Microsoft has announced new health data and AI tools, including a suite of medical imaging and healthcare service models and automated documentation tools for nurses, according to CNBC.
The tools aim to help healthcare organizations build AI applications faster and free up doctors’ time on administrative tasks, which are a major cause of burnout. Nurses spend up to 41% of their time on documentation, according to a report from the Surgeon General’s office.
The new tools are the latest example of Microsoft’s efforts to establish itself as a leader in AI for healthcare.
Last October, the company unveiled a series of health features across its Azure cloud computing platform and Fabric analytics platform.
Microsoft acquired Nuance Communications, a company that provides AI speech-to-text solutions for healthcare and other industries, in a $16 billion deal in 2021.
AI Models for Healthcare
With about 80% of hospital visits and healthcare systems relying on imaging tests, Microsoft has released a set of open-source, multimodal AI models to analyze data types including medical images, clinical records, and genomic data. Healthcare organizations can use the models to build new applications and tools.
For example, digitizing a single pathology slide can take more than a gigabyte of storage, so AI-powered pathology models are often trained on small chunks of slides at a time.
On the other hand, Microsoft has built a full-slide model that improves genetic mutation prediction and cancer classification, according to a paper published in Nature . Now, healthcare systems can rely on it and adjust it to meet their needs.
Getting a basic model of a full slide in healthcare delivery was a challenge in the past, said Sarah Faze, chief strategy and digital officer at Providence. But now we can actually do it.
Health Care Agent Service
Microsoft has announced a new approach to healthcare that helps build AI agents that can help users answer questions, automate processes, and perform specific tasks.
With Microsoft Copilot Studio, these organizations can create agents equipped with healthcare-specific safeguards. When the answer cites clinical evidence, the source is displayed and a note is added explaining that the answer was generated by AI.
A healthcare organization could build an AI agent to help doctors identify relevant clinical trials for a patient. Microsoft said a doctor could type in the question What clinical trials would be appropriate for a 55-year-old man with diabetes and interstitial lung disease? and receive a list of potential options, saving the doctor the time and effort of searching for each trial.
AI agents that can help patients answer basic questions have been popular among health systems that have already begun testing the service, said Hadas Bitran, general manager of AI at Microsoft Health.
Agents that can help doctors answer questions about recent guidelines and patient history are also popular, she added.
Providing automated documentation for nurses
Last August, Microsoft announced that the next phase of its partnership with Epic Systems would be to build an AI-powered documentation tool for nurses.
Epic, a company that sells healthcare software and electronic health records to more than 280 million people in the United States, has a longstanding relationship with Microsoft.
Meanwhile, Microsoft subsidiary Nuance offers an automated documentation tool for doctors called DAX Copilot, which was unveiled last year. It allows doctors to record their patient visits in a structured format, and AI automatically converts them into clinical notes and summaries.
That means doctors won’t have to spend time writing these notes themselves every time they see a patient.
The technology has exploded in popularity this year. Nuance announced that DAX Copilot was generally available within Epic’s electronic health record in January.
But so far, DAX Copilot has only been available to doctors. Microsoft says that’s set to change: It’s working on a similar tool optimized for nurses.