Two AIs just matched or beat doctors on diagnosis. The catch: none of the patients were real. (Ana Maria Constantin, June 19, 2026, Next Web)
The first system, Mira, was built by academic researchers in Germany.Given access to a simulated medical record, it can choose from more than 85,000 actions: tests, prescriptions, even hospital admissions. Across more than 500 emergency-department cases, it reached a diagnostic accuracy of about 87 per cent, against 78 per cent for a panel of six doctors. It was strongest on conditions with clear test results, such as pancreatitis and appendicitis.
The second, Amie, is Google’s, and runs on its Gemini model.
Tested against 21 UK GPs across 100 multi-visit cases, it matched them on clinical reasoning and produced treatment plans that stuck more closely to official guidelines. On a benchmark for tricky medication decisions, it came out ahead.