By providing plausible label maps for one medical image, the Tyche machine-learning model could help clinicians and researchers capture crucial information.

The low-cost hardware outperforms state-of-the-art versions and could someday enable an affordable, in-home device for health monitoring.

Applied during endoscopic procedures, GastroShield could help prevent complications such as bleeding and leakage from weakened gastrointestinal tissues.

Dermatologists and general practitioners are somewhat less accurate in diagnosing disease in darker skin, a new study finds. Used correctly, AI may be able to help.

A new MIT study identifies six systemic factors contributing to patient hazards in laboratory diagnostics tests.

Study of rigorous trial shows mixed results, suggests need to keep examining how nutrition can combat a pervasive disease.

By reevaluating existing data, researchers find the procedure is even more valuable than consensus had indicated.

The one-step fabrication process rapidly produces miniature chemical reactors that could be used to detect diseases or analyze substances.

MIT researchers develop a customized onboarding process that helps a human learn when a model’s advice is trustworthy.

MIT and MGH researchers design a local, gel-based drug-delivery platform that may provoke a system-wide immune response to metastatic tumors.