Chatbot-Delivered Interventions for Improving Mental Health Among Young People: A Systematic Review and Meta-Analysis.
Jiaying Li, Yan Li, Yule Hu and 4 others
PMID 40662463WHAT IT FOUND
Chatbot interventions for young people reduced psychological distress compared with controls, but did not significantly improve well-being.
Effects varied by platform and chatbot type, and many studies had high risk of bias.
Key findings
01Compared with control conditions, chatbot-delivered interventions produced a statistically significant reduction in psychological distress among young people.
02Chatbot-delivered interventions did not produce a statistically significant improvement in psychological well-being.
03Participants consistently reported positive satisfaction and acceptance, but only 14 studies integrated safeguarding measures.
STILL TO COME
How it was doneWhat they foundWhat it means for RNs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Most included studies were small and many had no control group. Only 11 trials had usable outcome data for the meta-analysis. Most studies used self-reported outcomes without assessor blinding, which raised risk of bias. The included samples were mostly nonclinical and from educational settings in high-income countries, so the results may not apply to patients in clinical or low-resource settings. Long-term effects were not examined, and only 14 studies integrated safeguarding measures.
Declared interests
The authors declare no conflicts of interest.
The easy way to misread this
Do not read this as proof that chatbots improve young people's mental health overall. The distress benefit was small and the well-being result was not significant, and the evidence was heterogeneous and at risk of bias.