Microsoft’s Mustafa Suleyman says its AI outperforms doctors on hard cases as he chases ‘medical superintelligence’
MAI-DxO scored 83% on complex cases versus 36% for physicians
Research paper
Microsoft's MAI-DxO diagnostic system correctly diagnosed complex medical cases in a simulation more than twice as often as generalist physicians, according to a study published Thursday in Science.
The system coordinates several AI agents that question a patient, order tests and debate a diagnosis, mimicking a panel of doctors.
In a simulation using complex cases from the New England Journal of Medicine, it was correct 83% of the time, while primary care doctors and general internists working individually with reference materials were correct 36% of the time.
The study notes that cases this complex are usually handled by specialists or physician teams, who were not part of the comparison.
Microsoft tested MAI-DxO with models from OpenAI, Google, Anthropic, Meta and DeepSeek, and its best results came with OpenAI's GPT-5 and GPT-5.5.
On its own with a short, basic prompt, GPT-5 scored 78.9% on complex cases at about $8,400 per case; DxO cut that cost by about $3,000 but raised accuracy by only about four points.
With GPT-5.5, DxO increased accuracy from 72% to nearly 87% at a slightly cheaper cost, though gains did not appear on emergency department cases.
Microsoft is working with Mayo Clinic to train a foundation model for healthcare, planned for release next year, and will evaluate DxO's clinical reasoning with Beth Israel Deaconess Medical Center.
From the source
In a simulation using complex cases from the New England Journal of Medicine, it was correct 83% of the time. Primary care doctors and general internists, working individually with reference materials, were correct 36% of the time.
OpenAI, Google,
Anthropic,
Meta and
DeepSeek, and its best results came with OpenAI's GPT-5 and GPT-5.5.