Can AI detect depression based on the way a patient talks?

Medical Economics January 17, 2025
Austin Littrell

Key Takeaways

• The USPSTF recommended depression screening in adults, but only 4.1% of primary care patients are screened.
• Kintsugi Voice Biomarker Technology uses machine learning to analyze speech, identifying depression with 71% sensitivity and 74% specificity.
• The tool flagged 20% of cases as uncertain, suggesting further clinical evaluation.
• It can support primary care screenings without adding burden, but further studies are needed to assess workflow integration and other influencing conditions.

A machine learning tool designed to analyze vocal patterns for signs of depression successfully identified depression in 71% of patients who had it.

In 2016, the U.S. Preventive Services Task Force (USPSTF) recommended screening for depression in the general adult population when adequate systems are in place to...

Today's Sponsors

Today's Sponsor