Effectiveness of Chatbots in Mental Health Screening and Assessment: Systematic Review.
Isabel Morales Gil, Inés Marti-Estevez, Sandra Doval et al.
✦ AI-curated · Sources linked
In 30 seconds
This systematic review evaluated the effectiveness of chatbots and AI-based conversational agents for mental health screening and assessment in adults. Eighteen studies were analyzed, revealing that generative models achieved sensitivities of 0.84 to 0.93 and specificities of 0.80 to 0.96 for depression and anxiety. The review highlights the potential of these technologies in improving access to mental health evaluations.
Key findings
- Rule-based chatbots showed high reliability with Cronbach α >0.85.
- Generative models achieved sensitivities of 0.84 to 0.93 for depression and anxiety.
- Hybrid approaches had an F1-score of 92.1% for cognitive impairment.
- User satisfaction was reported at ≥70% across most studies.
Why it matters
The findings suggest that chatbots and AI can enhance mental health screening and assessment, potentially addressing barriers to access. Their integration into clinical practice could improve early detection and intervention for mental health disorders.
What to keep in mind
Methodological quality varied among studies, with a moderate risk of bias in critical dimensions.