It’s not easy to get depression-detecting AI through the FDA

The Verge / 4/3/2026

💬 OpinionSignals & Early TrendsIndustry & Market Moves

Key Points

  • The California startup Kintsugi, which spent seven years developing AI that detects depression and anxiety from speech, is shutting down after it failed to obtain timely FDA clearance.
  • The company will release most of its technology as open-source, making key components available to researchers and developers.
  • Kintsugi’s approach focuses on prosody and speech delivery (how something is said) rather than the content itself, aiming to complement mental-health assessments that currently rely on questionnaires and clinical interviews.
  • The article notes potential reuse of the underlying techniques outside healthcare, including detecting deepfake audio.
  • The case highlights how challenging FDA pathways can be for clinical AI tools compared with conventional physical-medicine diagnostic devices.
A vintage computer on a background of 1s and 0s with a brain on the screen representing AI

For the past seven years, the California-based startup Kintsugi has been developing AI designed to detect signs of depression and anxiety from a person's speech. But after failing to secure FDA clearance in time, the company is shutting down and releasing most of its technology as open-source. Some elements may even find a second life beyond healthcare, like detecting deepfake audio.

Mental health assessments still largely rely on patient questionnaires and clinical interviews, rather than the lab tests or scans common in physical medicine. Instead of focusing on what someone is saying, Kintsugi's software analyzes how it is being said. Th …

Read the full story at The Verge.