Mental health

AI may detect depression just from your voice

an old-fashioned cutaway illustration of a person speaking
Illustration: Sarah Grillo/Axios

During a conversation, humans can grasp a friend's mood or intent by relying on subtle vocal cues or word choice. Now, researchers at MIT say they have developed an algorithm that can detect if the friend is depressed, one of the most widely suffered — and often undiagnosed — conditions in the U.S.

Why it matters: About 1 in 15 adults — 37 million Americans — experience major depressive episodes, but many times go untreated.

Jail can be a death sentence for the mentally ill

The Pueblo County Detention Center in Colorado. Photo: Aaron Ontiveroz/The Denver Post via Getty Images

When the U.S. started shutting down large institutional mental health hospitals in the 1960s — facilities that had become infamous for their poor conditions and subpar treatment — they didn't actually stop institutionalizing people with mental illness. They just started doing it in jails and prisons instead.

The big picture: Nearly half of the roughly 740,000 people being held in American jails have been diagnosed with a mental disorder and about a quarter are in "serious psychological distress," according to a new and impressive investigation by the Virginian-Pilot and Marquette University.