Microsoft announced Thursday new healthcare data and artificial intelligence tools, including a collection of medical imaging models, a service for healthcare agents and an automated documentation solution for nurses.
The tools aim to help healthcare organizations develop AI applications faster and save physicians time on administrative tasks, a leading cause of burnout in the industry. According to a report from the Office of the Surgeon General, nurses spend up to 41% of their time on documentation.
“By integrating AI into healthcare, our goal is to reduce the burden on medical staff, promote collective collaboration among the healthcare team, and increase the overall efficiency of healthcare systems across the country,” said Mary Varghese Presti, vice president of portfolio development and Incubation at Microsoft Health and Life Sciences said in a pre-recorded 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 unveiled a suite of health features for its Azure cloud and fabric analytics platform. In 2021, the company also acquired Nuance Communications, which provides voice-to-text AI solutions for healthcare and other sectors, in a $16 billion deal.
Many of the solutions announced by Microsoft on Thursday are in early development or only available in preview. Healthcare organizations will test and validate them before the company rolls them out more broadly. Microsoft declined to disclose the cost of these new tools.
AI models for healthcare
Microsoft's model catalog
Courtesy of Microsoft
Approximately 80% of visits to hospitals and health systems involve an imaging study because physicians often rely on images to treat patients.
Microsoft is launching a collection of open-source, multimodal AI models that can analyze data types beyond just text, such as medical images, clinical records and genomic data. Healthcare organizations can use the models to develop new applications and tools.
For example, digitizing a single pathology slide can require more than a gigabyte of storage, so many existing pathology AI models were trained on small slide pieces at a time. Microsoft and Providence Health & Services have developed a whole-film model that improves mutation prediction and cancer subtyping, according to an article published in the journal Nature.
Now health systems can build on it and adapt it to their needs.
“In the past, it's been a challenge to develop a comprehensive foundation model for pathology… and now we're actually able to do it,” said Sara Vaezy, chief strategy and digital officer at Providence, in an interview with CNBC. “It really was kind of a game changer.”
The models are available in the model catalog in Azure AI Studio, which serves as Microsoft's generative AI development center.
Health agent services
Microsoft's health agent service.
Courtesy of Microsoft
Microsoft also announced a new way for healthcare systems to develop AI agents.
AI agents vary in complexity but can help users answer questions, automate processes, and perform specific tasks.
Through Microsoft Copilot Studio, these organizations can create agents equipped with health-specific protections. For example, if an answer contains a reference to clinical evidence, the source is displayed and a note indicates whether the answer is AI-generated. According to Microsoft, counterfeits and omissions are also reported.
For example, a healthcare organization could develop an AI agent to help doctors identify relevant clinical trials for a patient. Microsoft said a doctor can type in the question: “What clinical trials for a 55-year-old man with diabetes and interstitial lung disease?” and get a list of possible options. This would save the doctor the time and effort of finding every single study.
AI agents that can help patients answer basic questions are gaining popularity among health systems that have already started testing the service, said Hadas Bitran, general manager of health AI at Microsoft Health and Life Sciences, in a question-and-answer session with reporters. Agents that can help doctors answer questions about current guidelines and patients' medical history are also widely available, she added.
Microsoft's Health Agent service is available in preview starting Thursday.
Providing automated documentation for caregivers
In August, Microsoft announced that the next phase of its partnership with Epic Systems would be dedicated to developing an AI-powered documentation tool for nurses, and the company detailed those plans on Thursday.
Epic is a healthcare software provider that manages the electronic health records of more than 280 million people in the United States. The company has had a long-standing relationship with Microsoft.
Microsoft's Nuance already offers an automated documentation tool for doctors called DAX Copilot, which was introduced last year. It allows doctors to consensually record their visits to patients and the AI automatically converts them into clinical notes and summaries.
Ideally, this means doctors don't have to spend time typing up these notes themselves every time they see a patient.
The technology is enjoying enormous popularity this year. Nuance announced that DAX Copilot became generally available in Epic's electronic health record in January – a coveted seal of approval in the healthcare industry. By integrating a tool like DAX Copilot directly into physicians' EHR workflows, they don't have to switch apps to access it, saving time and reducing administrative burden.
But until now, DAX Copilot was only available to doctors. Microsoft said that is changing. A similar tool optimized for nurses is being developed.
“The nursing workflow is very different than that of physicians, and any solution designed for nurses must integrate into the way they work,” Presti said during the briefing. “Our team has spent hours following nurses throughout their shift to see how they complete their tasks and identify where the greatest points of friction exist throughout the day.”
Microsoft is collaborating on development with organizations such as Stanford Health Care, Northwestern Medicine and Tampa General Hospital.
Comments are closed.