Microsoft researchers described MAI-DxO, a system that acts like a crack medical team, in a paper published in Science this month. When challenged with extraordinarily complex cases, MAI-DxO was more than twice as accurate as physicians armed with textbooks and the internet—and nearly four times as accurate as those relying solely on their own knowledge. The system also surpassed doctors on typical emergency room cases, achieving 80 percent accuracy versus 47 percent for physicians. Study author Eric Horvitz told Science he has been working on principles and applications of AI in medicine since the 1980s, and that his hope is these advances will help bring timely and effective care to more people. The article notes that AI already outperforms doctors at spotting breast cancer on mammograms and detecting skin cancer in curated datasets, and that systems can detect signs of cancer spread and heart disease, but that standard medical licensing exams gauge a physician's knowledge rather than the messy realities of diagnosis. Earlier this year, a team at Harvard Medical School and colleagues developed a benchmark to compare AI and physicians, and pitting OpenAI's o1-preview reasoning model against two expert physicians on emergency room cases, the AI performed better across clinical tasks, from triage and chart reviews to deciding whether to admit or discharge.