Contrary to common understanding, sepsis is not a one-size-afflicts-all condition. It’s a set of many, and each can be placed into one of four key subcategories—i.e., phenotypes—such that, going forward, stricken patients could receive tailored treatments.

A Colorado teenager has won $75,000 for his machine learning and computer vision project that helps orthopedic surgeons improve the accuracy of screw placement during spinal surgery.

People who struggle to get a good night’s sleep and seek medical help for the problem are producing mega data on things like eye movement, breathing, brain activity and restless legs. Which is to say sleep medicine is as ripe as any field in healthcare for help from AI.

A natural language processing algorithm has achieved 90% precision in automatically spotting signs of social isolation in cancer patients by “reading” clinical notes in a hospital’s electronic health record.

A San Jose-based company focused on machine learning for care optimization, Health[at]Scale, has raised $16 million in a Series A funding round, with Optum as its sole investor.

Academic and popular writings on the use of “embodied” AI in mental healthcare are piling up fast. But where’s the guidance for psychiatrists, psychotherapists and clinical social workers looking to use robots, avatars and chatbots with real patients?

Instead of Googling symptoms to when feeling an ailment and landing on an incorrect diagnosis, AI could soon provide accurate diagnosis without needing to go to a doctor’s office.