[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-370322-105":59,"doc-detail-370322-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","breast-cancer-prediction-based-on-gene-expression-data-using-interpretable-machine-learning-techniques","Breast cancer prediction based on gene expression data using interpretable machine learning techniques","","Breast cancer prediction based on gene expression data using interpretable machine learning techniques aims to improve breast cancer diagnosis and treatment development by building reliable, explainable models. Using a dataset with 1208 observations and 3602 genes, the study applies feature selection to identify influential predictive genes. It compares K-nearest Neighbors, random forests, and support vector machines, then explains gene importance through Shapley values, partial dependence plots, and accumulated local effects. Model-based ranking with LOCI aligns across SVM and RF and highlights ten key genes, supporting medical decision-making.",{"@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/breast-cancer-prediction-based-on-gene-expression-data-using-interpretable-machine-learning-techniques/370322/",{"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/breast-cancer-prediction-based-on-gene-expression-data-using-interpretable-machine-learning-techniques/370322.png","ImageObject",300,407,{"name":92,"@type":93},"Theodore","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What dataset size and gene count are used for the breast cancer prediction study?","Question",{"text":112,"@type":113},"The study uses 1208 observations and 3602 genes in its gene-expression dataset for breast cancer prediction.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which machine learning models are evaluated in the paper?",{"text":117,"@type":113},"K-nearest Neighbors (KNN), random forests (RF), and support vector machine (SVM) are used to build prediction models.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the study explain which genes drive the model predictions?",{"text":121,"@type":113},"It uses explainable machine learning methods including Shapley values, partial dependence (PDPS) and accumulated local effects (ALE) plots to rank and interpret gene importance. Additionally, LOCI identifies the ten most critical genes, with rankings aligned across SVM and RF.","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},370322,1790654136,{"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":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":56,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},7971461740886,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nBreast cancer prediction based on gene expression data using interpretable machine learning techniques  \nGabriel Kallah-Dagadu1,2, Mohanad Mohammed2, Justine B Nasejje3, Nobuhle Nokubonga Mchunu5, Halima STwabi4, Jesca Mercy Batidzirai2, Geoffrey Chiyuzga Singini4, Portia Nevhungoni6 & Innocent Maposa7􀀍  \nBreast cancer remains a global health burden, with an increase in deaths related to this particular cancer. Accurately predicting and diagnosing breast cancer is important for treatment development and survival of patients. This study aimed to accurately predict breast cancer using a dataset comprising 1208 observations and 3602 genes. The study employed feature selection techniques to identify the most influential predictive genes for breast cancer using machine learning (ML) models. The study used K-nearest Neighbors (KNN), random forests (RF), and a support vector machine (SVM). Furthermore, the study employed feature-and model-based importance and explainable ML methods, including Shapley values, Partial dependency (PDPS), and Accumulated Local Effects (ALE) plots, to explain the genes’ importance ranking from the ML methods. Shapley values highlighted the significance of some of the genes in predicting cancer presence. Model-based feature ranking techniques, particularly the Leaving-One-Covariate-In (LOCI) method, identified the ten most critical genes for predicting tumor cases. The LOCI rankings from the SVM and RF methods were aligned. Additionally, visualization methods such as PDPS andALE plots demonstrated how individual feature changes affect predictions and interactions with other genes. By combining feature selection techniques and explainable ML methods, this study has demonstrated the interpretability and reliability of machine learning models for breast cancer prediction, emphasizing the importance of incorporating explainable ML approaches for medical decision-making.  \nKeywords Breast cancer, Prediction, Machine learning, Interpretable machine learning  \nCancer remains a paramount global health challenge, marked by the uncontrolled proliferation and spread of abnormal cells throughout the body1. Its impact is profound, with approximately 19.3 million new cases and nearly 10 million deaths reported worldwide in 2020, spanning 185 countries and encompassing 36 different cancer types2. Among these, breast cancer stands as one of the most prevalent forms among women and ranks as the second leading cause of death in both developed and developing nations3. Recognizing the urgency of the situation, organizations like the World Health Organization and governments globally have strategically prioritized combating breast, cervical, and childhood cancers to alleviate the global cancer burden4. However, comprehensive assessments ofthis burden are hindered by sparse or unavailable data in certain regions, further compounded by delays in diagnosis and treatment, particularly aggravated by events like the COVID-19 pandemic5–7. Enhancing the accuracy of breast cancer screenings, diagnosis, and treatment is paramount in controlling its burden6.  \n1Department of Statistics and Actuarial Science, University of Ghana, Accra, Ghana. 2School of Mathematics, Statistics, and Computer Science, University of KwaZulu-Natal, Pietermaritzburg, South Africa. 3School of Statistics and Actuarial Science, University of the Witwatersrand, Johannesburg-Braamfontein, South Africa.  \n4Department of Mathematical Sciences, University of Malawi, Zomba, Malawi. 5Biostatistics Research Unit, South African Medical Research Council, Durban, South Africa. 6Biostatistics Research Unit, South African Medical Research Council, Pretoria, South Africa. 7Division of Epidemiology and Biostatistics, Department of Global Health, Faculty of Medicine and Health Sciences, Stellenbosch University, Tygerberg, Cape Town, South Africa. 􀀍 email: [imaposa@sun.ac.za](imaposa@sun.ac.za)  \n[ww","cbCaivWv36f5W29O","https://ap.wps.com/l/cbCaivWv36f5W29O","pdf",3049485,"English","# Overview\n## Data and modeling approach\n## Feature selection and interpretability methods\n## Importance ranking and visualization","[{\"question\":\"What dataset size and gene count are used for the breast cancer prediction study?\",\"answer\":\"The study uses 1208 observations and 3602 genes in its gene-expression dataset for breast cancer prediction.\"},{\"question\":\"Which machine learning models are evaluated in the paper?\",\"answer\":\"K-nearest Neighbors (KNN), random forests (RF), and support vector machine (SVM) are used to build prediction models.\"},{\"question\":\"How does the study explain which genes drive the model predictions?\",\"answer\":\"It uses explainable machine learning methods including Shapley values, partial dependence (PDPS) and accumulated local effects (ALE) plots to rank and interpret gene importance. Additionally, LOCI identifies the ten most critical genes, with rankings aligned across SVM and RF.\"}]","Breast cancer prediction based on gene expression data using interpretable machine learning techniques | PDF",1790188012,48,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f050d90bb057d3b61bd153633808ce30.webp",983,1291,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/792ecb630852604c9f8da7ab2ed8c894.webp",982,1290,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/85c61d27e3058e84f37b67d49a326579.webp",981,1289,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/344a6646324e23ad36e43a3012c67b63.webp",980,1287]