[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-353839-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-353839-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","a-panel-of-machine-learning-approaches-for-diagnostic-model-development-and-validation-in-ovarian-cancer","A panel of machine learning approaches for diagnostic model development and validation in ovarian cancer","","Ovarian cancer is a lethal gynecological malignancy often diagnosed at advanced stages, while commonly used biomarkers and imaging lack sufficient sensitivity and specificity. A robust machine-learning diagnostic framework is developed and validated using large-scale gene expression data. Five GEO datasets are analyzed with batch-effect correction, and 113 ML algorithms are systematically compared. The Lasso + NaiveBayes model is selected, achieves strong AUC performance and 100% recall in independent validations, and identifies 12 diagnostic core genes.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/a-panel-of-machine-learning-approaches-for-diagnostic-model-development-and-validation-in-ovarian-cancer/353839/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/a-panel-of-machine-learning-approaches-for-diagnostic-model-development-and-validation-in-ovarian-cancer/353839.png","ImageObject",300,407,{"name":42,"@type":43},"Valentina","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-15","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the study address in ovarian cancer diagnosis?","Question",{"text":63,"@type":64},"Existing diagnostic tools have limited sensitivity and specificity and many ML models are constrained by small sample sizes and insufficient validation. The study targets robust diagnostic model development and validation.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which datasets and model-evaluation strategy are used?",{"text":68,"@type":64},"Five GEO gene-expression datasets are used, with multiple cohorts assigned for training and independent validation. After batch-effect correction, 113 ML algorithms are compared systematically, and the best model is further validated.",{"name":70,"@type":61,"acceptedAnswer":71},"What is the main outcome and which genes are identified?",{"text":72,"@type":64},"The Lasso + NaiveBayes model shows the strongest diagnostic performance with high AUC values and 100% recall in both validation cohorts. Twelve core genes (model genes) are identified, with CP showing the highest diagnostic value.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},353839,1790508861,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":55,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":99,"preview_page_count":33,"preview_urls":145},13056703020460,"https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923","Original Article  \nA panel of machine learning approaches for diagnostic model development and validation in ovarian cancer  \nShengyan Shen1,2\\#, Lingling Zhang1,2\\#, Qiran Sun1,2, Yating Huang1,2, Ying Yang1,2, Ningning Hu1,2, Susu Jiang1,2, Liwen Zhang1,2, Xiaoqin Wang1,2, Rujun Chen1,2^  \n1Department of Gynecology and Obstetrics, Shanghai Fifth People’s Hospital, Fudan University, Shanghai, China; 2Center of Community-Based Health Research, Fudan University, Shanghai, China  \nContributions: (I) Conception and design: S Shen, X Wang, R Chen; (II) Administrative support: Liwen Zhang; (III) Provision of study materials or patients: N Hu, Y Yang; (IV) Collection and assembly of data: Lingling Zhang, Q Sun, Y Huang; (V) Data analysis and interpretation: S Shen, Lingling Zhang, R Chen, X Wang, S Jiang; (VI) Manuscript writing: All authors; (VII) Final approval of manuscript: All authors.  \n\\#These authors contributed equally to this work.  \nCorrespondence to: Rujun Chen, MD; Xiaoqin Wang, MD. Department of Gynecology and Obstetrics, Shanghai Fifth People’s Hospital, Fudan University, Shanghai, China; Center of Community-Based Health Research, Fudan University, 801 Heqing Road, Minhang District, Shanghai 200240, China. Email: [chenrujun@fudan.edu.cn](chenrujun@fudan.edu.cn); [wangxiaoqin@fudan.edu.cn](wangxiaoqin@fudan.edu.cn).  \nBackground: Ovarian cancer is a lethal gynecological malignancy, with ~70% of patients diagnosed at advanced stages (5-year survival \u003C30%) due to suboptimal early detection tools. Current modalities [e.g., carbohydrate antigen 125 (CA125), imaging] lack adequate sensitivity and specificity, while existing machine learning (ML)-based diagnostic models are constrained by small sample sizes and insufficient validation. This study aims to develop and validate a robust ML-based diagnostic model for ovarian cancer using large-scale gene expression data, identify core diagnostic biomarkers, and explore their functional and immune-related  \nmechanisms.  \nMethods: We analyzed five Gene Expression Omnibus (GEO) datasets, with GSE26712, GSE29156, and GSE40595 assigned as the training cohort, and GSE66957 and GSE119054 as independent validation cohorts. Following batch effect correction, 113 ML algorithms were systematically compared. The optimal model was further validated, and its core genes [model gene (Mgenes)] were subjected to functional  \nenrichment and immune cell correlation analyses.  \nResults: The least absolute shrinkage and selection operator (Lasso) + NaiveBayes model demonstrated the strongest diagnostic performance, with area under the receiver operating characteristic curve (AUC) values of 0.991 in the training set, 0.889 in GSE119054, and 0.936 in GSE66957, and achieved 100% recall in both validation cohorts. Twelve Mgenes were identified, among which CP exhibited the highest diagnostic value (AUC =0.966). Functional enrichment revealed that Mgenes were predominantly involved in cell cycle regulation and DNA replication pathways, and correlation analyses confirmed their associations with key  \nimmune subsets (e.g., MAOB with regulatory T cells, STAR with CD8+ T cells) .  \nConclusions: The Lasso + NaiveBayes model enables robust ovarian cancer diagnosis, with high recall prioritizing the identification of all potential cases. The identified Mgenes act as both high-performance diagnostic biomarkers and functional mediators of tumorigenesis, laying a foundation for early detection  \nstrategies and mechanistic research into ovarian cancer.  \nKeywords: Ovarian cancer; machine learning (ML); diagnostic model; tumor immune microenvironment  \nSubmitted Nov 21, 2025. Accepted for publication Jan 13, 2026. Published online Feb 13, 2026.  \ndoi: 10.21037/tcr-2025-1-2580  \nView this article at: [https://dx.doi.org/10.21037/tcr-2025-1-2580](https://dx.doi.org/10.21037/tcr-2025-1-2580)  \n^ ORCID: 0000-0002-9451-6280.  \n© AME Publishing Company. Transl Cancer Res 2026;15(2):123 | [https://dx.doi.org/10.21037/tcr-20","cbCairr6KfG544UY","https://ap.wps.com/l/cbCairr6KfG544UY","pdf",11848112,24,"English","# Background\n# Methods\n# Results\n# Conclusions\n# Introduction\n## Highlight box: Key findings","[{\"question\":\"What problem does the study address in ovarian cancer diagnosis?\",\"answer\":\"Existing diagnostic tools have limited sensitivity and specificity and many ML models are constrained by small sample sizes and insufficient validation. The study targets robust diagnostic model development and validation.\"},{\"question\":\"Which datasets and model-evaluation strategy are used?\",\"answer\":\"Five GEO gene-expression datasets are used, with multiple cohorts assigned for training and independent validation. After batch-effect correction, 113 ML algorithms are compared systematically, and the best model is further validated.\"},{\"question\":\"What is the main outcome and which genes are identified?\",\"answer\":\"The Lasso + NaiveBayes model shows the strongest diagnostic performance with high AUC values and 100% recall in both validation cohorts. Twelve core genes (model genes) are identified, with CP showing the highest diagnostic value.\"}]","A panel of machine learning approaches for diagnostic model development and validation in ovarian cancer | PDF",1790107485,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/679ee1df1e24c768d33dea3d5c7fcc14.webp",983,1287,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a4d187f2b00dc5dbf779293a689ab9c4.webp",982,1286,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/8f0879b25744110d28de5c812d5b1b27.webp",981,1284,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/037c45be8d080953e9ab5c2fb6bacf63.webp",980,1283]