AI-assisted interviews increase the accuracy of diagnosing mental illness

A new study shows that an AI assistant can conduct assessment interviews with patients with greater accuracy than the rating scales used in healthcare today. In the study, 303 participants were interviewed by AI assistant Alba, who then suggested possible psychiatric diagnoses.

In addition to being interviewed by an AI assistant, participants also had to fill out standardized rating scales for the nine most common psychiatric diagnoses. The results showed that the AI ​​assistant’s assessments were more consistent with participants’ actual diagnoses than the rating scales.

The study included people with confirmed diagnoses for conditions such as depression, anxiety, obsessive-compulsive disorder, PTSD, ADHD, autism, eating disorders, substance use disorders and bipolar disorder, as well as a control group. All participants had an online interview with the AI ​​assistant Alba, in which 15-20 open-ended questions about their mental health were asked and then…