AI system detects PTSD in children through facial expressions without breaching privacy

A research team at the University of South Florida has developed a cutting-edge AI-powered system capable of identifying Post-Traumatic Stress Disorder (PTSD) in children by analyzing their facial micro-expressions during therapy sessions, all while ensuring their privacy is not violated.

The system processed more than 185,000 video frames from interviews involving children with psychologists and parents. The results revealed clear expression patterns in children with PTSD, especially during sessions with mental health professionals—confirming existing psychological findings about the ease of opening up to trained experts.

Researchers aim to expand testing to include broader age groups and cultural backgrounds. The technology could soon be used to support therapists during diagnosis, reducing the need for stressful and repeated sessions.

Dr. Sean Canavan, one of the study’s supervisors, noted:

« If this system proves reliable on a larger scale, it could reshape the future of diagnosing childhood mental health disorders. »