Microsoft has expanded its Text Analytics offering within Azure Cognitive Services. It’s new offering, Text Analytics for Health, allows users to extract and analyze unstructured medical data. To create the feature, Microsoft trained its Text Analytics engine with a broad range of medical data sets including clinical notes, clinical trials protocols, and more. The goal is to gain insights from such data without the traditional time-intensive task of manually reading through these data sets.
“The healthcare industry is overwhelmed with data,” Hadas Bitran, Microsoft Healthcare Group Manager, commented in a blog post announcement. “Much of this healthcare data is in the form of unstructured text, such as doctor’s notes, medical publications, electronic health records, clinical trials protocols, medical encounter transcripts, and more. Healthcare organizations, providers, researchers, pharmaceutical companies, and others face an incredible challenge in trying to identify and draw insights from all that information. Unlocking insights from this data has massive potential for improving healthcare services and patient outcomes.”
Text Analytics for Health is currently available as a preview feature. Words and phrases that the feature is looking for include diagnosis, medication name, symptom/sign, examinations, treatments, dosage, and route of administration. Additionally, users can extract more than 100 types of personal identifiable information from the unstructured text. For a full list of health entity types, review the documentation.
Identifying and extracting keywords is step one. What is done with those words is a much bigger problem to solve. Currently, the Text Analytics for Health container performs Named Entity Recognition (NER), relation extraction, entity negation and entity linking. Developers can apply their own security and data governance requirements. Check out the preview site to learn more.
Go to Source
Author: <a href="https://www.programmableweb.com/user/%5Buid%5D">ecarter</a>