[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126410-en":3,"doc-seo-126410-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126410,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","What machine learning teaches us about depression prediction across the life course - An exploratory comparison of predictive models","Identifying individuals at risk for depression early is critical for preventing long-term mental health impairment. Depression severity, duration, and triggers vary widely, complicating prediction. This study evaluates five machine learning models—logistic regression, decision tree, XGBoost, support vector machine, and neural networks—for forecasting self-reported depressive symptoms and clinical depression in adolescence and adulthood using 20 years of nationally representative longitudinal data, trained with early-life (ages 12–18) and later genetic polygenic score predictors. XGBoost shows the highest ROC-AUC, exceeding logistic regression by 0.02, while logistic regression performs comparably overall. Early-life predictors prove informative across the life course, adolescence emerges as a key period, environmental data dominates, and polygenic scores add little when combined.","SSM-Population Health 32 (2025) 101886  \n| What machine learning teaches us about depression prediction across the life course: An exploratory comparison of predictive models\u003Cbr>Rafael Geurgasa ,∗, Saul J. Newman b,c,d, Evelina T. Akimova a,e,f, Katherine N. Thompson a, Robbee Wedowa,e,f,g\u003Cbr>a Department of Sociology, Purdue University, USA b Centre for Longitudinal Studies, University College, UK c University College, University of Oxford, UK d Institute of Population Aging, University of Oxford, UK e Department of Statistics, Purdue University, USA\u003Cbr>f Center on Aging and the Life Course (CALC), Purdue University, USA\u003Cbr>g Department of Medical and Molecular Genetics, Indiana University School of Medicine, USA |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords: Depression Prediction Machine learning\u003Cbr>Polygenic scores |  | Identifying individuals at risk for depression early is important for preventing long-term mental health issues. However, the variability in depression severity, duration, and triggers complicates predictions. This study explores whether machine learning models can outperform traditional methods, like Logistic Regression, in predicting self-reported depressive symptoms and clinical depression during adolescence and adulthood. We applied five machine learning models with varying complexity levels – Logistic Regression, Decision Tree, XGBoost, Support Vector Machine, and Neural Networks – using data from a nationally representative longitudinal study of the U.S., which tracked participants for 20 years. The models were trained with earlylife predictors (ages 12–18) from Wave I, including environmental factors (family, school, health) and genetic predispositions (polygenic scores) from Wave IV. Models were evaluated on their ability to predict depressive symptoms and clinical diagnoses in both adolescence and adulthood. After evaluating the performance of all five models, XGBoost emerged as the most effective, with a 0.02 increase in ROC-AUC compared to the benchmark Logistic Regression model. While this is a slight performance improvement, overall, Logistic Regression performs about as well as many of our ML models. Early-life data showed strong predictive value for depressive symptoms and clinical diagnoses in adolescence and adulthood, highlighting adolescence as a critical period. Polygenic scores do not add predictive power when combined with environmental data. Feature importance analyses identified self-perception and physical health as key predictors of depressive symptoms, while trauma and life-changing events were more influential for clinical depression. |\n\n1. Introduction  \nMental health is currently a global challenge and a public health concern. Mental health problems are among the leading causes of overall morbidity (Vos et al., 2015) and disability (Lozano et al., 2012), and are further linked to suicide risk (Appleby et al., 2017).  \nDepression is one of the most common and widely studied mental health conditions. Depression has been described as the ‘‘common cold’’of mental health (Gitterman, 1991), a metaphor that underscores its widespread prevalence and impact. It affects over 300 million people worldwide with detrimental consequences for individuals’ health, relationships, and life outcomes (Kessing et al., 2023). This burden is especially pronounced in adolescents and young adults, whereby  \n∗ Corresponding author.  \nE-mail address: [rgeurgas@purdue.edu](rgeurgas@purdue.edu) (R. Geurgas).  \ndepression and anxiety are leading contributors to overall sickness and disability (World Health Organization, 2023).  \nDespite growing attention and public health efforts, depression often goes undiagnosed until it becomes severe. Conventional approaches to identifying at-risk groups, such as screenings based on a limited set of risk factors (e.g., family history, trauma exposure, or socioeconomic disadvantage), have had only moderate success in predicting futur","cbCaieJln0xoYvip","https://ap.wps.com/l/cbCaieJln0xoYvip","pdf",3338254,6,1,15,"English","en",105,"# Introduction\n## Depression as a public health challenge\n## Prediction challenges and the need for interdisciplinary approaches\n## Adolescence as a critical developmental window","[{\"question\":\"What is the main goal of this study on depression prediction?\",\"answer\":\"To test whether machine learning models can outperform traditional approaches like logistic regression in predicting depressive symptoms and clinical depression across adolescence and adulthood.\"},{\"question\":\"Which predictors and data sources are used to train the models?\",\"answer\":\"Models are trained using early-life predictors from ages 12–18 (Wave I), including environmental factors such as family, school, and health, plus genetic predispositions represented by polygenic scores from Wave IV.\"},{\"question\":\"How do the five machine learning models compare in predictive performance?\",\"answer\":\"XGBoost performs best, improving ROC-AUC by 0.02 versus logistic regression, but logistic regression overall is about as effective as many of the other ML models.\"}]","What machine learning teaches us about depression prediction across the life course - An exploratory comparison of predictive models | PDF",1785904915,38,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"what-machine-learning-teaches-us-about-depression-prediction-across-the-life-course-an-exploratory-comparison-of-predictive-models","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/what-machine-learning-teaches-us-about-depression-prediction-across-the-life-course-an-exploratory-comparison-of-predictive-models/126410/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is the main goal of this study on depression prediction?","Question",{"text":77,"@type":78},"To test whether machine learning models can outperform traditional approaches like logistic regression in predicting depressive symptoms and clinical depression across adolescence and adulthood.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which predictors and data sources are used to train the models?",{"text":82,"@type":78},"Models are trained using early-life predictors from ages 12–18 (Wave I), including environmental factors such as family, school, and health, plus genetic predispositions represented by polygenic scores from Wave IV.",{"name":84,"@type":75,"acceptedAnswer":85},"How do the five machine learning models compare in predictive performance?",{"text":86,"@type":78},"XGBoost performs best, improving ROC-AUC by 0.02 versus logistic regression, but logistic regression overall is about as effective as many of the other ML models.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]