[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-356406-105":59,"doc-detail-356406-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","longitudinal-multisource-clinical-model-for-early-lung-cancer-risk-stratification-and-screening","Longitudinal multisource clinical model for early lung cancer risk stratification and screening","","A lightweight multichannel deep learning approach is developed to support lung cancer screening through longitudinal risk stratification using routine pre-diagnostic healthcare data. A retrospective cohort study used Taiwan’s National Health Insurance Research Database with 99 615 individuals, including 575 lung cancer cases, extracting diagnostic codes, medication records, and medical orders over 36 months. Log-likelihood ratio feature selection reduced dimensionality by 99.8% while retaining clinical relevance. The model achieved an F1-score of 0.5738 and AUROC of 0.8316, with ablation and SHapley analyses showing medical orders and utilisation patterns as key drivers. Results indicate scalable deployment in resource-constrained settings.",{"@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/longitudinal-multisource-clinical-model-for-early-lung-cancer-risk-stratification-and-screening/356406/",{"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/longitudinal-multisource-clinical-model-for-early-lung-cancer-risk-stratification-and-screening/356406.png","ImageObject",300,407,{"name":92,"@type":93},"Levi","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does this study address in lung cancer screening?","Question",{"text":112,"@type":113},"Lung cancer mortality is high partly because diagnoses often occur at late stages. Current screening methods like low-dose CT can be limited by cost and access, especially in resource-constrained settings.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which data and timeframe were used to train the model?",{"text":117,"@type":113},"The study used routine pre-diagnostic healthcare data from Taiwan’s National Health Insurance Research Database. Features were extracted using diagnostic codes, medication records, and medical orders within a 36-month observation window.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the proposed model improve efficiency and performance?",{"text":121,"@type":113},"Log-likelihood ratio feature selection reduced computational requirements by 99.8% while keeping clinical relevance. The lightweight multichannel CNN achieved stronger precision and F1-score than baseline methods, with AUROC reported at 0.8316.","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},356406,1790812522,{"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":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":39,"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":46,"preview_page_count":19,"preview_urls":144},7971461740909,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Open access Original research  \nLongitudinal multisource clinical model for early lung cancer risk stratification and screening  \nChia-Hui Chien,1,2,3 Shih-Chuan Chang,4 Yung-Chun Chang  ,4,5 Yu-Chuan Li  2,3,6,7  \nTo cite: Chien C-H, Chang S-C, Chang Y-C, et al. Longitudinal multisource clinical model for early lung cancer risk stratification and screening. BMJ Health Care Inform 2026;33:e101989 . doi:10 . 1136/ bmjhci-2025-101989  \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-2025-101989](bmjhci-2025-101989)) .  \nReceived 04 December 2025 Accepted 11 January 2026  \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.  \nFor numbered affiliations see end of article.  \nCorrespondence to  \nDr Yung-Chun Chang; [changyc@tmu.edu.tw](changyc@tmu.edu.tw)  \nDr Yu-Chuan Li; [jack@tmu.edu.tw](jack@tmu.edu.tw)  \nABSTRACT  \nObjectives Lung cancer is the leading cause of cancerrelated mortality worldwide, with poor prognosis largely due to late-stage diagnosis. Current screening methods such as low-dose CT face accessibility and cost barriersin resource-limited settings. This study develops a lightweight multichannel convolutional neural network for lung cancer screening support through longitudinal risk stratification using routine pre-diagnostic healthcare data. Methods We conducted a retrospective cohort study using Taiwan’s National Health Insurance Research Database, comprising 99 615 individuals (575 lung cancer cases; 99 040 non-cancer controls) . Diagnostic codes, medication records and medical orders within a 36-month observation window were extracted. Loglikelihood ratio feature selection was implemented to reduce dimensionality, achieving 99.8% reduction in computational requirements while retaining clinical relevance. A multichannel Convolutional Neural Network (CNN) architecture was designed to process these heterogeneous data modalities simultaneously.  \nResults The proposed method achieved an F₁-score of 0.5738, precision of 0 .7149, Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.8316 and Area Under the Precision-Recall Curve (AUPRC) of 0.1617, outperforming baseline methods in precision and F₁-score. Ablation studies confirmed that medical orders provide primary predictive value, while medication features contribute limited discriminative signal in the prediagnostic phase. SHapley Additive exPlanations analysis revealed that routine healthcare utilisation patterns, rather than cancer-specific features, drive risk stratification. Discussion The lightweight architecture enables deployment in resource-constrained clinical environments while maintaining robust performance, offering potential as a preliminary screening tool to identify high-risk individuals for further diagnostic examination.  \nConclusion Efficient deep learning models using routine clinical data can facilitate lung cancer risk stratification and screening, providing a scalable solution for clinical implementation.  \nINTRODUCTION  \nLung cancer remains the leading cause of cancer-related mortality worldwide. In 2022, approximately 2.5 million new cases were diagnosed globally, resulting in  \nWHAT IS ALREADY KNOWN ON THIS TOPIC  \n\n| ⇒ Deep learning models using electronic health records have shown promise for cancer risk prediction, but computational demands and interpretability limitations hinder deployment in resource-constrained clinical settings where preliminary screening tools are most needed.\u003Cbr>WHAT THIS STUDY ADDS |\n| --- |\n| ⇒ This study demonstrates that a lightweight multichannel Convolutional Neural Network (CNN) with log-likelihood ratio feature selection can achieve superior precision (0 .7149) and F₁-score (0 .5738) for lung cancer detection, while reducing computational requirements by 99 ","cbCaiq5torzzMGXW","https://ap.wps.com/l/cbCaiq5torzzMGXW","pdf",1217552,"English","# Abstract\n## Objectives\n## Methods\n## Results\n## Discussion\n## Conclusion","[{\"question\":\"What problem does this study address in lung cancer screening?\",\"answer\":\"Lung cancer mortality is high partly because diagnoses often occur at late stages. Current screening methods like low-dose CT can be limited by cost and access, especially in resource-constrained settings.\"},{\"question\":\"Which data and timeframe were used to train the model?\",\"answer\":\"The study used routine pre-diagnostic healthcare data from Taiwan’s National Health Insurance Research Database. Features were extracted using diagnostic codes, medication records, and medical orders within a 36-month observation window.\"},{\"question\":\"How does the proposed model improve efficiency and performance?\",\"answer\":\"Log-likelihood ratio feature selection reduced computational requirements by 99.8% while keeping clinical relevance. The lightweight multichannel CNN achieved stronger precision and F1-score than baseline methods, with AUROC reported at 0.8316.\"}]","Longitudinal multisource clinical model for early lung cancer risk stratification and screening | PDF",1790125238,[145,149,153,157],{"page_no":8,"url":146,"width":147,"height":148},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7d937b0a5443d06923f576182617d20d.webp",983,1310,{"page_no":14,"url":150,"width":151,"height":152},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e5293f3bed20b92b34d61a12ef6ab4fe.webp",982,1309,{"page_no":81,"url":154,"width":155,"height":156},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a5589bbbc10607dd545ea9a649309087.webp",981,1308,{"page_no":19,"url":158,"width":159,"height":160},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/07aeec8ddfc868b158f4f765e2a4d5c1.webp",980,1306]