Conversational AI platform provides Modest Mental Health Benefits in Students with Anxiety and Depression: JAMA
Israel: Researchers have found in a randomized trial in university students that a conversational AI platform produced modest improvements in anxiety and depression over 12 weeks, with self-reported benefits and no serious adverse effects. The findings were published in JAMA Network Open by Anat Shoshani from the Baruch Ivcher School of Psychology, Reichman University, Israel, and colleagues.
The growing burden of mental health disorders worldwide has highlighted the need for accessible and scalable interventions. Conversational artificial intelligence (AI) platforms are emerging as potential tools to bridge this gap by offering personalized, on-demand psychological support. However, robust clinical evidence evaluating their effectiveness and underlying mechanisms has remained limited until now.
To address this, the researchers conducted a three-arm randomized clinical trial involving 995 university students experiencing psychological distress. Participants were assigned to one of three groups: a 12-week AI-based conversational platform, face-to-face group therapy, or a waiting list control. The study evaluated key mental health outcomes, including anxiety, depression, posttraumatic stress disorder (PTSD), well-being, and life satisfaction at the end of the intervention period.
The trial revealed the following findings:
- The AI-based intervention resulted in greater reductions in anxiety compared to both group therapy and the control group.
- Improvements in depressive symptoms were more pronounced in the AI group compared to the waiting list control.
- No significant differences were observed between groups for posttraumatic stress disorder (PTSD) symptoms.
- Participants using the AI platform reported notable improvements in overall well-being.
- Life satisfaction scores were higher in the AI group compared to both comparison groups.
- The findings suggest the AI intervention may provide broader psychological benefits beyond symptom reduction.
- A stronger perceived digital therapeutic alliance was significantly associated with higher user engagement.
- Greater perceived connection with the AI platform was linked to improved psychological outcomes.
- Participants perceived the AI as having human-like therapeutic qualities such as empathy, warmth, and competence.
Despite these encouraging findings, the study has several limitations. Outcomes were based on self-reported measures rather than clinician assessments, which may affect the objectivity of results. Additionally, participant dropout at the three-month follow-up was relatively high, potentially influencing long-term outcome estimates. The study also did not fully assess the impact on healthcare utilization or long-term cost-effectiveness.
Overall, the findings suggest that conversational AI platforms can provide meaningful, albeit modest, improvements in mental health outcomes among young adults. While not a replacement for conventional therapy, such tools may serve as valuable adjuncts or early intervention options within broader mental health care systems. The authors emphasize the need for further research to explore long-term benefits, safety, and optimal integration into existing care frameworks.
Reference:
Shoshani A, Gurfinkel B, Kor A, et al. Efficacy of a Conversational AI Agent for Psychiatric Symptoms and Digital Therapeutic Alliance: A Randomized Clinical Trial. JAMA Netw Open. 2026;9(4):e266713. doi:10.1001/jamanetworkopen.2026.6713
Next Story