[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-346714-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-346714-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","cross-cancer-survival-prediction-using-machine-learning-models","Cross-cancer survival prediction using machine learning models","","Cross-cancer survival prediction addresses critical gaps in oncology prognosis by using artificial intelligence to transfer knowledge across cancer types. Machine learning models trained on specific cancers were applied to predict three-year survival for other cancer types, focusing on the most frequent tumors and digestive-system cancers. Data from Hospital Based Cancer Registries of São Paulo (2000–2019) enabled cross-prediction, with XGBoost and LightGBM selecting the best-performing model for different topographies. Combined oral cavity, esophageal, and stomach data achieved 80.18% balanced accuracy, comparable to 79.92% for the stomach-specific model, with no significant statistical difference.",{"@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/cross-cancer-survival-prediction-using-machine-learning-models/346714/",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/cross-cancer-survival-prediction-using-machine-learning-models/346714.png","ImageObject",300,407,{"name":42,"@type":43},"Aurora","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-01","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What survival outcome does the study predict across cancer types?","Question",{"text":63,"@type":64},"The study predicts three-year survival after diagnosis across different cancer types using machine learning models.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is cross-prediction enabled in the study?",{"text":68,"@type":64},"Training uses data from specific cancer types, and models are then evaluated independently on other cancer types to assess cross-prediction potential.",{"name":70,"@type":61,"acceptedAnswer":71},"Which algorithms are used and how is the best model chosen?",{"text":72,"@type":64},"XGBoost and LightGBM are used, and the model with the best performance is selected for predictions across different topographies.","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},346714,1790657666,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"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":111,"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":115,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144,"preview_page_count":33,"preview_urls":145},4810365810221,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nCross-cancer survival prediction using machine learning models  \nLucas Buk Cardoso1􀀍, Jones Eduardo Egydio1, Tatiana Natasha Toporcov2, Nanci Yumi Utida2, Maria Paula Curado3, Gisele Aparecida Fernandes3, Adeylson Guimarães Ribeiro4, Bryan Gilvaz Chin1 & Vanderlei Cunha Parro1  \nAmong the many challenges faced by healthcare systems, cancer remains one of the most urgent. This makes the application of artificial intelligence a critical tool for enhancing early detection and optimizing treatment strategies, especially given the growing volume of patient data being collected.  \nIn this study, machine learning models trained on data for a specific type of cancer were employed to predict three-year survival after diagnosis for other cancer types. Two groups were considered: the most frequent cancers and those related to the digestive system. The data were extracted from the Hospital Based Cancer Registries ofSão Paulo, covering 2000 to 2019, with a consistent selection protocol across all cancer types to enable cross-prediction. XGBoost and LightGBM algorithms were used, choosing the best-performing model for predictions across different topographies. Using a combined dataset oforal cavity, esophageal, and stomach cancers, the model achieved a balanced accuracy of 80.18%, compared with 79.92% for the stomach-specific model. Statistical testing showed no significant difference between these values, suggesting comparable predictive performance. These results illustrate the potential of cross-prediction, especially for rare cancer types where data scarcity represents a significant challenge.  \nKeywords Survival prediction, Cancer, Machine learning, Cross-prediction, XGBoost  \nWith rapid technological advancements, artificial intelligence (AI) has emerged as a transformative force capable of revolutionizing global healthcare1. Among the myriad challenges in healthcare, cancer remains one of the most significant, highlighting the critical need for accurate disease prognosis prediction. Machine learning (ML) tools offer great potential to address the multifaceted challenges of cancer survival prediction2–4. By leveraging advanced ML models and real-world clinical parameters, notable predictive accuracy has been achieved2,5. These models integrate diverse input parameters, capturing complex relationships across cancer types6,7.  \nRegistries, databases, and repositories have played pivotal roles in advancing AI applications in cancer treatment8. While modern AI techniques have demonstrated substantial efficacy across medical domains, their dependence on large datasets remains a key limitation9, 10. Therefore, existing databases, such as national cancer registries, provide invaluable clinical data and serve as essential resources for research8, 11.  \nHowever, access to extensive registry databases is not universally available, especially for rare cancer subtypes and considering regional disparities in the quality of patient registries. To address this, transfer learning represents a great strategy – especially used in deep learning – where previously trained algorithms are used on other problems, reusing the training weights12, 13. This technique is widely used in image data, but there is a lack of studies that verify its validity in tabular datasets, mainly due to the difficulty in finding high-quality and extensive databases14, most of them are small and specialized, making it difficult to create complex models15.  \nEven when trained on heterogeneous datasets, ML models can achieve good results in predictions16, highlighting the importance of investigating approaches such as cross-prediction in areas with data limitations. The Hospital Based Cancer Registries of the state of São Paulo (RHC/SP), which has data on cancer patients since 200017, represents a great opportunity to validate cross-prediction across different types of cancer.  \nThis study aimed to deve","cbCaihs3b0WtLW5T","https://ap.wps.com/l/cbCaihs3b0WtLW5T","pdf",1729082,"English","# Background\n# Methods\n## Data source and study design\n## Model training and evaluation\n# Results\n## Population characteristics\n# Keywords","[{\"question\":\"What survival outcome does the study predict across cancer types?\",\"answer\":\"The study predicts three-year survival after diagnosis across different cancer types using machine learning models.\"},{\"question\":\"How is cross-prediction enabled in the study?\",\"answer\":\"Training uses data from specific cancer types, and models are then evaluated independently on other cancer types to assess cross-prediction potential.\"},{\"question\":\"Which algorithms are used and how is the best model chosen?\",\"answer\":\"XGBoost and LightGBM are used, and the model with the best performance is selected for predictions across different topographies.\"}]","Cross-cancer survival prediction using machine learning models | PDF",1790062510,23,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b5ede2bfd393996247460063bfa4d0c7.webp",983,1291,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0e1285d3df1ba5b0a48344842abc5c06.webp",982,1290,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a405acd87e7d31d43b7f26b7fbe86c8d.webp",981,1289,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0955b7bd2bc299bbf3e5a1046100cb4f.webp",980,1287]