Qiyi Wang, Jiale Zhong, Kai Qi, Hanshuo Bao, Yang Wang, Shuai Guo, Aiguo Chen
Mental health disorders impose a substantial global burden, while access to care remains constrained. AI-based chatbots have emerged as scalable digital interventions, yet existing evidence is limited by heterogeneous intervention types and methodological shortcomings. This study aimed to evaluate the effects of AI-based chatbot interventions on mental health using a three-level meta-analytic approach. A systematic review was conducted across seven databases, yielding 16 eligible studies and 67 effect sizes. A three-level random-effects meta-analysis was performed to account for dependency among multiple outcomes within studies. AI-based chatbot interventions were associated with a statistically significant small-to-moderate improvement in mental health outcomes (Hedges' g = 0.47, 95% CI [0.18, 0.77]). Leave-one-out sensitivity analyses indicated that the pooled effect estimate remained stable. No significant moderators were identified, although significant improvements were observed across depression, anxiety, loneliness, affect, and sleep. Most studies presented some risk of bias, and overall evidence certainty was low. Overall, AI-based chatbot interventions were associated with modest improvements across multiple mental health domains. These findings should be interpreted as reflecting the effects of the interventions as integrated packages rather than the isolated therapeutic contribution of AI technology.