The Efficacy of Rule-Based Versus Large Language Model-Based Chatbots in Alleviating Symptoms of Depression and Anxiety: Systematic Review and Meta-Analysis.

J Med Internet Res · 2025 · PMC12677872 · PMID 41343858

Europe PMC DOI

hedged sentences

0.1700

closest p · 3.4× alpha

0.1700

boldest claim

The sentences

did not reach statistical significanceP =.17not close (p > 0.1)

However, the effect of LLM-based interventions did not reach statistical significance ( g =0.407; 95% CI −0.734 to 1.550; P =.17), which may be limited by sample size or heterogeneity.

also in 111,027 other papers

a clear trendno p-value reported

Existing literature shows a clear trend of regional concentration among research participants, with the United States and China accounting for the highest proportion (67% combined).

also in 19,460 other papers

a significant trendno p-value reported

However, meta-regression results indicate that their intervention effectiveness does not show a significant trend over time.

also in 9,775 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.