microsoft announced Thursday new healthcare data and artificial intelligence tools, including a collection of medical image models, a healthcare agent service, and an automated documentation solution for nurses.
The tool aims to help healthcare organizations build AI applications faster and save clinicians time on administrative tasks, a leading cause of burnout in the industry. According to a report by the Public Health Directorate, nurses spend 41% of their time completing paperwork.
“By integrating AI into healthcare, our goal is to reduce the burden on medical staff, foster collaboration across healthcare teams, and increase the overall efficiency of healthcare systems across the country,” Portfolio said. said Mary Varghese Presti, Vice President of Evolution and Incubation. Microsoft Health and Life Sciences said in a prerecorded briefing with reporters.
The new tools are the latest example of Microsoft’s efforts to establish itself as a leader in healthcare AI. Last October, the company announced a set of health features across its Azure cloud and fabric analytics platform. In 2021, it acquired Nuance Communications, a provider of speech-to-text AI solutions for healthcare and other sectors, in a $16 billion deal.
Many of the solutions Microsoft announced Thursday are in early stages of development or only available in preview. Healthcare organizations plan to test and validate them before the company rolls them out more widely. Microsoft declined to say how much these new tools will cost.
Healthcare AI model
Microsoft model catalog
Provided by Microsoft
Doctors often use images to treat patients, so approximately 80% of hospital and medical office visits include imaging tests.
Microsoft is announcing a collection of open-source multimodal AI models that can analyze non-text data types, including medical images, clinical records, and genomic data. Healthcare organizations can use models to build new applications and tools.
For example, digitizing a single pathology slide can require more than a gigabyte of storage, so many existing AI pathology models have been trained on small pieces of slides at a time. Microsoft and Providence Health & Services have built a whole-slide model that improves mutation prediction and cancer subtyping, according to a paper published in the peer-reviewed journal Nature.
Healthcare systems can now build on this foundation and fine-tune it to suit their needs.
“It used to be difficult to get a basic model of the entire slide for pathology…and now we can actually do it,” said Sarah, Providence’s chief strategy and digital officer. Vasey said in an interview with CNBC. “It was really kind of a game changer.”
Models are available in the Model Catalog within Azure AI Studio, which serves as Microsoft’s generative AI development hub.
healthcare agent service
Microsoft’s Healthcare Agent Service.
Provided by Microsoft
Microsoft also announced new ways for healthcare systems to build AI agents.
AI agents vary in complexity and can help users answer questions, automate processes, and perform specific tasks.
Through Microsoft Copilot Studio, these organizations can create agents with healthcare-specific safety measures. For example, if an answer includes a reference to clinical evidence, the source will be shown and a note will indicate whether the answer was generated by AI. Microsoft says it will also alert you to fabrications and omissions.
For example, healthcare organizations can build AI agents that help doctors identify clinical trials that are relevant to their patients. According to Microsoft, doctors can enter questions such as, “What clinical trial would you perform on a 55-year-old man with diabetes and interstitial pneumonia?” You will receive a list of potential options. This will save physicians time and effort in finding each test.
AI agents that can help patients answer basic questions are popular among health systems that have already begun testing the service, said Hadas Bitran, general manager of medical AI at Microsoft Health and Life Sciences. He said this in a Q&A with reporters. Agents that help doctors answer questions about recent guidelines and a patient’s medical history are also common, she added.
Microsoft’s Healthcare Agent service will be available in preview starting Thursday.
Provide automated documentation to nurses
Microsoft announced in August that the next phase of its partnership with Epic Systems would be dedicated to building AI-powered documentation tools for nurses, and the company announced details of its plans on Thursday.
Epic is a healthcare software vendor that stores electronic health records for more than 280 million people in the United States. We have a long-standing relationship with Microsoft.
Microsoft’s Nuance already offers an automated document creation tool for doctors called DAX Copilot, which it announced last year. This allows doctors to consensually record patient encounters, and AI automatically converts them into clinical notes and summaries.
Ideally, this means that doctors don’t have to spend time entering these notes themselves every time they see a patient.
This technology has exploded in popularity this year. Nuance announced that DAX Copilot became generally available within Epic Electronic Health Records in January. This is a coveted seal of approval within the medical industry. Integrating a tool like DAX Copilot directly into a physician’s EHR workflow eliminates the need to switch apps to access it, helping to save time and reduce administrative workload.
But so far, DAX Copilot is only available to doctors. Microsoft said that’s about to change. We are building a similar tool optimized for nurses.
“Nursing workflows are very different from physician workflows, and any solution developed for nurses needs to be integrated with the way nurses work,” Presti said at the briefing. “Our team spends hours observing nurses during their shifts to see how they perform their jobs and understand where the biggest friction points are throughout the day. I discovered it.”
Microsoft is working with organizations such as Stanford Health Care, Northwestern Medicine, and Tampa General Hospital.
