A multimodal approach to depression diagnosis: insights from machine learning algorithm development in primary care.

IF 3.5 3区 医学 Q1 CLINICAL NEUROLOGY European Archives of Psychiatry and Clinical Neuroscience Pub Date : 2025-03-10 DOI:10.1007/s00406-025-01990-5
Julia Eder, Mark Sen Dong, Melanie Wöhler, Maria S Simon, Catherine Glocker, Lisa Pfeiffer, Richard Gaus, Johannes Wolf, Kadir Mestan, Helmut Krcmar, Nikolaos Koutsouleris, Antonius Schneider, Jochen Gensichen, Richard Musil, Peter Falkai
{"title":"A multimodal approach to depression diagnosis: insights from machine learning algorithm development in primary care.","authors":"Julia Eder, Mark Sen Dong, Melanie Wöhler, Maria S Simon, Catherine Glocker, Lisa Pfeiffer, Richard Gaus, Johannes Wolf, Kadir Mestan, Helmut Krcmar, Nikolaos Koutsouleris, Antonius Schneider, Jochen Gensichen, Richard Musil, Peter Falkai","doi":"10.1007/s00406-025-01990-5","DOIUrl":null,"url":null,"abstract":"<p><p>General practitioners play an essential role in identifying depression and are often the first point of contact for patients. Current diagnostic tools, such as the Patient Health Questionnaire-9, provide initial screening but might lead to false positives. To address this, we developed a two-step machine learning model called Clinical 15, trained on a cohort of 581 participants using a nested cross-validation framework. The model integrates self-reported data from validated questionnaires within a study sample of patients presenting to general practitioners. Clinical 15 demonstrated a balanced accuracy of 88.2% and incorporates a traffic light system: green for healthy, red for depression, and yellow for uncertain cases. Gaussian mixture model clustering identified four depression subtypes, including an Immuno-Metabolic cluster characterized by obesity, low-grade inflammation, autonomic nervous system dysregulation, and reduced physical activity. The Clinical 15 algorithm identified all patients within the immuno-metabolic cluster as depressed, although 22.2% (30.8% across the whole dataset) were categorized as uncertain, leading to a yellow traffic light. The biological characterization of patients and monitoring of their clinical course may be used for differential risk stratification in the future. In conclusion, the Clinical 15 model provides a highly sensitive and specific tool to support GPs in diagnosing depression. Future algorithm improvements may integrate further biological markers and longitudinal data. The tool's clinical utility needs further evaluation through a randomized controlled trial, which is currently being planned. Additionally, assessing whether GPs actively integrate the algorithm's predictions into their diagnostic and treatment decisions will be critical for its practical adoption.</p>","PeriodicalId":11822,"journal":{"name":"European Archives of Psychiatry and Clinical Neuroscience","volume":" ","pages":""},"PeriodicalIF":3.5000,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Archives of Psychiatry and Clinical Neuroscience","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00406-025-01990-5","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

General practitioners play an essential role in identifying depression and are often the first point of contact for patients. Current diagnostic tools, such as the Patient Health Questionnaire-9, provide initial screening but might lead to false positives. To address this, we developed a two-step machine learning model called Clinical 15, trained on a cohort of 581 participants using a nested cross-validation framework. The model integrates self-reported data from validated questionnaires within a study sample of patients presenting to general practitioners. Clinical 15 demonstrated a balanced accuracy of 88.2% and incorporates a traffic light system: green for healthy, red for depression, and yellow for uncertain cases. Gaussian mixture model clustering identified four depression subtypes, including an Immuno-Metabolic cluster characterized by obesity, low-grade inflammation, autonomic nervous system dysregulation, and reduced physical activity. The Clinical 15 algorithm identified all patients within the immuno-metabolic cluster as depressed, although 22.2% (30.8% across the whole dataset) were categorized as uncertain, leading to a yellow traffic light. The biological characterization of patients and monitoring of their clinical course may be used for differential risk stratification in the future. In conclusion, the Clinical 15 model provides a highly sensitive and specific tool to support GPs in diagnosing depression. Future algorithm improvements may integrate further biological markers and longitudinal data. The tool's clinical utility needs further evaluation through a randomized controlled trial, which is currently being planned. Additionally, assessing whether GPs actively integrate the algorithm's predictions into their diagnostic and treatment decisions will be critical for its practical adoption.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
抑郁症诊断的多模式方法:从初级保健中的机器学习算法开发中获得的启示。
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 去求助
来源期刊
CiteScore
8.80
自引率
4.30%
发文量
154
审稿时长
6-12 weeks
期刊介绍: The original papers published in the European Archives of Psychiatry and Clinical Neuroscience deal with all aspects of psychiatry and related clinical neuroscience. Clinical psychiatry, psychopathology, epidemiology as well as brain imaging, neuropathological, neurophysiological, neurochemical and moleculargenetic studies of psychiatric disorders are among the topics covered. Thus both the clinician and the neuroscientist are provided with a handy source of information on important scientific developments.
期刊最新文献
Antidepressants, relapse-prevention medications and both combined to reduce alcohol-related hospitalizations in individuals with severe alcohol use disorder. Relating proprioceptive embodiment to body dissatisfaction in anorexia and bulimia patients: effect of visual body images. Suboptimal antidepressant use among inpatients and outpatients with symptoms of depression: a cross-sectional analysis of the POKAL core data set. A multimodal approach to depression diagnosis: insights from machine learning algorithm development in primary care. Higher neutrophil-lymphocyte ratio predicts poor response to repetetive transcranial magnetic stimulation(rTMS) in treatment resistant depression.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1