Medical AI tools are growing, but are they being tested properly?

Experts argue that current tests are distracting and new ones are needed

A medical caduceus with scales, silhouetted against a dimly lit, tan background

Measuring progress in health care AI performance relies heavily on question-answer tests, researchers argue, and not enough on evaluating real-world medical tasks.

doomu/Getty Images

Artificial intelligence algorithms are being built into almost all aspects of health care. They’re integrated into breast cancer screenings, clinical note-taking, health insurance management and even phone and computer apps to create virtual nurses and transcribe doctor-patient conversations.