Microsoft Seeks Role in Clinical Decisions With AI

Microsoft’s MAI-DxO correctly diagnosed 83% of complex medical cases in a simulation, compared with 36% for primary care doctors and general internists working individually with reference materials, according to a study published Thursday in Science. The comparison didn’t include specialists or physician teams, who usually handle cases of that complexity. The findings give Microsoft a platform to press for a larger role for its AI in clinical decisions, but they don’t establish how the system performs in routine care.

A simulated benchmark

The researchers drew cases from the New England Journal of Medicine. MAI-DxO, also called DxO, coordinates several AI agents that question patients, order tests and debate diagnoses, much like a panel of doctors. Microsoft tested it with models from OpenAI, Google, Anthropic, Meta and DeepSeek; its best results came with OpenAI’s GPT-5 and GPT-5.5.

Study data indicated that much of the improvement came from greater capability in the underlying models, while Microsoft’s orchestration system added gains. Microsoft joins Google and OpenAI in saying its AI can match or outperform doctors. But the benchmark compared performance on complex cases in a simulation, not with specialist teams handling those cases.

Microsoft also measured estimated operating costs. With a short, basic prompt, GPT-5 scored 78.9% on complex cases at about $8,400 per case. DxO cut the cost by about $3,000 and lifted accuracy by about four percentage points. On emergency department cases, GPT-5 with and without DxO showed little improvement in accuracy or cost.

GPT-5.5, released in April 2026, scored 72% on complex cases on its own; with DxO, its accuracy rose to nearly 87% at a slightly lower cost. On emergency department cases, both versions scored about 85% at similar cost. Gemini 2.5 Flash scored 46.4% on its own and nearly 69% with DxO. Microsoft researchers said accuracy gains naturally shrink as models approach the theoretical maximum. A spokesperson said, “The DxO orchestration helps with the broader challenge of optimization both accuracy and cost.”

From benchmark to hospital

Microsoft plans to evaluate DxO’s clinical reasoning across hospital settings through a new partnership with Beth Israel Deaconess Medical Center in Boston. Patients will receive standard treatment, including triage, time with a specialist, treatments, investigations and a decision on whether it’s safe to discharge. Patients who consent will also engage with DxO, and Microsoft and its partners will compare the system’s recommendations with those of human doctors.

“This technology is ready for real-world evaluations, and you can imagine the complexity and diversity of issues that come from a Boston emergency department on a Friday evening,” Dominic King, vice president of Health at Microsoft AI, told TechCrunch. King said the study would include emergency and urgent-care settings, and provide evidence by the end of the study period about whether the systems could be deployed at greater scale in the future. “We think this will be the biggest study of its kind.”

Google published a clinical study with Beth Israel in The Lancet this month to evaluate its AMIE conversational diagnostic AI during real-world urgent-care visits, with human physicians monitoring interactions in real time. Microsoft’s planned evaluation and Google’s study put major technology companies and hospital partners at the center of clinical AI testing. The base study reports no transfer of public authority or demographic effects; it focuses on model performance, costs and proposed clinical evaluations.

Microsoft’s expansion plans

Mustafa Suleyman, Microsoft AI’s CEO, called the result a step toward “medical superintelligence.” A manifesto published alongside Microsoft’s Science study described the term as “the capacity to surpass the strongest contemporary human-led health systems in medical reasoning and coordination across the full arc of care.” Microsoft says it aims to move beyond benchmarking tasks such as answering medical exam questions and generating diagnoses, and toward integrating AI with clinicians and healthcare systems to improve outcomes.

Dominic King described healthcare’s “growing mismatch between demand and supply of medical expertise.” Suleyman said Microsoft is working with the Mayo Clinic to train a healthcare foundation model, with release planned for next year. He also said the company sees DxO as part of its foundational infrastructure for healthcare developments.

Microsoft already sells dictation and radiology tools to clinicians. Suleyman said, “We have to have the absolute number one state-of-the-art medical clinical decision support products over the next few years.” The study records a simulated performance advantage on selected complex cases and a corporate push toward further testing; whether the system can be deployed at greater scale remains a question for the planned evaluations.