{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T05:09:12Z","timestamp":1770959352476,"version":"3.50.1"},"reference-count":29,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"content-version":"unspecified","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council of Taiwan","doi-asserted-by":"crossref","award":["NSTC 113-2221-E-038-019-MY3"],"award-info":[{"award-number":["NSTC 113-2221-E-038-019-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100020595","name":"National Science and Technology Council of Taiwan","doi-asserted-by":"crossref","award":["NSTC 114-2410-H-038-034-MY3"],"award-info":[{"award-number":["NSTC 114-2410-H-038-034-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Health Care Inform"],"accepted":{"date-parts":[[2025,12,27]]},"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a multichannel convolutional neural network (MCNN) to analyse 36-month pre-diagnostic healthcare records from Taiwan\u2019s National Health Insurance Research Database. The study included 19\u2009954 female patients (596 cancer cases, 19\u2009358 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 cross-validation, with performance compared against nine baseline algorithms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>MCNN achieved superior balanced performance with Macro-F\u2081 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 cancer-specific diagnostic codes. SHapley Additive exPlanations (SHAP) interpretability analysis demonstrated the model\u2019s ability to identify pre-diagnostic phases through temporal healthcare utilisation patterns. Systematic feature selection reduced computational requirements by over 99%, enabling validation on Taiwan\u2019s population-scale National Health Insurance Research Database (NHIRD).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Clinical implementation through electronic health record (EHR) integration offers practical pathways for accessible cancer risk assessment during routine healthcare encounters.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjhci-2025-101874","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T04:30:17Z","timestamp":1770957017000},"page":"e101874","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Early detection of female-specific cancers using longitudinal healthcare records with a multichannel convolutional neural network"],"prefix":"10.1136","volume":"33","author":[{"given":"Chia-Hui","family":"Chien","sequence":"first","affiliation":[{"name":"Computer Science, Middlesex University, London, England, UK"},{"name":"International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan"},{"name":"Graduate Institute of Biomedical Informatics, College of Medical Science & Technology, Taipei Medical University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shih-Chuan","family":"Chang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Data Science, Taipei Medical University, Taipei City, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9634-8380","authenticated-orcid":false,"given":"Yung-Chun","family":"Chang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Data Science, Taipei Medical University, Taipei City, Taiwan"},{"name":"Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6497-4232","authenticated-orcid":false,"given":"Yu-Chuan","family":"Li","sequence":"additional","affiliation":[{"name":"International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan"},{"name":"Graduate Institute of Biomedical Informatics, College of Medical Science & Technology, Taipei Medical University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2026,2,12]]},"reference":[{"key":"2026021220301257000_33.1.e101874.1","unstructured":"Ministry of Health and Welfare T . Cancer registry annual report 2024. 2025. Available: https:\/\/dep.mohw.gov.tw\/DOS\/lp-5069-113-xCat-y113.html"},{"key":"2026021220301257000_33.1.e101874.2","doi-asserted-by":"publisher","DOI":"10.7326\/M15-0969"},{"key":"2026021220301257000_33.1.e101874.3","doi-asserted-by":"publisher","DOI":"10.1309\/AJCPTGD94EVRSJCG"},{"key":"2026021220301257000_33.1.e101874.4","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.21421"},{"key":"2026021220301257000_33.1.e101874.5","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21763"},{"key":"2026021220301257000_33.1.e101874.6","doi-asserted-by":"crossref","first-page":"2182","DOI":"10.1016\/S0140-6736(21)00731-5","article-title":"Ovarian cancer population screening and mortality after long-term follow-up in the UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS): a randomised controlled trial","volume":"397","author":"Menon","year":"2021","journal-title":"The Lancet"},{"key":"2026021220301257000_33.1.e101874.7","doi-asserted-by":"publisher","DOI":"10.2147\/CLEP.S196293"},{"key":"2026021220301257000_33.1.e101874.8","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics15040406","article-title":"Early Diagnosis of Ovarian Cancer: A Comprehensive Review of the Advances, Challenges, and Future Directions","volume":"15","author":"Hong","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"2026021220301257000_33.1.e101874.9","doi-asserted-by":"crossref","DOI":"10.2196\/11936","article-title":"Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review","volume":"20","author":"Brinker","year":"2018","journal-title":"J Med Internet Res"},{"key":"2026021220301257000_33.1.e101874.10","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","author":"McKinney","year":"2020","journal-title":"Nature New Biol"},{"key":"2026021220301257000_33.1.e101874.11","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djq495"},{"key":"2026021220301257000_33.1.e101874.12","doi-asserted-by":"crossref","DOI":"10.4178\/epih.e2018062","article-title":"Data resource profile: the National Health Insurance Research Database (NHIRD)","volume":"40","author":"Lin","year":"2018","journal-title":"Epidemiol Health"},{"key":"2026021220301257000_33.1.e101874.13","doi-asserted-by":"crossref","DOI":"10.1016\/j.canep.2021.102072","article-title":"Does changing healthcare use signal opportunities for earlier detection of cancer? A review of studies using information from electronic patient records","volume":"76","author":"White","year":"2022","journal-title":"Cancer Epidemiol"},{"key":"2026021220301257000_33.1.e101874.14","unstructured":"World Health Organization . WHO collaborating centre for drug statistics methodology. atc\/ddd index 2024. World Health Organization; 2024. Available: https:\/\/atcddd. fhi. no\/atc_ddd_index"},{"key":"2026021220301257000_33.1.e101874.15","unstructured":"Yang Y , Pedersen JO . A comparative study on feature selection in text categorization. Proceedings of the fourteenth international conference on machine learning; 1997"},{"key":"2026021220301257000_33.1.e101874.16","unstructured":"Choi E , et al . Doctor ai: predicting clinical events via recurrent neural networks. Machine learning for healthcare conference; 2016"},{"key":"2026021220301257000_33.1.e101874.17","doi-asserted-by":"crossref","unstructured":"Guo H , Tang R , Ye Y , et al . DeepFM: a factorization-machine based neural network for ctr prediction. Twenty-Sixth International Joint Conference on Artificial Intelligence; Melbourne, Australia, 2017 doi:10.24963\/ijcai.2017\/239","DOI":"10.24963\/ijcai.2017\/239"},{"key":"2026021220301257000_33.1.e101874.18","unstructured":"Society IC . 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021: IEEE; 2021"},{"key":"2026021220301257000_33.1.e101874.19","unstructured":"Devlin J , et al . Bert: pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers); 2019"},{"key":"2026021220301257000_33.1.e101874.20","unstructured":"Lundberg SM , Lee S-I . A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 2017;30."},{"key":"2026021220301257000_33.1.e101874.21","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1814259"},{"key":"2026021220301257000_33.1.e101874.22","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/S0140-6736(11)60993-8","article-title":"Relevance of breast cancer hormone receptors and other factors to the efficacy of adjuvant tamoxifen: patient-level meta-analysis of randomised trials","volume":"378","year":"2011","journal-title":"The Lancet"},{"key":"2026021220301257000_33.1.e101874.23","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2009.25.6529"},{"key":"2026021220301257000_33.1.e101874.24","doi-asserted-by":"crossref","DOI":"10.1038\/ncomms5022","article-title":"Temporal disease trajectories condensed from population-wide registry data covering 6.2 million patients","volume":"5","author":"Jensen","year":"2014","journal-title":"Nat Commun"},{"key":"2026021220301257000_33.1.e101874.25","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1702071"},{"key":"2026021220301257000_33.1.e101874.26","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1001\/jamainternmed.2015.3540","article-title":"Nationwide Population Science: Lessons From the Taiwan National Health Insurance Research Database","volume":"175","author":"Hsing","year":"2015","journal-title":"JAMA Intern Med"},{"key":"2026021220301257000_33.1.e101874.27","doi-asserted-by":"publisher","DOI":"10.1158\/1055-9965.EPI-15-0578"},{"key":"2026021220301257000_33.1.e101874.28","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21557"},{"key":"2026021220301257000_33.1.e101874.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0300-7"}],"container-title":["BMJ Health &amp; Care Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjhci-2025-101874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T04:30:20Z","timestamp":1770957020000},"score":1,"resource":{"primary":{"URL":"https:\/\/informatics.bmj.com\/lookup\/doi\/10.1136\/bmjhci-2025-101874"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,2,12]]},"published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1136\/bmjhci-2025-101874"],"URL":"https:\/\/doi.org\/10.1136\/bmjhci-2025-101874","relation":{},"ISSN":["2632-1009"],"issn-type":[{"value":"2632-1009","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}