机器学习在情绪障碍治疗反应预测中的应用：一项系统综述和荟萃分析

IF 12.2 1区心理学 Q1 PSYCHOLOGY, CLINICAL

Clinical Psychology Review Pub Date : 2025-05-22 DOI:10.1016/j.cpr.2025.102593

Joshua Curtiss , Christopher DiPietro

{"title":"机器学习在情绪障碍治疗反应预测中的应用：一项系统综述和荟萃分析","authors":"Joshua Curtiss , Christopher DiPietro","doi":"10.1016/j.cpr.2025.102593","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Emotional disorders such as depression and anxiety affect millions globally and pose a significant burden on public health. Personalized treatment approaches using machine learning (ML) to predict treatment response could revolutionize treatment strategies. However, there is limited evidence as to whether ML is successful in predicting treatment outcomes. This meta-analysis aims to evaluate the accuracy of ML algorithms in predicting binary treatment response (responder vs. non-responder) to evidence-based psychotherapies, pharmacotherapies, and other treatments for emotional disorders, and to examine moderators of prediction accuracy.</div></div><div><h3>Methods</h3><div>Following PRISMA guidelines, a comprehensive literature search was conducted across PubMed and PsycINFO from January 1st, 2010 to March 27th, 2025. Studies were included if they used ML methods to predict treatment response in patients with emotional disorders. Data were extracted on sample size, type of treatment, predictors used, ML methods, and prediction accuracy. Meta-analytic techniques were used to synthesize findings and identify moderators of prediction accuracy.</div></div><div><h3>Results</h3><div>Out of 3816 non-duplicate records, 155 studies met inclusion criteria. The overall mean prediction accuracy was 0.76 (95 % CI: 0.74–0.78), and the mean area under the curve was 0.80 indicating good discrimination. The average sensitivity and specificity were 0.73 and 0.75, respectively. Moderator analyses indicated that studies using more robust cross-validation procedures exhibited higher prediction accuracy. Neuroimaging data as predictors were associated with higher accuracy compared to clinical and demographic data. Moreover, results indicated that studies with larger responder rates, as well as those that did not correct for imbalances in outcome rates, were associated with higher prediction accuracy.</div></div><div><h3>Conclusions</h3><div>ML methods show promise in predicting treatment response for emotional disorders, with varying degrees of accuracy depending on the type of predictors used and the rigor of methodological procedures implemented. Future research should focus on improving methodological integrity and exploring the integration of multimodal data to enhance prediction accuracy.</div></div>","PeriodicalId":48458,"journal":{"name":"Clinical Psychology Review","volume":"120 ","pages":"Article 102593"},"PeriodicalIF":12.2000,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning in the prediction of treatment response for emotional disorders: A systematic review and meta-analysis\",\"authors\":\"Joshua Curtiss , Christopher DiPietro\",\"doi\":\"10.1016/j.cpr.2025.102593\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Emotional disorders such as depression and anxiety affect millions globally and pose a significant burden on public health. Personalized treatment approaches using machine learning (ML) to predict treatment response could revolutionize treatment strategies. However, there is limited evidence as to whether ML is successful in predicting treatment outcomes. This meta-analysis aims to evaluate the accuracy of ML algorithms in predicting binary treatment response (responder vs. non-responder) to evidence-based psychotherapies, pharmacotherapies, and other treatments for emotional disorders, and to examine moderators of prediction accuracy.</div></div><div><h3>Methods</h3><div>Following PRISMA guidelines, a comprehensive literature search was conducted across PubMed and PsycINFO from January 1st, 2010 to March 27th, 2025. Studies were included if they used ML methods to predict treatment response in patients with emotional disorders. Data were extracted on sample size, type of treatment, predictors used, ML methods, and prediction accuracy. Meta-analytic techniques were used to synthesize findings and identify moderators of prediction accuracy.</div></div><div><h3>Results</h3><div>Out of 3816 non-duplicate records, 155 studies met inclusion criteria. The overall mean prediction accuracy was 0.76 (95 % CI: 0.74–0.78), and the mean area under the curve was 0.80 indicating good discrimination. The average sensitivity and specificity were 0.73 and 0.75, respectively. Moderator analyses indicated that studies using more robust cross-validation procedures exhibited higher prediction accuracy. Neuroimaging data as predictors were associated with higher accuracy compared to clinical and demographic data. Moreover, results indicated that studies with larger responder rates, as well as those that did not correct for imbalances in outcome rates, were associated with higher prediction accuracy.</div></div><div><h3>Conclusions</h3><div>ML methods show promise in predicting treatment response for emotional disorders, with varying degrees of accuracy depending on the type of predictors used and the rigor of methodological procedures implemented. Future research should focus on improving methodological integrity and exploring the integration of multimodal data to enhance prediction accuracy.</div></div>\",\"PeriodicalId\":48458,\"journal\":{\"name\":\"Clinical Psychology Review\",\"volume\":\"120 \",\"pages\":\"Article 102593\"},\"PeriodicalIF\":12.2000,\"publicationDate\":\"2025-05-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Clinical Psychology Review\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0272735825000595\",\"RegionNum\":1,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PSYCHOLOGY, CLINICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Psychology Review","FirstCategoryId":"102","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0272735825000595","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY, CLINICAL","Score":null,"Total":0}

引用次数: 0

摘要

抑郁和焦虑等情绪障碍影响着全球数百万人，并对公共卫生构成重大负担。使用机器学习（ML）预测治疗反应的个性化治疗方法可能会彻底改变治疗策略。然而，关于ML是否能成功预测治疗结果的证据有限。本荟萃分析旨在评估ML算法在预测基于证据的心理治疗、药物治疗和其他情绪障碍治疗的二元治疗反应（反应者与无反应者）方面的准确性，并检查预测准确性的调节因子。方法按照PRISMA指南，对2010年1月1日至2025年3月27日的PubMed和PsycINFO进行全面的文献检索。如果研究使用ML方法预测情绪障碍患者的治疗反应，则纳入研究。从样本量、治疗类型、使用的预测因子、ML方法和预测准确性等方面提取数据。荟萃分析技术用于综合研究结果并确定预测准确性的调节因子。结果3816份非重复记录中，155项研究符合纳入标准。总体平均预测准确率为0.76 (95% CI: 0.74-0.78)，平均曲线下面积为0.80，判别良好。平均敏感性和特异性分别为0.73和0.75。调节分析表明，使用更稳健的交叉验证程序的研究显示出更高的预测准确性。与临床和人口统计数据相比，神经影像学数据作为预测指标具有更高的准确性。此外，结果表明，应答率较高的研究，以及那些没有纠正结果率不平衡的研究，与较高的预测准确性相关。结论sml方法有望预测情绪障碍的治疗反应，根据所使用的预测因子的类型和方法程序的严谨性，具有不同程度的准确性。未来的研究应注重提高方法的完整性，探索多模态数据的整合，以提高预测精度。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Machine learning in the prediction of treatment response for emotional disorders: A systematic review and meta-analysis

Background

Emotional disorders such as depression and anxiety affect millions globally and pose a significant burden on public health. Personalized treatment approaches using machine learning (ML) to predict treatment response could revolutionize treatment strategies. However, there is limited evidence as to whether ML is successful in predicting treatment outcomes. This meta-analysis aims to evaluate the accuracy of ML algorithms in predicting binary treatment response (responder vs. non-responder) to evidence-based psychotherapies, pharmacotherapies, and other treatments for emotional disorders, and to examine moderators of prediction accuracy.

Methods

Following PRISMA guidelines, a comprehensive literature search was conducted across PubMed and PsycINFO from January 1st, 2010 to March 27th, 2025. Studies were included if they used ML methods to predict treatment response in patients with emotional disorders. Data were extracted on sample size, type of treatment, predictors used, ML methods, and prediction accuracy. Meta-analytic techniques were used to synthesize findings and identify moderators of prediction accuracy.

Results

Out of 3816 non-duplicate records, 155 studies met inclusion criteria. The overall mean prediction accuracy was 0.76 (95 % CI: 0.74–0.78), and the mean area under the curve was 0.80 indicating good discrimination. The average sensitivity and specificity were 0.73 and 0.75, respectively. Moderator analyses indicated that studies using more robust cross-validation procedures exhibited higher prediction accuracy. Neuroimaging data as predictors were associated with higher accuracy compared to clinical and demographic data. Moreover, results indicated that studies with larger responder rates, as well as those that did not correct for imbalances in outcome rates, were associated with higher prediction accuracy.

Conclusions

ML methods show promise in predicting treatment response for emotional disorders, with varying degrees of accuracy depending on the type of predictors used and the rigor of methodological procedures implemented. Future research should focus on improving methodological integrity and exploring the integration of multimodal data to enhance prediction accuracy.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Clinical Psychology Review PSYCHOLOGY, CLINICAL-

CiteScore

23.10

自引率

1.60%

发文量

期刊介绍： Clinical Psychology Review serves as a platform for substantial reviews addressing pertinent topics in clinical psychology. Encompassing a spectrum of issues, from psychopathology to behavior therapy, cognition to cognitive therapies, behavioral medicine to community mental health, assessment, and child development, the journal seeks cutting-edge papers that significantly contribute to advancing the science and/or practice of clinical psychology. While maintaining a primary focus on topics directly related to clinical psychology, the journal occasionally features reviews on psychophysiology, learning therapy, experimental psychopathology, and social psychology, provided they demonstrate a clear connection to research or practice in clinical psychology. Integrative literature reviews and summaries of innovative ongoing clinical research programs find a place within its pages. However, reports on individual research studies and theoretical treatises or clinical guides lacking an empirical base are deemed inappropriate for publication.