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

IF 3.3 2区医学 Q1 PSYCHIATRY

Depression and Anxiety Pub Date : 2025-01-27 DOI:10.1155/da/8930012

Ying Lau, Wei How Darryl Ang, Wen Wei Ang, Patrick Cheong-Iao Pang, Sai Ho Wong, Kin Sun Chan

{"title":"Artificial Intelligence–Based Psychotherapeutic Intervention on Psychological Outcomes: A Meta-Analysis and Meta-Regression","authors":"Ying Lau, Wei How Darryl Ang, Wen Wei Ang, Patrick Cheong-Iao Pang, Sai Ho Wong, Kin Sun Chan","doi":"10.1155/da/8930012","DOIUrl":null,"url":null,"abstract":"<div>\n 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.\n 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.\n 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.\n 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.\n Trial Registration: CRD42022330228\n </div>","PeriodicalId":55179,"journal":{"name":"Depression and Anxiety","volume":"2025 1","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/da/8930012","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Depression and Anxiety","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1155/da/8930012","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHIATRY","Score":null,"Total":0}

引用次数: 0

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

Abstract Image

查看原文本刊更多论文

基于人工智能的心理治疗干预对心理结果的影响：meta分析和meta回归

背景：基于人工智能（AI）的心理治疗干预可能为扩大精神病学护理带来新的可行方法。然而，证明其有效性的证据仍然很少。我们在干预后和随访评估中评估了基于人工智能的心理治疗干预对抑郁、焦虑和压力症状的疗效。方法：通过PubMed、Embase、CINAHL、Cochrane Library、Scopus、IEEE Xplore、Web of Science、PsycINFO、ProQuest等9个电子数据库进行三步综合检索。结果：纳入31篇出版物的30项随机对照试验（rct），涉及来自9个国家的6100名受试者。大多数（79.1%）有意向治疗分析的试验，但不到一半（48.6%）有超方案分析的试验被评为低风险。荟萃分析显示，干预措施在干预后评估时显著降低抑郁症状（t = - 4.40, p = 0.001），具有中等效应（g = - 0.54, 95% CI: - 0.79至- 0.29），在评估后6-12个月(t = - 3.14, p <；0.016)，效应值较小（g = - 0.23, 95% CI: - 0.40至- 0.06）。我们的亚组分析显示，抑郁的参与者在减轻抑郁症状方面比有压力和其他条件的参与者有显著更大的效应。在干预后和随访评估中，我们发现与比较者相比，基于人工智能的心理治疗干预并没有显著改变焦虑、压力以及抑郁、焦虑和压力症状的总分。随机效应单变量荟萃回归未发现干预后抑郁和焦虑症状的任何显著协变量。证据的确定性介于中等和极低之间。结论：基于人工智能的心理治疗干预可以在常规治疗之外用于减轻抑郁症状。有长期随访数据的精心设计的随机对照试验是必要的。试验注册：CRD42022330228

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Depression and Anxiety 医学-精神病学

CiteScore

15.00

自引率

1.40%

发文量

审稿时长

4-8 weeks

期刊介绍： Depression and Anxiety is a scientific journal that focuses on the study of mood and anxiety disorders, as well as related phenomena in humans. The journal is dedicated to publishing high-quality research and review articles that contribute to the understanding and treatment of these conditions. The journal places a particular emphasis on articles that contribute to the clinical evaluation and care of individuals affected by mood and anxiety disorders. It prioritizes the publication of treatment-related research and review papers, as well as those that present novel findings that can directly impact clinical practice. The journal's goal is to advance the field by disseminating knowledge that can lead to better diagnosis, treatment, and management of these disorders, ultimately improving the quality of life for those who suffer from them.