud-based tool, which it released Thursday as a private preview, combines data from medical records, statements, and clinical trials and displays it in FHIR format. It is based on the Google Cloud Healthcare API, an application programming interface that was publicly released last year and is designed to link healthcare data with third-party applications.

Ideally, the data would be used to help clinicians identify gaps in care or mark patients at high risk for certain conditions by providing a “longitudinal” medical history, and provide researchers with a basis for analyzing data with artificial intelligence and other analytical tools in the cloud, according to Google. …

Google said the healthcare data processing tool was briefed on the work it is doing with the Mayo Clinic in Rochester, Minnesota, which has a multi-year contract with Google Cloud.

Loading...

As of last year, FHIR and APIs were not widely adopted in healthcare, one expert said. report Market research company Chilmark Research released it in the spring of 2020.

Brian Murphy, an analyst who wrote the report and director of research at Chilmark, wrote that he expects this to change in the future. They will become “dominant” in the healthcare industry as HHS compliance regulations come into effect and software vendors will continue to create new tools based on FHIR standards.

Earlier this month, CMS began enforcing requirements from its interoperability rule, which requires the payers it regulates to implement FHIR-based APIs that allow patients to access tickets and receive information. Beginning in December 2022, ONC-certified healthcare IT software developers will be required to make FHIR-based APIs available to customers.

FHIR adoption has accelerated somewhat over the past year, Murphy said.

“The adoption is stable but slow,” he said. However, “there is a lot of energy and excitement around it.”

According to Jeff Becker, chief analyst at CB Insights, a venture capital and start-up data analytics firm, tech giants have chosen healthcare as the ripe field for AI.

The widespread development and adoption of artificial intelligence tools in healthcare will require “many small steps,” starting with figuring out how to store huge amounts of health data, including medical records, claims, and patient-derived health data from devices, into a standard. “The way that algorithms can digest and analyze,” he said.

“Some of the data standardization … is really just the first step in a longer story,” Becker said.

Source link

Loading...

Read More

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button