[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124234-en":3,"doc-seo-124234-105":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},124234,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Evaluating Machine Learning Models for Breast Cancer Survival Prediction Using Patient Demographics and Tumor Characteristics","Evaluating machine learning models for breast cancer survival prediction using patient demographics and tumor characteristics is conducted with a SEER-sourced dataset of over 4,000 female patients diagnosed between 2006 and 2010. Six models are assessed: logistic regression, linear discriminant analysis, decision tree, boosted tree, random forest, and neural network. After preprocessing and 5-fold cross-validation, the neural network achieves the best ROC AUC (0.8636). On an independent test set, it reaches accuracy 0.9057 and ROC AUC 0.8665, indicating strong capability for modeling survival outcomes.","UCLA  \nUCLA Electronic Theses and Dissertations  \nTitle  \nEvaluating Machine Learning Models for Breast Cancer Survival Prediction Using Patient Demographics and Tumor Characteristics  \nPermalink  \n[https://escholarship.org/uc/item/3wp122nf](https://escholarship.org/uc/item/3wp122nf)  \nAuthor  \nZhang, Yuxin  \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  \nEvaluating Machine Learning Models for Breast Cancer Survival Prediction Using Patient Demographics and Tumor Characteristics  \nA thesis submitted in partial satisfaction of the requirements for the degree Master of Applied Statistics and Data Science  \nby  \nYuxin Zhang  \n© Copyright by Yuxin Zhang 2025  \nABSTRACT OF THE THESIS  \nEvaluating Machine Learning Models for  \nBreast Cancer Survival Prediction Using  \nPatient Demographics and Tumor Characteristics  \nby  \nYuxin Zhang  \nMaster of Applied Statistics and Data Science  \nUniversity of California, Los Angeles, 2025  \nProfessor Yingnian Wu, Chair  \n(This thesis explores the use of machine learning models to predict breast cancer survival based on patient demographics and tumor characteristics. The dataset, sourced from the SEER program, includes over 4,000 female patients diagnosed between 2006 and 2010 . Six classification models were evaluated: logistic regression, linear discriminant analysis, decision tree, boosted tree, random forest, and neural network. After preprocessing and 5-fold crossvalidation, the neural network achieved the highest cross-validated ROC AUC of 0 .8636. On the independent test set, it reached an accuracy of 0 .9057 and a ROC AUC of 0 .8665. These results suggest that neural networks can effectively model survival outcomes and offer potential for use in clinical decision support. )  \nThe thesis of Yuxin Zhang is approved.  \nGuang Cheng  \nGeorge Michailidis  \nYingnian Wu, Committee Chair  \nUniversity of California, Los Angeles  \n2025  \nTo my advisors, Dave Zes whose guidance made this work possible  \niv  \nTABLE OF CONTENTS  \n1 Introduction ...................................... 1  \n1.1 What is Breast Cancer? ............................. 1  \n1.2 Why might this model be useful? ........................ 2  \n2 Data Collection and Preprocessing ....................... 3  \n2.1 Data description ................................. 3  \n2.2 Cleaning data ................................... 4  \n2.3 Data Split ..................................... 4  \n3 Exploratory Data Analysis ............................. 6  \n3.1 Survival Status Distribution ........................... 6  \n3.2 Age Distribution ................................. 7  \n3.3 Tumor Size Analysis ............................... 7  \n3.4 Survival Duration ................................. 10  \n4 Methodology ..................................... 13  \n4.1 Overview of the Approach ............................ 13  \n4.2 Data Preprocessing Summary .......................... 13  \n4.3 Modeling Techniques ............................... 14  \n4.3.1 Logistic Regression ............................ 14  \n4.3.2 Linear Discriminant Analysis (LDA) .................. 14  \n4.3.3 Decision Tree ............................... 14  \n4.3.4 Boosted Trees ............................... 15  \n4.3.5 Random Forest .............................. 15  \n4.3.6 Neural Network .............................. 15  \n4.4 Model Evaluation Strategy ............................ 15  \n4.4.1 Cross-Validation ............................. 15  \n4.4.2 Evaluation Metrics ............................ 16  \n5 Model Selection and Evaluation ......................... 17  \n5.1 Modeling Strategy ................................ 17  \n5.2 Model Setup and Tuning ............................. 18  \n5.3 Model Performance Comparison ......................... 18  \n5.3.1 Logistic Regression ............................ 18  \n5.3.2 Linear Discriminant Analysis","cbCaicpxE0k7JRqg","https://ap.wps.com/l/cbCaicpxE0k7JRqg","pdf",2068872,1,39,"English","en",105,"# 1 Introduction\n## 1.1 What is Breast Cancer?\n## 1.2 Why might this model be useful?\n# 2 Data Collection and Preprocessing\n## 2.1 Data description\n## 2.2 Cleaning data\n## 2.3 Data Split\n# 3 Exploratory Data Analysis\n## 3.1 Survival Status Distribution\n## 3.2 Age Distribution\n## 3.3 Tumor Size Analysis\n## 3.4 Survival Duration\n# 4 Methodology\n## 4.1 Overview of the Approach\n## 4.2 Data Preprocessing Summary\n## 4.3 Modeling Techniques\n## 4.4 Model Evaluation Strategy\n# 5 Model Selection and Evaluation\n## 5.1 Modeling Strategy\n## 5.2 Model Setup and Tuning\n## 5.3 Model Performance Comparison\n## 5.4 Best Model Selection\n## 5.5 Final Model Evaluation on Test Set\n# 6 Findings and Conclusions\n## 6.1 Limitations\n## 6.2 Future Work","[{\"question\":\"What data source and patient cohort are used for the survival prediction study?\",\"answer\":\"The study uses a dataset sourced from the SEER program, including over 4,000 female patients diagnosed between 2006 and 2010.\"},{\"question\":\"Which machine learning models are evaluated for predicting breast cancer survival?\",\"answer\":\"Six models are evaluated: logistic regression, linear discriminant analysis, decision tree, boosted tree, random forest, and neural network.\"},{\"question\":\"How does the neural network perform compared with other models?\",\"answer\":\"After 5-fold cross-validation, the neural network achieves the highest cross-validated ROC AUC of 0.8636. On the independent test set, it reaches accuracy 0.9057 and ROC AUC 0.8665.\"}]","Evaluating Machine Learning Models for Breast Cancer Survival Prediction Using Patient Demographics and Tumor Characteristics | PDF",1785821162,98,{"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},"evaluating-machine-learning-models-for-breast-cancer-survival-prediction-using-patient-demographics-and-tumor-characteristics","",{"@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/evaluating-machine-learning-models-for-breast-cancer-survival-prediction-using-patient-demographics-and-tumor-characteristics/124234/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What data source and patient cohort are used for the survival prediction study?","Question",{"text":75,"@type":76},"The study uses a dataset sourced from the SEER program, including over 4,000 female patients diagnosed between 2006 and 2010.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are evaluated for predicting breast cancer survival?",{"text":80,"@type":76},"Six models are evaluated: logistic regression, linear discriminant analysis, decision tree, boosted tree, random forest, and neural network.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the neural network perform compared with other models?",{"text":84,"@type":76},"After 5-fold cross-validation, the neural network achieves the highest cross-validated ROC AUC of 0.8636. On the independent test set, it reaches accuracy 0.9057 and ROC AUC 0.8665.","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"]