– Microsoft recently launched a preview feature of text analytics for healthcare, which enables developers to process and extract insights from unstructured medical data, according to a recent press release.
The feature is part of Text Analytics in Azure Cognitive Services and is capable of processing a broad range of data types and tasks without the need for time-intensive, manual development of custom models to extract insights from the data, Microsoft said.
Text Analytics for Health is trained on a range of medical data, including various formats of clinical notes, clinical trial protocols, and more.
Users are able to detect words and phrases mentioned in unstructured text as entities that can be associated with semantic types in the healthcare and biomedical domain, Microsoft said. These words include diagnosis, medication name, symptoms, examinations, treatments, dosage, and route of administration.
Additionally, users can also uncover more than 100 types of personally identifiable information, including protected health information, in unstructured text.
The Text Analytics for Health feature enables researchers, data analysts, medical professionals, and ISVs in the healthcare and biomedical space to unlock various scenarios.
These scenarios include producing analytics on historical medical data and creating prediction models, matching patients to clinical trials, or assisting in clinical quality reviews.
Currently, the feature is available in containers, which allows companies to deploy resources in their own development environment that meets specific security and data governance requirement, Microsoft said.
The container provides REST-based query prediction endpoints.
And in response to the COVID-19 pandemic, Microsoft partnered with the Allen Institute of AI and leading research groups to prepare the COVID-19 Open Research Dataset, the company stated in the press release.
“With Cognitive Search and Text Analytics, we developed the COVID-19 search engine, which enables researchers to more quickly evaluate and gain insights from the overwhelming amount of information about COVID-19,” Microsoft said.
The company is also working closely with organizations such as the University College London (UCL), which is conducting reviews of medical research reports.
“One of our focuses as a research group is undertaking systematic reviews across a range of policy areas,” said James Thomas at UCL, professor and director of the EPPI-Centre’s reviews facility for the department of health.
“We have been partnering with engineers at Microsoft and data scientists to build a ‘living’ reviews system – that automatically identifies relevant research for reviews as they are published. Text Analytics for health provides a powerful tool for extracting insights from clinical literature, with rich support for a wide range of healthcare terminology so that we can more quickly and accurately identify relevant information.”
Nearly 80 percent of the world’s electronic information is “unstructured,” and most is never used, according to an IDC analysis.
Most of this health and patient data is medical notes, prescriptions, audio interview transcripts, and pathology and radiology reports.
In 2018, Amazon launched a machine learning service that can extract meaningful information from unstructured EHR data and free-text clinical notes.
The service, Amazon Comprehend Medical, allows developers to sift through unstructured data and uncover key clinical terms related to a patient’s diagnoses, medication symptoms, treatments, and other interactions with the healthcare system.
Developers must provide unstructured medical text to Comprehend Medical.
The service will essentially “read” the text and then identify and return the medical information contained within it.
“Amazon Comprehend Medical allows developers to identify the key common types of medical information automatically, with high accuracy, and without the need for large numbers of custom rules,” Taha A. Kass-Hout, MD, and Matt Wood, MD, said in the announcement.
“Comprehend Medical can identify medical conditions, anatomic terms, medications, details of medical tests, treatments and procedures.”