[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128182-en":3,"doc-seo-128182-105":31,"detail-sidebar-cat-0-en-105":92},{"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},128182,549768702563,"Sage","https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083",8,"Research & Report","An Assessment of Machine Learning Models and Algorithms for Early Prediction and Diagnosis of Diabetes Using Health Indicators","The thesis assesses machine learning models and algorithms to enable early prediction and diagnosis of Type 2 diabetes from health survey indicators. It uses 2015 BRFSS data, performs feature selection with Random Forest importance to retain predictors contributing to at least 90% of total gain, applies standard normalization, and balances classes with SMOTE. Models including Logistic Regression, SVM, Decision Trees, Random Forest, XGBoost, and CatBoost are fine-tuned with Optuna and evaluated via cross-validation and held-out testing. A stacked ensemble (Random Forest + XGBoost with Logistic Regression as the final decision maker) achieves strong F1-scores of 0.82 on the test set and 0.94 under cross-validation.","CALIFORNIA STATE UNIVERSITY SAN MARCOS  \nTHESIS SIGNATURE PAGE  \nTHESIS SUBMITTED IN PARTIAL FULFILLMENT  \nOF THE REQUIREMENTS FOR THE DEGREE  \nMASTER OF SCIENCE  \nIN  \nCOMPUTER SCIENCE  \nTHESIS TITLE: AN ASSESSMENT OF MACHINE LEARNING MODELS AND ALGORITHMS FOR EARLY PREDICTION AND DIAGNOSIS OF DIABETES USING HEALTH INDICATORS  \nAUTHOR: SHVAM VIJAY WAGH  \nDATE OF SUCCESSFUL DEFENSE: 05/02/2025  \nTHE THESIS HAS BEEN ACCEPTED BY THE THESIS COMMITTEE IN  \nPARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTER OF SCIENCE IN COMPUTER SCIENCE.  \nDr. Ahmad R. Hadaegh.  \n\n| THESIS COMMITTEE CHAIR\u003Cbr>Md Lutfor Rahman | SIGNATURE | DATE |\n| --- | --- | --- |\n\nTHESIS COMMITTEE MEMBER  \nSIGNATURE  \nDATE  \nAN ASSESSMENT OF MACHINE LEARNING MODELS AND ALGORITHMS FOR EARLY PREDICTION AND DIAGNOSIS OF DIABETES  \nUSING HEALTH INDICATORS  \nIn Partial Fulfillment  \nof the Requirements for the Degree  \nMaster of Science in Computer Science  \nby  \nShivam Vijay Wagh  \nMay 2025  \n© 2025 Shivam Vijay Wagh  \nALL RIGHTS RESERVED  \nCOMMITTEE MEMBERSHIP  \nTITLE: An Assessment of Machine Learning Models and Algorithms for Early Prediction and Diagnosis of Diabetes Using Health Indicators  \nAUTHOR: Shivam Vijay Wagh  \nDATE SUBMITTED: May 2025  \nCOMMITTEE CHAIR: Dr. Ahmad R. Hadaegh.  \nProfessor (CSTEM Computer Science and  \nInformation Systems)  \nCOMMITTEE MEMBER: Md Lutfor Rahman.  \nProfessor (CSTEM Computer Science and  \nInformation Systems)  \nABSTRACT  \nAn Assessment of Machine Learning Models and Algorithms for Early Prediction and Diagnosis of Diabetes Using Health Indicators  \nShivam Vijay Wagh  \nType 2 diabetes is a serious and growing global health issue, affecting more than 500 million people. Because it often develops without obvious symptoms, early detection is essential to prevent serious complications like heart disease, kidney damage, and nerve problems. In this study, we build a machine learning system to predict diabetes using health survey data from the 2015 Behavioral Risk Factor Surveillance System (BRFSS) . We first select the most important features using Random Forest feature importance, keeping only those that make up at least 90% of the total contribution. These features are then scaled using standard normalization, and we apply SMOTE to balance the number of diabetic and non-diabetic samples in the training data.  \nWe test several machine learning models including Logistic Regression, Support Vector Machines (SVM), Decision Trees, Random Forest, XGBoost, and CatBoost. Each model is fine-tuned using the Optuna framework, using both cross-validation and separate test data for evaluation. Our best result comes from a stacked ensemble model that combines Random Forest and XGBoost as base models, with Logistic Regression as the final decision maker. This model achieves an F1-score of 0.82 on the test set and 0.94 in cross-validation. Although the CatBoost model also gave strong results, it was not included in the final ensemble due to only a small improvement in performance.  \nOverall, this research shows that selecting the right features, balancing the dataset, and using ensemble learning can greatly improve prediction results. The system we developed offers a practical and accurate way to help detect diabetes early, which could be useful for public health programs and personal risk screening.  \nKeywords: Select descriptive keywords and separate terms with a comma and a space.  \nTABLE OF CONTENTS  \nPage  \nCHAPTER  \n1. INTRODUCTION . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1  \n2. BACKGROUND AND RELATED WORK . . . . . . . . . . . . . . . . . . 4  \n3. METHODOLOGY . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7  \n3.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7  \n3.2 Exploratory Data Analysis (EDA)                 8  \n3.2.1 Cramr’s V Correlation Matrix ................. 9  \n3.2.2 BMI and Diabetes...................................................................","cbCaiczwSXNFpGke","https://ap.wps.com/l/cbCaiczwSXNFpGke","pdf",1195292,3,1,35,"English","en",105,"# 1. Introduction\n# 2. Background and Related Work\n# 3. Methodology\n## 3.1 Dataset\n## 3.2 Exploratory Data Analysis (EDA)\n## 3.3 Preprocessing Techniques\n## 3.4 Model Selection and Evaluation\n## 3.5 Stacked Ensemble Architecture\n## 3.6 Evaluation Metrics","[{\"question\":\"What data source is used for diabetes prediction in the study?\",\"answer\":\"The system is built using health survey data from the 2015 Behavioral Risk Factor Surveillance System (BRFSS).\"},{\"question\":\"How are important features selected and why?\",\"answer\":\"Random Forest feature importance is used to keep only features that account for at least 90% of total contribution, reducing noise and focusing on the most informative indicators.\"},{\"question\":\"Which model performs best and what evaluation results does it achieve?\",\"answer\":\"The best-performing approach is a stacked ensemble combining Random Forest and XGBoost, with Logistic Regression as the final decision maker, reaching an F1-score of 0.82 on the test set and 0.94 in cross-validation.\"}]","An Assessment of Machine Learning Models and Algorithms for Early Prediction and Diagnosis of Diabetes Using Health Indicators | PDF",1785945323,88,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":29},"an-assessment-of-machine-learning-models-and-algorithms-for-early-prediction-and-diagnosis-of-diabetes-using-health-indicators","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"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":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/an-assessment-of-machine-learning-models-and-algorithms-for-early-prediction-and-diagnosis-of-diabetes-using-health-indicators/128182/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What data source is used for diabetes prediction in the study?","Question",{"text":76,"@type":77},"The system is built using health survey data from the 2015 Behavioral Risk Factor Surveillance System (BRFSS).","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are important features selected and why?",{"text":81,"@type":77},"Random Forest feature importance is used to keep only features that account for at least 90% of total contribution, reducing noise and focusing on the most informative indicators.",{"name":83,"@type":74,"acceptedAnswer":84},"Which model performs best and what evaluation results does it achieve?",{"text":85,"@type":77},"The best-performing approach is a stacked ensemble combining Random Forest and XGBoost, with Logistic Regression as the final decision maker, reaching an F1-score of 0.82 on the test set and 0.94 in cross-validation.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"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":107,"slug":139},19,"General","general"]