[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-344808-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-344808-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","early-detection-of-female-specific-cancers-using-longitudinal-healthcare-records-with-a-multichannel-convolutional-neural-network","Early detection of female-specific cancers using longitudinal healthcare records with a multichannel convolutional neural network","","A study develops and validates a multichannel convolutional neural network for early detection of female-specific cancers using longitudinal administrative healthcare data. The model analyses 36-month prediagnostic records from Taiwan’s National Health Insurance Research Database, covering 19 954 women (596 cancer cases, 19 358 controls) across 1999–2013. Feature selection identifies top signals across diagnostic codes, medications, and medical orders. Results report strong balanced performance and SHAP-based interpretability, highlighting clinically relevant prediagnostic phases. The approach supports EHR-based risk assessment for breast, ovarian, cervical, and uterine cancers.",{"@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/early-detection-of-female-specific-cancers-using-longitudinal-healthcare-records-with-a-multichannel-convolutional-neural-network/344808/",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/early-detection-of-female-specific-cancers-using-longitudinal-healthcare-records-with-a-multichannel-convolutional-neural-network/344808.png","ImageObject",300,407,{"name":42,"@type":43},"Lucas Martin","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-06","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",5,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does this study address?","Question",{"text":63,"@type":64},"Female-specific cancers lack comprehensive early detection approaches, especially for ovarian and endometrial cancers where population-level screening remains limited.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is the predictive model built and evaluated?",{"text":68,"@type":64},"The study trains a multichannel convolutional neural network on 36-month prediagnostic records and validates using stratified 10-fold crossvalidation, comparing against baseline algorithms.",{"name":70,"@type":61,"acceptedAnswer":71},"What do the results and interpretability analyses show?",{"text":72,"@type":64},"The model achieves strong balanced performance and SHAP interpretability reveals pre-diagnostic phases reflected in temporal healthcare utilisation patterns, alongside clinically relevant features.","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},344808,1791075712,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,100,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"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":55,"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":111,"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":117,"preview_page_count":33,"preview_urls":144},8796095360427,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Open access Original research  \nEarly detection of female-specific cancers using longitudinal healthcare records with a multichannel convolutional neural network  \nChia-Hui Chien,1,2,3 Shih-Chuan Chang,4 Yung-Chun Chang  ,4,5 Yu-Chuan Li  2,3  \nTo cite: Chien C-H, Chang S-C, Chang Y-C, et al. Early detection of female-specific cancers using longitudinal healthcare records with a multichannel convolutional neural network. BMJ Health Care Inform 2026;33:e101874 . doi:10 . 1136/ bmjhci-2025-101874  \n► Additional supplemental material is published online only. To view, please visit the journal online ([https://doi.org/10.1136/](https://doi.org/10.1136/)[ ](https://doi.org/10.1136/)[bmjhci-2025-101874](bmjhci-2025-101874)) .  \nReceived 14 October 2025 Accepted 27 December 2025  \n© Author(s) (or their employer(s)) 2026. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ Group.  \n1Computer Science, Middlesex University, London, UK 2International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan  \n3Graduate Institute of Biomedical Informatics, College of Medical Science & Technology, Taipei Medical University, Taipei, Taiwan  \n4Graduate Institute of Data Science, Taipei Medical University, Taipei City, Taiwan 5Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei, Taiwan  \nCorrespondence to  \nDr Yung-Chun Chang; [changyc@tmu.edu.tw](changyc@tmu.edu.tw)  \nABSTRACT  \nObjectives Female-specific cancers, including breast, ovarian, cervical and uterine malignancies, lack comprehensive early detection approaches, particularly for ovarian and endometrial cancers where effective population-level screening remains limited. This study aimed to develop and validate a computational method for early detection of female-specific cancers using longitudinal healthcare records.  \nMethods We developed a multichannel convolutional neural network (MCNN) to analyse 36-month prediagnostic healthcare records from Taiwan’s National Health Insurance Research Database. The study included 19 954 female patients (596 cancer cases, 19 358 controls) from 1999 to 2013. Log-likelihood ratio feature selection identified top 10 features across three data modalities (diagnostic codes, medications, medical orders) . The six-channel architecture processed temporal patterns through stratified 10-fold crossvalidation, with performance compared against nine baseline algorithms.  \nResults MCNN achieved superior balanced performance with Macro-F₁ score of 0 . 8443, precision of 0.9135 and recall of 0 . 7978, outperforming traditional machine learning and deep learning approaches. Feature analysis revealed clinically relevant patterns including tamoxifen therapy, immunohistochemical procedures and cancerspecific diagnostic codes. SHapley Additive exPlanations (SHAP) interpretability analysis demonstrated the model’s ability to identify pre-diagnostic phases through temporal healthcare utilisation patterns. Systematic feature selection reduced computational requirements by over 99%, enabling validation on Taiwan’s populationscale National Health Insurance Research Database (NHIRD) .  \nDiscussion The multichannel deep learning approach enables unified early detection across four female cancer types using routine administrative data, addressing detection gaps for ovarian and endometrial cancers while providing complementary risk stratification for existing screening programmes.  \nConclusion Clinical implementation through electronic health record (EHR) integration offers practical pathways for accessible cancer risk assessment during routine healthcare encounters.  \nWHAT IS ALREADY KNOWN ON THIS TOPIC  \n\n| ⇒ Established screening programmes exist for breast and cervical cancers, but systematic early detection for ovarian and endometrial cancers remains ineffective due to asymptomatic early stages and lack of reliable population-level screening tools.\u003Cbr>WHAT THIS STUDY ADDS ","cbCaifexFPW3h5lK","https://ap.wps.com/l/cbCaifexFPW3h5lK","pdf",1133830,"English","# Abstract\n# Methods\n## Data source and cohort\n## Model architecture and validation\n# Results\n## Performance metrics\n## Feature and interpretability analysis\n# Discussion\n# Conclusion\n# What is already known on this topic\n# What this study adds\n# How this study might affect research, practice or policy","[{\"question\":\"What problem does this study address?\",\"answer\":\"Female-specific cancers lack comprehensive early detection approaches, especially for ovarian and endometrial cancers where population-level screening remains limited.\"},{\"question\":\"How is the predictive model built and evaluated?\",\"answer\":\"The study trains a multichannel convolutional neural network on 36-month prediagnostic records and validates using stratified 10-fold crossvalidation, comparing against baseline algorithms.\"},{\"question\":\"What do the results and interpretability analyses show?\",\"answer\":\"The model achieves strong balanced performance and SHAP interpretability reveals pre-diagnostic phases reflected in temporal healthcare utilisation patterns, alongside clinically relevant features.\"}]","Early detection of female-specific cancers using longitudinal healthcare records with a multichannel convolutional neural network | PDF",1790055331,[145,149,153,157],{"page_no":22,"url":146,"width":147,"height":148},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/83c63d7950d07c44b3980e9d3ab4dcae.webp",983,1310,{"page_no":26,"url":150,"width":151,"height":152},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/18869c5f6198aaa54f55130e47436285.webp",982,1309,{"page_no":30,"url":154,"width":155,"height":156},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6e28e89741c4c1379a97fd9e2a0cfdfb.webp",981,1308,{"page_no":33,"url":158,"width":159,"height":160},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e7f57ac688d6d3ca6534d7f1f5acf8ca.webp",980,1306]