[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123290-en":3,"doc-seo-123290-105":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":20,"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},123290,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Mortality Prediction in Heart Failure Using Machine Learning - Thesis Abstract","Mortality Prediction in Heart Failure Using Machine Learning evaluates whether machine learning improves risk prediction for 299 heart-failure patients using real clinical data. Three predictive models are tested: logistic regression, a decision tree, and XGBoost, trained after data preparation and assessed with accuracy and ROC-AUC. Model comparison highlights trade-offs between interpretability and predictive performance. Logistic regression achieves the highest accuracy at 85%, while XGBoost captures complex patterns with AUC 0.8920. The decision tree remains easy to interpret with strong results at 80% accuracy.","UCLA  \nUCLA Electronic Theses and Dissertations  \nTitle  \nMortality Prediction in Heart Failure Using Machine Learning  \nPermalink  \n[https://escholarship.org/uc/item/0kg946d4](https://escholarship.org/uc/item/0kg946d4)  \nAuthor  \nChen, Gaohong  \nPublication Date  \n2025  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA Los Angeles  \nMortality Prediction in Heart Failure Using Machine Learning  \nA thesis submitted in partial satisfaction of the requirements for the degree Master of Applied Statistics and Data Science  \nby  \nGaohong Chen  \n© Copyright by Gaohong Chen 2025  \nABSTRACT OF THE THESIS  \nMortality Prediction in Heart Failure  \nUsing Machine Learning  \nby  \nGaohong Chen  \nMaster of Applied Statistics and Data Science  \nUniversity of California, Los Angeles, 2025  \nProfessor Yingnian Wu, Chair  \nThis study examines how machine learning can improve those predictions using real clinical data from 299 patients. Three models were tested: logistic regression, decision tree, and XGBoost. The analysis focused on key health indicators, including age, ejection fraction, kidney function, and sodium levels. After preparing the data and training the models, their performance was measured using several metrics, including accuracy and the area under the ROC curve. Logistic regression achieved the highest accuracy of 85 percent. XGBoost performed best overall in capturing complex patterns, with an AUC of 0 .8920. While the decision tree offered an easy to understand approach with good results, achieving an accuracy of 80 percent. Each model had strengths, depending on whether simplicity or predictive power was more important.  \nThe thesis of Gaohong Chen is approved.  \nNicolas Christou  \nYuhua Zhu  \nYingnian Wu, Committee Chair  \nUniversity of California, Los Angeles 2025  \nTABLE OF CONTENTS  \n1 Introduction 1  \n1.1 Background and Motivation ........................... 1  \n2 Data Description 4  \n2.1 Dataset Source .................................. 4  \n2.2 Dataset information ................................ 4  \n2.3 Data Preprocessing ................................ 5  \n3 Exploratory Data Analysis 7  \n3.1 Distribution of the Target by Numerical Variable ............... 8  \n3.2 Distribution of the Target by Categorical Variable ............... 12  \n3.3 EDA Conclusion ................................. 16  \n4 Statistical Modeling 18  \n4.1 Model Building Approaches ........................... 18  \n4.2 Logistic Regression ................................ 18  \n4.3 Decision Tree ................................... 22  \n4.4 Extreme Gradient Boosting ........................... 27  \n5 Conclusion 30  \n6 References 33  \nLIST OF FIGURES  \n3.1 Distribution of Target Variable ......................... 7  \n3.2 Distribution of Age by Death Event ...................... 8  \n3.3 Distribution of Ejection Fraction by Death Event ............... 9  \n3.4 Distribution of Serum Creatinine by Death Event ............... 10  \n3.5 Distribution of Serum Sodium by Death Event ................. 11  \n3.6 High Blood Pressure by Death Event ...................... 12  \n3.7 Anaemia by Death Event ............................. 13  \n3.8 Sex by Death Event ................................ 14  \n3.9 Smoking by Death Event ............................. 15  \n3.10 Correlation matrix ................................ 17  \n4.1 ROC Curve for Logistic Regression ....................... 21  \n4.2 Classification Tree Built on the Training Set .................. 22  \n4.3 Cross-Validation Misclassification Error by Tree Size ............. 23  \n4.4 Visualization of the Pruned Decision Tree with 7 Terminal Nodes ...... 24  \n4.5 Feature importance derived from the XGBoost model ............. 28  \nLIST OF TABLE  \n2.1 Data Description ................................. 5  \n4.1 Logistic Regression Coefficients ......................... 20  \n4.2 Comparison of Baseline and Pru","cbCaindg5vf2rbct","https://ap.wps.com/l/cbCaindg5vf2rbct","pdf",2189459,1,42,"English","en",105,"# Introduction\n## Background and Motivation\n# Data Description\n## Dataset Source\n## Dataset information\n## Data Preprocessing\n# Exploratory Data Analysis\n## Distribution of the Target by Numerical Variable\n## Distribution of the Target by Categorical Variable\n## EDA Conclusion\n# Statistical Modeling\n## Model Building Approaches\n## Logistic Regression\n## Decision Tree\n## Extreme Gradient Boosting\n# Conclusion\n# References\n# List of Figures\n# List of Tables","[{\"question\":\"What data and study cohort are used for mortality prediction?\",\"answer\":\"The study uses real clinical data from 299 heart-failure patients. Key health indicators include age, ejection fraction, kidney function, and sodium levels.\"},{\"question\":\"Which machine learning models are compared in the thesis?\",\"answer\":\"Three models are tested: logistic regression, a decision tree, and XGBoost. Each model is trained after data preparation.\"},{\"question\":\"How do the models perform, and which one is best overall?\",\"answer\":\"Logistic regression achieves the highest accuracy at 85%. XGBoost performs best overall in capturing complex patterns with an AUC of 0.8920, while the decision tree offers good interpretability with about 80% accuracy.\"}]","Mortality Prediction in Heart Failure Using Machine Learning - Thesis Abstract | PDF",1785815769,106,{"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},"mortality-prediction-in-heart-failure-using-machine-learning-thesis-abstract","",{"@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/mortality-prediction-in-heart-failure-using-machine-learning-thesis-abstract/123290/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data and study cohort are used for mortality prediction?","Question",{"text":75,"@type":76},"The study uses real clinical data from 299 heart-failure patients. Key health indicators include age, ejection fraction, kidney function, and sodium levels.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are compared in the thesis?",{"text":80,"@type":76},"Three models are tested: logistic regression, a decision tree, and XGBoost. Each model is trained after data preparation.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the models perform, and which one is best overall?",{"text":84,"@type":76},"Logistic regression achieves the highest accuracy at 85%. XGBoost performs best overall in capturing complex patterns with an AUC of 0.8920, while the decision tree offers good interpretability with about 80% accuracy.","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"]