Predicting Treatment Response of rTMS in Major Depressive Disorder Using a Explainable Machine Learning Model Based on EEG and Clinical Features.

Biological psychiatry. Cognitive neuroscience and neuroimaging Pub Date : 2025-02-18 DOI:10.1016/j.bpsc.2025.02.002

Zongya Zhao, Xiangying Ran, Yanxiang Niu, Mengyue Qiu, Shiyang Lv, Mingjie Zhu, Junming Wang, Mingcai Li, Zhixian Gao, Chang Wang, Yongtao Xu, Wu Ren, Xuezhi Zhou, Xiaofeng Fan, Jinggui Song, Mingchao Qi, Yi Yu

{"title":"Predicting Treatment Response of rTMS in Major Depressive Disorder Using a Explainable Machine Learning Model Based on EEG and Clinical Features.","authors":"Zongya Zhao, Xiangying Ran, Yanxiang Niu, Mengyue Qiu, Shiyang Lv, Mingjie Zhu, Junming Wang, Mingcai Li, Zhixian Gao, Chang Wang, Yongtao Xu, Wu Ren, Xuezhi Zhou, Xiaofeng Fan, Jinggui Song, Mingchao Qi, Yi Yu","doi":"10.1016/j.bpsc.2025.02.002","DOIUrl":null,"url":null,"abstract":"Objective: Major Depressive Disorder (MDD) is highly heterogeneous in response to rTMS, and identifying predictive biomarkers is essential for personalized treatment. However, current researches either only uses EEG or clinical features, lacks interpretability, or have small sample sizes.Method: This study included 74 MDD patients who responded (Responder) and 43 MDD who did not respond (NonResponder) to rTMS. Eight baseline EEG metrics and clinical features were sent to seven machine learning models to classify Responder from NonResponder. SHAP was used to interpret feature contributions.Result: Combining phase locking value (PLV) and clinical features with Support Vector Machine (SVM) achieved optimal classification performance (accuracy=97.33%). SHAP revealed that delta and beta band functional connectivity (F3-P7, F3-P4, P3-P8, T7-Cz) significantly influenced predictions and differed between groups.Conclusion: This study developed an explainable predictive framework to predict rTMS response in MDD, enhancing the accuracy of rTMS response prediction and supporting personalized treatment in MDD.","PeriodicalId":93900,"journal":{"name":"Biological psychiatry. Cognitive neuroscience and neuroimaging","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biological psychiatry. Cognitive neuroscience and neuroimaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1016/j.bpsc.2025.02.002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: Major Depressive Disorder (MDD) is highly heterogeneous in response to rTMS, and identifying predictive biomarkers is essential for personalized treatment. However, current researches either only uses EEG or clinical features, lacks interpretability, or have small sample sizes.

Method: This study included 74 MDD patients who responded (Responder) and 43 MDD who did not respond (NonResponder) to rTMS. Eight baseline EEG metrics and clinical features were sent to seven machine learning models to classify Responder from NonResponder. SHAP was used to interpret feature contributions.

Result: Combining phase locking value (PLV) and clinical features with Support Vector Machine (SVM) achieved optimal classification performance (accuracy=97.33%). SHAP revealed that delta and beta band functional connectivity (F3-P7, F3-P4, P3-P8, T7-Cz) significantly influenced predictions and differed between groups.

Conclusion: This study developed an explainable predictive framework to predict rTMS response in MDD, enhancing the accuracy of rTMS response prediction and supporting personalized treatment in MDD.

查看原文本刊更多论文

基于脑电图和临床特征的可解释机器学习模型预测重性抑郁症rTMS治疗反应

目的：重度抑郁症（MDD）对rTMS的反应具有高度异质性，识别预测性生物标志物对于个性化治疗至关重要。然而，目前的研究要么只使用脑电图或临床特征，要么缺乏可解释性，要么样本量小。方法：本研究纳入74例对rTMS有反应（Responder）的MDD患者和43例对rTMS无反应（NonResponder）的MDD患者。8个基线EEG指标和临床特征被发送到7个机器学习模型中，以区分响应者和非响应者。SHAP用于解释特征贡献。结果：相锁值（PLV）与临床特征相结合，支持向量机（SVM）的分类效果最佳，准确率为97.33%。SHAP结果显示，δ和β带功能连通性（F3-P7、F3-P4、P3-P8、T7-Cz）显著影响预测结果，且组间存在差异。结论：本研究建立了一个可解释的预测框架来预测MDD患者的rTMS反应，提高了rTMS反应预测的准确性，为MDD患者的个性化治疗提供了支持。

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

Biological psychiatry. Cognitive neuroscience and neuroimaging

自引率

0.00%

发文量