Microsoft recently announced new data and artificial intelligence products that are designed to facilitate healthcare organisations’ access to the vast volumes of information gathered by healthcare professionals and medical facilities.
Microsoft is introducing the first industry-specific data solutions within Fabric, a data and analytics platform, which unify data and insights under a single unified architecture and user experience. Microsoft stated that these new tools will streamline and expedite the time-consuming process of bringing together separate data sources.
By consolidating fragmented data, health systems can ultimately enhance patient care and accommodate a larger volume of patients.
Microsoft has been conducting trials of Fabric for healthcare with specific customers, including Northwestern Medicine, Arthur Health, and SingHealth. They already plan to leverage the analytics platform to advance some of their most prominent use cases.
The current technological landscape, along with Microsoft Fabric, Azure, and generative AI, is poised to revolutionise and transform patient care.
Within Azure AI services, Microsoft is releasing new tools to assist organisations in maximizing the value of AI to increase positive impact on patient outcomes. This includes the introduction of the Azure AI Health Bot, a generative AI chatbot capable of retrieving data from an organisation's internal records and trusted external sources, as well as sources such as the Food and Drug Administration and the National Institutes of Health.
Microsoft has introduced another solution called Text Analytics for Health designed to label and extract critical medical information from diverse unstructured data sources, including clinical documents and notes.
Microsoft has revealed three new models as part of Azure AI Health Insights. The first model, known as "patient timeline," uses generative AI to compile information from various data sources, presenting clinicians with a straightforward summary of a patient's medical history.
The second model, clinical report simplification, uses generative AI allowing clinicians to simplify medical jargon into simple language, so that it can be shared with others, including patients.
The final model, radiology insights, focuses on supporting clinicians and radiologists in identifying errors and inconsistencies across reports, while also providing follow-up recommendations.
Image Credit: iStock