METHODS: A systematic search was executed across multiple databases, including PubMed, Cochrane Library, Web of Science, PsycINFO, and Embase on April 4th, 2024. The effect size of treatment efficacy was calculated using the standardized mean difference (Hedge\'s g). Quality assessment measures were implemented to ensure trial\'s quality.
RESULTS: In our analysis of 18 randomized controlled trials involving 3477 participants, we observed noteworthy improvements in depression (g = -0.26, 95 % CI = -0.34, -0.17) and anxiety (g = -0.19, 95 % CI = -0.29, -0.09) symptoms. The most significant benefits were evident after 8 weeks of treatment. However, at the three-month follow-up, no substantial effects were detected for either condition.
CONCLUSIONS: Several limitations should be considered. These include the lack of diversity in the study populations, variations in chatbot design, and the use of different psychotherapeutic approaches. These factors may limit the generalizability of our findings.
CONCLUSIONS: This meta-analysis highlights the promising role of AI-based chatbot interventions in alleviating depressive and anxiety symptoms among adults. Our results indicate that these interventions can yield substantial improvements over a relatively brief treatment period.
方法:在多个数据库中执行系统搜索,包括PubMed,科克伦图书馆,WebofScience,PsycINFO,4月4日Embase,2024.使用标准化平均差(Hedge'sg)计算治疗功效的效应大小。实施质量评估措施,确保试验质量。
结果:在我们对包括3477名参与者的18项随机对照试验的分析中,我们观察到抑郁(g=-0.26,95%CI=-0.34,-0.17)和焦虑(g=-0.19,95%CI=-0.29,-0.09)症状显著改善.最显著的益处在治疗8周后是明显的。然而,在三个月的随访中,两种情况均未发现实质性影响.
结论:应该考虑一些限制。这些包括研究人群缺乏多样性,聊天机器人设计的变化,以及使用不同的心理治疗方法。这些因素可能会限制我们研究结果的普遍性。
结论:这项荟萃分析强调了基于AI的聊天机器人干预在缓解成人抑郁和焦虑症状方面的有希望的作用。我们的结果表明,这些干预措施可以在相对短暂的治疗期内产生实质性的改善。