Artificial Intelligence–Based Psychotherapeutic Intervention on Psychological Outcomes: A Meta-Analysis and Meta-Regression

Abstract

Background: Artificial intelligence (AI)–based psychotherapeutic interventions may bring a new and viable approach to expanding psychiatric care. However, evidence of their effectiveness remains scarce. We evaluated the efficacy of AI-based psychotherapeutic interventions on depressive, anxiety, and stress symptoms at postintervention and follow-up assessments.

Methods: A three-step comprehensive search via nine electronic databases (PubMed, Embase, CINAHL, Cochrane Library, Scopus, IEEE Xplore, Web of Science, PsycINFO, and ProQuest Dissertations and Theses) was performed.

Results: Thirty randomized controlled trials (RCTs) in 31 publications involving 6100 participants from nine countries were included. The majority (79.1%) of trials with intention-to-treat analysis but less than half (48.6%) of trials with perprotocol analysis were graded as low risk. Meta-analyses showed that interventions significantly reduced depressive symptoms at the postintervention assessment (t = −4.40, p = 0.001) with medium effect size (g = −0.54, 95% CI: −0.79 to −0.29) and at 6–12 months of assessment (t = −3.14, p < 0.016) with small effect size (g = −0.23, 95% CI: −0.40 to −0.06) in comparison with comparators. Our subgroup analyses revealed that the depressed participants had a significantly larger effect size in reducing depressive symptoms than participants with stress and other conditions. At postintervention and follow-up assessments, we discovered that AI-based psychotherapeutic interventions did not significantly alter anxiety, stress, and the total scores of depressive, anxiety, and stress symptoms in comparison to comparators. The random-effects univariate meta-regression did not identify any significant covariates for depressive and anxiety symptoms at postintervention. The certainty of evidence ranged between moderate and very low.

Conclusions: AI-based psychotherapeutic interventions can be used in addition to usual treatments for reducing depressive symptoms. Well-designed RCTs with long-term follow-up data are warranted.

Trial Registration: CRD42022330228