[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291145-105":59,"doc-detail-291145-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","predicting-metabolic-syndrome-for-major-depressive-disorder-patients-a-machine-learning-approach-thesis","Predicting Metabolic Syndrome for Major Depressive Disorder Patients - A Machine Learning Approach - Thesis","","Metabolic syndrome is highly prevalent among Major Depressive Disorder (MDD) patients, and early identification of at-risk individuals can enable timely clinical intervention. Predictive modeling is difficult in psychiatric cohorts because clinical datasets are often small, contain missing values, and include heterogeneous variables. This thesis evaluates whether metabolic syndrome can be predicted using baseline information from the METADAP cohort and examines how different missing-data preprocessing choices affect predictive performance, feature importance, and subgroup errors.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/predicting-metabolic-syndrome-for-major-depressive-disorder-patients-a-machine-learning-approach-thesis/291145/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/predicting-metabolic-syndrome-for-major-depressive-disorder-patients-a-machine-learning-approach-thesis/291145.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is predicting metabolic syndrome in MDD patients challenging?","Question",{"text":112,"@type":113},"Predictive modeling is difficult because psychiatric datasets are typically small, contain missing values, and include heterogeneous clinical variables.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which machine learning models are evaluated in the thesis?",{"text":117,"@type":113},"The study evaluates CatBoost, XGBoost, Random Forest, TabNet, Logistic Regression, and a multilayer perceptron.",{"name":119,"@type":110,"acceptedAnswer":120},"How does missing-data preprocessing affect model performance?",{"text":121,"@type":113},"Performance varies substantially: CatBoost is most stable when missing values are preserved, while in the complete-case setup TabNet shows the highest performance. Overall, the findings emphasize that preprocessing strategies can strongly influence results in small clinical datasets.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},291145,1789643551,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","AMERICAN UNIVERSITY OF BEIRUT  \nPREDICTING METABOLIC SYNDROME FOR MAJOR DEPRESSIVE DISORDER PATIENTS: A MACHINE LEARNING APPROACH  \nby  \nREEM AHMAD MOHAMAD  \nA thesis  \nsubmitted in partial fulfillment of the requirements for the degree of Master of Science  \nto the Graduate Program in Computational Science  \nof the Faculty of Arts and Sciences  \nat the American University of Beirut  \nBeirut, Lebanon  \nFebruary 2026  \nAMERICAN UNIVERSITY OF BEIRUT  \nPREDICTING METABOLIC SYNDROME FOR MAJOR DEPRESSIVE DISORDER PATIENTS: A MACHINE LEARNING APPROACH  \nby  \nREEM AHMAD MOHAMAD  \nApproved by:  \n\n| Dr. Khalil El Asmar, Assistant Professor Department of Epidemiology and Biostatistics | Advisor |\n| --- | --- |\n| Dr. Shady Elbassuoni , Associate Professor Department of Computer Science | Member of Committee |\n\nDr. Elias Ghossoub, Associate Professor Member of Committee  \nDepartment of Psychiatry  \nDate of thesis defense: February, 12, 2026  \nAcknowledgements  \nI would first like to express my deepest gratitude to Dr. Khalil El Asmar, my thesis advisor, for his continuous guidance and support throughout this work. His advice, patience, and high academic standards pushed me to think more critically and work more rigorously. His encouragement during challenging moments was a constant source of motivation, and I am sincerely grateful for the time and effort he dedicated to guiding this thesis.  \nI am also very thankful to my co-advisor, Dr. Shady Elbassuoni, for sharing his expertise in machine learning and for his thoughtful and constructive guidance. His insights helped me approach the technical aspects of this work with greater depth and clarity, and significantly strengthened the quality of the analysis.  \nI would like to thank Dr. Elias Ghossoub for serving on my thesis committee. His background in psychiatry and clinical research provided an important perspective on the medical and psychological context of this study, and his presence on the committee added valuable interdisciplinary balance to the evaluation of this work.  \nI would also like to sincerely thank Dr. Jihad Touma, Director of the Computational Science Program, for his continuous support, encouragement, and commitment to the success of students in the program. His dedication to fostering a strong academic environment played an important role throughout my master’s studies.  \nI am especially grateful to Dr. Sarah Najem, my academic advisor throughout my master’s degree, for her constant guidance, encouragement, and availability. Her support and reassurance were invaluable, and her trust helped me move forward with confidence during this journey.  \nFinally, I would like to thank my family and friends for their patience, encouragement, and unwavering support. Without them, this journey would have been much harder.  \nFor transparency, generative AI tools were used solely to assist with improving wording, clarity, and organization during the revision process. All research, analysis, and conclusions presented in this thesis are entirely the author’s own.  \nAbstract of the Thesis of  \nReem Ahmad Mohamad for  Master of Science  \nMajor: Computational Science  \nTitle: Predicting Metabolic Syndrome for Major Depressive Disorder Patients: A Machine Learning Approach  \nMetabolic syndrome is highly prevalent among patients with Major Depressive Disorder (MDD), and early identification of individuals at risk may support timely clinical intervention. However, predictive modelling in psychiatric cohorts is challenging because clinical datasets are typically small, contain missing values, and include heterogeneous clinical variables.  \nThis thesis investigates the feasibility of predicting metabolic syndrome using baseline information from the METADAP cohort. Several machine learning models were evaluated, including CatBoost, XGBoost, Random Forest, TabNet, Logistic Regression, and a multilayer perceptron. To examine how data preprocessing influences predictive performance, three experiment","cbCaio9ekSmc6NVa","https://ap.wps.com/l/cbCaio9ekSmc6NVa","pdf",368894,65,"English","# Acknowledgements\n# Abstract\n# Abbreviations\n# 1 Introduction\n## 1.1 Background and Motivation\n## 1.2 Objective\n## 1.3 Overview\n# 2 Clinical Background\n## 2.1 Metabolic Syndrome\n## 2.2 Major Depressive Disorder\n# 3 Metadap Dataset\n## 3.1 Description Of The Dataset\n# 4 Methodology\n## 4.1 Model Selection and Rationale\n## 4.2 Features Selection\n## 4.3 Missing Data Handling and Imputation Strategy\n## 4.4 Train-Test Split\n## 4.5 Class Imbalance\n## 4.6 Model Tuning and Cross-Validation Strategy\n## 4.7 Interpret","[{\"question\":\"Why is predicting metabolic syndrome in MDD patients challenging?\",\"answer\":\"Predictive modeling is difficult because psychiatric datasets are typically small, contain missing values, and include heterogeneous clinical variables.\"},{\"question\":\"Which machine learning models are evaluated in the thesis?\",\"answer\":\"The study evaluates CatBoost, XGBoost, Random Forest, TabNet, Logistic Regression, and a multilayer perceptron.\"},{\"question\":\"How does missing-data preprocessing affect model performance?\",\"answer\":\"Performance varies substantially: CatBoost is most stable when missing values are preserved, while in the complete-case setup TabNet shows the highest performance. Overall, the findings emphasize that preprocessing strategies can strongly influence results in small clinical datasets.\"}]","Predicting Metabolic Syndrome for Major Depressive Disorder Patients - A Machine Learning Approach - Thesis | PDF",164]