[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125219-en":3,"doc-seo-125219-105":30,"detail-sidebar-cat-0-en-105":91},{"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},125219,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","A Clinical Risk Prediction Model for Depressive Disorders Based on Seven Machine Learning Algorithms","A retrospective study develops a clinically interpretable risk prediction model for depressive disorders using routine blood test indicators and seven machine learning algorithms. Data from 284 patients with depressive disorders and 214 healthy controls collected between January and October 2024 were split into training and test sets. Univariate logistic regression with feature selection via Boruta and LASSO identified key predictors, and a nomogram was built from a multivariable logistic regression model. The model demonstrates strong discrimination, calibration, and clinical utility as an auxiliary diagnostic tool.","International Journal of General Medicine downloaded from [https://www.dovepress.com/](https://www.dovepress.com/)  \nFor personal use only.  \nInternational Journal of General Medicine  \n Open Access Full Text Article  \nORIGINAL RESEARCH  \nA Clinical Risk Prediction Model for Depressive Disorders Based on Seven Machine Learning Algorithms  \nWeifeng Jin*, Shuzi Chen*, Mengxia Wang*, Ping Lin  \nDepartment of Medical Laboratory, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, People’s Republic of China  \n*These authors contributed equally to this work  \nCorrespondence: Ping Lin, Email [Linpingsun20000@aliyun.com](Linpingsun20000@aliyun.com)  \n\n| Objective: To develop a clinical risk prediction model for depressive disorders using seven machine learning algorithms based on routine blood test indicators.\u003Cbr>Methods: A retrospective study was conducted, involving 284 patients with depressive disorders and 214 healthy controls recruited between January and October 2024. Clinical data, including age, sex, and routine blood test results, were collected. The dataset was randomly divided into a training set (70%; n=348) and a test set (30%; n=150) . Univariate logistic regression analysis (p\u003C0.1) was initially performed to identify potential predictors, followed by feature selection using the Boruta and LASSO algorithms. Seven machine learning algorithms were employed to construct predictive models, with their performance evaluated using metrics such as AUC, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), precision, recall, and F1 score. A multivariable logistic regression model was subsequently used to develop a nomogram, and its discrimination, calibration, and clinical utility were comprehensively assessed.\u003Cbr>Results: Four significant predictors (alkaline phosphatase [AKP], serotonin, phenylalanine [Phe], and arginine [Arg]) were identified through univariate logistic regression combined with Boruta and LASSO feature selection. Among the seven algorithms, the random forest model exhibited the highest AUC, achieving an AUC of 1.000 (95% CI: 1.000–1.000) in the training set and 0.958 (95% CI: 0.931–0.985) in the test set. However, due to concerns about potential overfitting, the multivariable logistic regression model was selected as the final predictive model. A nomogram was constructed based on this model.\u003Cbr>Conclusion: This study successfully developed a clinically interpretable risk prediction model for depressive disorders by integrating machine learning algorithms and routine blood test indicators. The logistic regression model demonstrated robust performance across all metrics and holds potential as a reliable auxiliary tool for the diagnosis of depressive disorders.\u003Cbr>Keywords: depressive disorders, machine learn |\n| --- |\n| Introduction\u003Cbr>Depressive disorder is a prevalent mental illness with a rapidly increasing global burden, posing a significant public health challenge. A study published in The Lancet reported that the COVID-19 pandemic led to a 28% increase in the prevalence of major depressive disorder and a 26% increase in anxiety disorders worldwide in 2020, with women and younger populations being disproportionately affected.1 Currently, the diagnosis of depressive disorders relies primarily on clinical evaluations conducted by psychiatrists, based on criteria outlined in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) or the International Classification of Diseases, Tenth Revision (ICD-10) . However, the absence of objective biomarkers for depressive disorders remains a critical limitation, reducing the accuracy and efficiency of diagnosis. Although significant efforts have been made to identify potential biomarkers, no widely accepted or reliable objective indicators have been established to date.2,3 |\n\nReceived: 3 March 2025  \nAccepted: 30 April 2025  \nPublished: 8 May 2025  \nInternational Journa","cbCaiuYnoLuliVPk","https://ap.wps.com/l/cbCaiuYnoLuliVPk","pdf",9266815,1,13,"English","en",105,"# Introduction\n## Diagnostic challenges and need for biomarkers\n## Machine learning and blood-test based modeling\n# Methods\n## Study design and participants\n## Data collection and feature selection\n## Model building and evaluation","[{\"question\":\"What data source and study design were used to build the risk model?\",\"answer\":\"A retrospective study used routine blood test data collected from 284 patients with depressive disorders and 214 healthy controls between January and October 2024.\"},{\"question\":\"How were candidate predictors selected for the final model?\",\"answer\":\"Univariate logistic regression screened potential predictors, and Boruta plus LASSO feature selection was used to identify significant variables.\"},{\"question\":\"Why was the multivariable logistic regression model chosen over the random forest model?\",\"answer\":\"Although the random forest showed the highest AUC, the multivariable logistic regression model was selected as the final predictive model due to concerns about potential overfitting, while still providing robust performance across metrics.\"}]","A Clinical Risk Prediction Model for Depressive Disorders Based on Seven Machine Learning Algorithms | PDF",1785897571,33,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-clinical-risk-prediction-model-for-depressive-disorders-based-on-seven-machine-learning-algorithms","",{"@graph":36,"@context":85},[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/a-clinical-risk-prediction-model-for-depressive-disorders-based-on-seven-machine-learning-algorithms/125219/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data source and study design were used to build the risk model?","Question",{"text":75,"@type":76},"A retrospective study used routine blood test data collected from 284 patients with depressive disorders and 214 healthy controls between January and October 2024.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were candidate predictors selected for the final model?",{"text":80,"@type":76},"Univariate logistic regression screened potential predictors, and Boruta plus LASSO feature selection was used to identify significant variables.",{"name":82,"@type":73,"acceptedAnswer":83},"Why was the multivariable logistic regression model chosen over the random forest model?",{"text":84,"@type":76},"Although the random forest showed the highest AUC, the multivariable logistic regression model was selected as the final predictive model due to concerns about potential overfitting, while still providing robust performance across metrics.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]