Microsoft Brings Azure Text Analytics in Line with Key Healthcare Data Standard
An update to Microsoft Azure Cognitive Services aims to bring order to the vast constellation of unstructured medical data, a major obstacle facing today's healthcare IT teams.
The new "Structuring to FHIR" feature in Text Analytics for Health, the natural language processing capability built into Microsoft Azure Cognitive Services, is now in public preview. The feature is designed to help health care organizations standardize unstructured data under the parameters of the FHIR, or the Fast Healthcare Interoperability Resources data format standard.
The goal of the FHIR is to help disparate sets of medical data "speak" to each other so that, for example, doctors can get a more complete picture of a patient's health history, researchers can analyze population health statistics easier, and developers can create apps that integrate seamlessly with modern hospital systems.
The addition of Structuring to FHIR means Text Analytics users can format various medical data types -- from doctors' notes to research papers to imaging reports and more -- to fit the FHIR standard.
"With the addition of Structuring to FHIR in public preview, Text Analytics for health customers and partners will now be able to structure diverse types of clinical documents to FHIR," wrote Hadas Bitran, head of Health & Life Sciences at Microsoft's Israel-based research and development center, in a blog post last month.
"The resources generated are grouped together into a single bundle that represents the clinical note, where all FHIR resources connect to the patient resource and reference to the exact point in the original text where the resource was generated. The FHIR output is structured in a hierarchy where resources such as observations and conditions maintain relationships with the resources representing the document sections within the bundle they came from. This allows for deeper patient insights, population-level insights, and decision support that maintains the context of the clinical narrative."
Users can then feed their FHIR-formatted assets into the new Azure Health Data Services data visualization platform, which Microsoft formally launched in March. Azure Health Data Services lets users visualize their data using tools like PowerBI and Synapse. Its integration with the Structuring to FHIR feature "allows for this data to be persisted alongside structured clinical and imaging data," Bitran said. "This makes downstream analytics and connections to other parts of the Microsoft ecosystem seamless."
The public preview of the Structuring to FHIR feature in Text Analytics can be accessed here with sign-up.
Gladys Rama (@GladysRama3) is the editor of Redmondmag.com, RCPmag.com and AWSInsider.net, and the editorial director of Converge360.