Therapeutic Interaction Features of AI Chatbots in Depression Interventions: Systematic Review and Meta-Analysis.

J Med Internet Res · 2026 · PMC13318397 · PMID 42379144

Europe PMC DOI

hedged sentences

0.1000

closest p · 2.0× alpha

0.1000

boldest claim

The sentences

failed to reach significanceP =.10so close (0.05 < p ≤ 0.1)

For dialogue depth, the high group was significantly associated with better outcomes (SMD=−0.35, 95% CI −0.61 to −0.10; P =.007; I 2=0%), while the low group failed to reach significance and showed substantial heterogeneity (SMD=−0.54, 95% CI −1.20 to 0.11; P =.10; I 2=97.0%).

also in 2,311 other papers

did not reach statistical significanceno p-value reported

Rule-based chatbots showed a nonsignificant pooled effect (OR 0.95, 95% CI 0.36‐2.51), while NLP/ML-based chatbots also did not reach statistical significance (OR 1.87, 95% CI 0.22‐16.28).

also in 75,868 other papers

a favorable trendno p-value reported

The results showed a favorable trend for depressive symptom reduction, but the overall evidence remained uncertain.

also in 1,005 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.