[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123500-en":3,"doc-seo-123500-105":30,"detail-sidebar-cat-0-en-105":95},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123500,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Predicting Mental Health Among Adolescents with Risk Behaviors Based on Machine Learning","Examines how specific adolescent risk behaviors contribute to mental health outcomes, with attention to gender differences. Using a nationally representative Chinese dataset of 8,670 high school students surveyed in 2020, the study applies an explainable machine learning approach. A gradient-boosted decision tree (XGBoost) predicts mental health measured by the Symptom Checklist-90 (SCL-90) from 22 risk behaviors, and SHAP values quantify feature contributions. The model performs well (RMSE=0.49, MAE=0.35) and identifies dizziness during sports, lack of seat belt use, and alcohol consumption as major risk factors.","cited.  \nThe authors declare that there is no conflict of interests regarding the publication of this paper.  \nReceived: 16.11.2025. Revised: 19.12.2025. Accepted: 19.12.2025. Published: 19.12.2025.  \nPredicting Mental Health Among Adolescents with Risk Behaviors Based on Machine Learning  \nYan Li 1, Luyan Teng2,*  \n1 Department of Psychology, Faculty of Medicine, University of Helsinki, Helsinki, Finland, [Email: yan.z.li@helsinki.fi](Email: yan.z.li@helsinki.fi) [https://orcid.org/0000-0002-2977-4945](https://orcid.org/0000-0002-2977-4945)  \n2 College of International Education, Sichuan International Studies University, China, Email: [luyan.teng@outlook.com](luyan.teng@outlook.com) [https://orcid.org/0000-0001-7673-3217](https://orcid.org/0000-0001-7673-3217)  \n*Corresponding Author  \nAbstract  \nObjectives  \nWhile mental health is known to predict risk behaviors, less is understood about how specific risk behaviors contribute to mental health outcomes, particularly across genders. This study used machine learning to examine the predictive relationships between various risk behaviorsand adolescent mental health, and to explore gender differences in these patterns.  \nMethods  \nWe analyzed data from the nationally representative Chinese “Database of Youth Health,”including 8,670 high school students surveyed in 2020. A gradient-boosted decision tree model (XGBoost) was used to predict mental health, measured by the Symptom Checklist-90 (SCL- 90), based on 22 risk behaviors. SHAP (Shapley Additive ExPlanations) values were calculated to interpret individual feature contributions.  \nResults  \nThe model showed good performance (RMSE = 0.49, MAE = 0.35). Frequent dizziness during sports, lack of seat belt use, and alcohol consumption were identified as significant risk factors.  \nGender differences emerged: earlier age of first smoking was more strongly associated with poorer mental health among girls, while exercise frequency was a stronger protective factor for boys.  \nConclusion  \nThese findings underscore the need for gender-sensitive mental health interventions that address both physical and behavioral risk factors, and demonstrate the utility of machine learning in identifying nuanced predictors of adolescent mental health.  \nKeywords: risk behaviors, mental health; adolescents, machine learning; gender differences  \nIntroduction  \nAdolescent risk behaviors encompass activities such as drug and alcohol abuse, reckless driving, and other dangerous behaviors (Sullivan et al., 2010) . Mental health problems such as anxiety, depression, and emotional dysregulation in adolescents can predict increased engagement in risky behavior (Deng et al., 2024; Jones et al., 2011; Kessler et al., 2005) . However, limited studies focusing on how risk behaviors predict mental health outcomes, although studies found they strongly correlated with each other (Brooks et al., 2002) . During adolescence, males are more prone to exhibit externalizing disorders such as substance abuse, which even lead to suicide death (Miranda-Mendizabal et al., 2019) . In contrast, females are more likely to develop internalizing mental health issues such as depression (Rosenfield & Mouzon, 2013) . However, we know little about how specific risk behavior affect the mental health of male and female differently.  \nMachine learning (ML) offers an advanced approach over traditional statistical methods, excelling in handling high-dimensional and complex datasets and revealing non-linear relationships (Abdolali & Gillis, 2021; Aghaabbasi & Chalermpong, 2023) . This capability enhances predictive accuracy and uncovers deeper data patterns often missed by conventional approaches. Therefore, the current study aims to build an explainable predictive model to identify how specific risk behaviors predict mental health outcomes among adolescents in China by using the ML data analysis methods. Through this investigation, we seek to provide valuable insights into the interplay betwe","cbCaihq7TWwkk69p","https://ap.wps.com/l/cbCaihq7TWwkk69p","pdf",560953,1,18,"English","en",105,"# Abstract\n## Objectives\n## Methods\n## Results\n## Conclusion\n# Introduction\n## Background and research questions\n# Method\n## Participants\n## Variables and measures","[{\"question\":\"What is the main objective of this study?\",\"answer\":\"To determine how specific adolescent risk behaviors predict mental health outcomes and to examine whether these predictive patterns differ by gender.\"},{\"question\":\"What data and model are used to predict adolescent mental health?\",\"answer\":\"The study uses the nationally representative Chinese “Database of Youth Health” (8,670 students). It applies XGBoost to predict SCL-90 mental health scores from 22 risk behaviors and uses SHAP for interpretability.\"},{\"question\":\"Which risk behaviors are identified as significant predictors?\",\"answer\":\"Frequent dizziness during sports, lack of seat belt use, and alcohol consumption are identified as significant risk factors for mental health.\"},{\"question\":\"What gender differences are reported in the findings?\",\"answer\":\"Earlier age of first smoking is more strongly associated with poorer mental health among girls, while exercise frequency is a stronger protective factor for boys.\"}]","Predicting Mental Health Among Adolescents with Risk Behaviors Based on Machine Learning | PDF",1785816882,45,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"predicting-mental-health-among-adolescents-with-risk-behaviors-based-on-machine-learning","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-mental-health-among-adolescents-with-risk-behaviors-based-on-machine-learning/123500/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main objective of this study?","Question",{"text":75,"@type":76},"To determine how specific adolescent risk behaviors predict mental health outcomes and to examine whether these predictive patterns differ by gender.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data and model are used to predict adolescent mental health?",{"text":80,"@type":76},"The study uses the nationally representative Chinese “Database of Youth Health” (8,670 students). It applies XGBoost to predict SCL-90 mental health scores from 22 risk behaviors and uses SHAP for interpretability.",{"name":82,"@type":73,"acceptedAnswer":83},"Which risk behaviors are identified as significant predictors?",{"text":84,"@type":76},"Frequent dizziness during sports, lack of seat belt use, and alcohol consumption are identified as significant risk factors for mental health.",{"name":86,"@type":73,"acceptedAnswer":87},"What gender differences are reported in the findings?",{"text":88,"@type":76},"Earlier age of first smoking is more strongly associated with poorer mental health among girls, while exercise frequency is a stronger protective factor for boys.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]