[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-353318-105":59,"doc-detail-353318-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","wdcn-a-comprehensive-neural-network-based-approach-for-estimating-breast-cancer-risk","WDCN: a comprehensive neural network based approach for estimating breast cancer risk","","Breast cancer is a leading cause of cancer mortality in women, making early detection critical, yet benefits vary substantially across risk groups. The study develops wide, deep, and cross network (WDCN), aiming to improve risk stratification beyond traditional polygenic risk scores that sum genetic variants but ignore gene–gene and gene–environment interactions. Results show WDCN outperforms PRS and baseline machine learning methods, reaching AUROC 0.6439 with 286 SNPs and 0.8865 with environmental features, further improving with 317 SNPs; top-30% individuals show relative risk 7.85. An rs2588809–age interaction is identified.",{"@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/wdcn-a-comprehensive-neural-network-based-approach-for-estimating-breast-cancer-risk/353318/",{"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/wdcn-a-comprehensive-neural-network-based-approach-for-estimating-breast-cancer-risk/353318.png","ImageObject",300,407,{"name":92,"@type":93},"PakDamar76","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-26","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":81},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does WDCN address compared with polygenic risk score (PRS)?","Question",{"text":112,"@type":113},"WDCN targets PRS limitations by incorporating interactions beyond additive genetic variant effects, including gene–gene and gene–environment relationships.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does WDCN perform in terms of AUROC?",{"text":117,"@type":113},"Using 286 SNP features yields AUROC 0.6439, while adding environmental features with genetic data raises it to 0.8865. Increasing SNPs to 317 further improves performance (0.6464 and 0.8872, with and without non-genetic factors).",{"name":119,"@type":110,"acceptedAnswer":120},"What does the study report for risk stratification and specific interactions?",{"text":121,"@type":113},"Individuals in the top 30% have a relative risk of 7.85 versus the bottom 30%. The study also identifies an interaction between rs2588809 and age.","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},353318,1790170732,{"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":81,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},962090893057,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Briefings in Bioinformatics, 2026, 27, bbag412 [https://doi.org/10.1093/bib/bbag412](https://doi.org/10.1093/bib/bbag412)  \n[Published: 6 August 2026](Published: 6 August 2026)  \nProblem Solving Protocol  \nWDCN: a comprehensive neural network based approach for  \nestimating breast cancer risk  \nHanshi Xu1 , Guangquan Zhang1 , Hua Lin2 , Mark Grosser2 , Jie Lu1 , *  \n1 Australian AI institute, Faculty of Engineering and Information Technology, University of Technology Sydney, 61 Broadway, Sydney 2007,  \nNew South Wales, Australia  \n2 23Strands, 26-32 Pirrama Road, Pyrmont 2009, New South Wales, Australia  \n*Corresponding author. Australian AI institute, Faculty of Engineering and Information Technology, University of Technology Sydney, 61 Broadway, Sydney 2007, New South Wales, Australia. [E-mail:](E-mail: jie.lu@uts.edu.au)[ jie.lu@uts.edu.au](E-mail: jie.lu@uts.edu.au)  \n\n| • • •\u003Cbr>Abstract\u003Cbr>Breast cancer is one of the most distressing cancers affecting women, and early detection is considered the most effective way to reduce breast cancer mortality. However, the benefits of early detection vary among different risk groups. Therefore, using a combination of genetic information, family history, and other factors to stratify populations by risk can help more people benefit from early detection. Traditional polygenic risk score (PRS) is essentially a weighted sum calculation method that has achieved some success, but it neglects the interactions between genes–genes, genes–environment, and their potential impact on breast cancer risk. In this context, we developed anew deep learning-based method called wide, deep, and cross network (WDCN) . Experimental results show that our algorithm outperforms PRS and other machine learning baseline methods and achieves an area under the receiver operating characteristic curve (AUROC) of 0.6439 when using 286 single nucleotide polymorphism (SNP) features and 0.8865 when incorporating environmental features with genetic data. Increasing the SNP set to 317 further raised the performance to 0.6464 and 0.8872, both with and without non-genetic factors. Risk stratification shows that individuals in the top 30% have a relative risk of 7.85 (95% CI: 6.98–8.83) compared with those in the bottom 30% . We also identified an interaction between rs2588809 and age. This novel approach has shown promise for initial risk stratification of populations, potentially providing better decision-making support for individuals and clinicians.\u003Cbr>Keywords breast cancer, artificial neural network, bioinformatics approach |  |\n| --- | --- |\n| Introduction | undergo annual or biennial mammography for breast cancer screen- |\n| Worldwide, breast cancer is prominently recognized as the most | ing. However, not everyone benefits from it. For individuals at high |\n| diagnosed malignant neoplasm in females and among the deadliest | risk of breast cancer, mammography may lead to false negatives, and |\n| forms of cancer. According to data from 2022, there were roughly | the more sensitive magnetic resonance imaging (MRI) is considered |\n| 2.3 million instances of newly diagnosed breast cancer, representing | a more suitable screening method [13] . For individuals at low risk, |\n| ∼11.6% of the total global cancer incidence rate [1, 2] . The number of | mammography carries the risk of overdiagnosis, leading to unnec- |\n| deaths from breast cancer accounts for ∼6 . 9% of all cancer-related | essary anxiety and radiation exposure [14, 15] . Thus, different risk |\n| deaths, ranking fourth in mortality [2] . Despite varying standards | groups should be recommended different screening strategies, which |\n| and methods for grading cancers in different countries, breast cancer | may bring greater benefits to individuals [16] . |\n| treatment exhibits a consistent trend. Early stage (stage I, stage II, stage III, or localized and regional stage) breast cancers have an 80% or | Polygenic risk score (PRS) is a commonly used method for ri","cbCail18LcHzTHDS","https://ap.wps.com/l/cbCail18LcHzTHDS","pdf",2193211,14,"English","# Abstract\n# Introduction\n## Breast cancer screening trade-offs\n## Polygenic risk score limitations\n## Improved PRS directions\n# Methods overview (WDCN)","[{\"question\":\"What problem does WDCN address compared with polygenic risk score (PRS)?\",\"answer\":\"WDCN targets PRS limitations by incorporating interactions beyond additive genetic variant effects, including gene–gene and gene–environment relationships.\"},{\"question\":\"How does WDCN perform in terms of AUROC?\",\"answer\":\"Using 286 SNP features yields AUROC 0.6439, while adding environmental features with genetic data raises it to 0.8865. Increasing SNPs to 317 further improves performance (0.6464 and 0.8872, with and without non-genetic factors).\"},{\"question\":\"What does the study report for risk stratification and specific interactions?\",\"answer\":\"Individuals in the top 30% have a relative risk of 7.85 versus the bottom 30%. The study also identifies an interaction between rs2588809 and age.\"}]","WDCN: a comprehensive neural network based approach for estimating breast cancer risk | PDF",1790104730,35]