Microsoft has released feature updates for its Azure AI Services for Health offerings, which include support for social determinants of health (SDOH) analytics, clinical trial matching, and responsible AI implementation. The features are part of Microsoft’s efforts to drive innovation in the healthcare sector and will be previewed at the HIMSS 2023 conference. The update for SDOH and ethnicity data enables users to extract insights from social, environmental, and demographic factors found in unstructured biomedical data, while Project Health Insights generates insights using patient data and pre-built AI models.
Microsoft has recently released a feature for its Cloud for Healthcare, offering updates to its Azure AI Services for Health aimed at improving social determinants of health (SDOH) analytics, responsible AI implementation, and clinical trial matching. The release of these features is part of Microsoft’s ongoing efforts to drive technological innovation in the healthcare sector, with the updates set to be previewed at the HIMSS 2023 conference.
One of the updates adds support for SDOH and ethnicity data within Azure’s Text Analytics for Health. This enables users to extract insights from social, environmental, and demographic factors found in unstructured biomedical data. Assertion detection is also included, allowing users to capture the negation of substance use by a patient using a combination of SDOH data, substance use, and substance use amount found in unstructured clinical notes.
Another update is the preview of Project Health Insights, which generates insights using patient data and includes pre-built AI models to generate specific insights based on confidence scores and evidence from the input data. Two Project Health Insights models will be demonstrated at HIMSS23 for cancer research and care: Oncology Phenotype and Clinical Trial Matcher. Oncology Phenotype allows clinicians to identify cancer attributes within a patient population with existing cancer diagnoses, while Clinical Trial Matcher helps match patients to potentially suitable clinical trials based on patient data and the trial’s eligibility criteria.
The third update previews a new Azure Health Bot template, which allows users to integrate Azure OpenAI Service into their Health Bot. Azure Health Bot’s capabilities include providing patient triage and healthcare-related information from clinically validated sources to users. The integration of OpenAI is designed to help provide answers to user queries when the bot does not understand what the end user is trying to ask.
Microsoft also announced the general availability of its accelerator kit for healthcare, part of the Responsible AI Dashboard in Azure Machine Learning. The accelerator kit is designed to assist users with training and debugging AI models to address fairness, explainability, and biases before deployment in healthcare settings.
These updates demonstrate Microsoft’s commitment to the healthcare sector and its goal of improving patient outcomes through technology. By leveraging AI and cloud computing, Microsoft is providing healthcare professionals with powerful tools to analyze data, match patients to clinical trials, and deliver personalized care. The updates also show Microsoft’s emphasis on responsible AI implementation, ensuring that AI models are fair, transparent, and unbiased, and providing users with the tools to debug and address any issues before deployment.
Leave a Reply