{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T19:57:18Z","timestamp":1772567838002,"version":"3.50.1"},"reference-count":28,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"20","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Over 20\u00a0million colonoscopies are performed in China annually. An automatic clinical decision support system (CDSS) with accurate semantic recognition of colonoscopy reports and guideline-based is helpful to relieve the increasing medical burden and standardize the healthcare. In this study, the CDSS was built under a hierarchical-label interpretable classification framework, trained by a state-of-the-art transformer-based model, and validated in a multi-center style.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>We conducted stratified sampling on a previously established dataset containing 302,965 electronic colonoscopy reports with pathology, identified 2041 patients\u2019 records representative of overall features, and randomly divided into the training and testing sets (7:3). A total of five\u00a0main labels and 22\u00a0sublabels were applied to annotate each record on a network platform, and the data were trained respectively by three pre-training models on Chinese corpus website, including bidirectional encoder representations from transformers (BERT)-base-Chinese (BC), the BERT-wwm-ext-Chinese (BWEC), and ernie-3.0-base-zh (E3BZ). The performance of trained models was subsequently compared with a randomly initialized model, and the preferred model was selected. Model fine-tuning was applied to further enhance the capacity. The system was validated in five other hospitals with 3177 consecutive colonoscopy cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The E3BZ pre-trained model exhibited the best performance, with a 90.18% accuracy and a 69.14% Macro-F1\u00a0score overall. The model achieved 100% accuracy in identifying cancer cases and 99.16% for normal cases. In external validation, the model exhibited favorable consistency and good performance among five hospitals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>The novel CDSS possesses high-level semantic recognition of colonoscopy reports, provides appropriate recommendations, and holds the potential to be a powerful tool for physicians and patients. The hierarchical multi-label strategy and pre-training method should be amendable to manage more medical text in the future.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/cm9.0000000000003469","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:33Z","timestamp":1747958433000},"page":"2631-2639","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Guideline-driven clinical decision support for colonoscopy patients using the hierarchical multi-label deep learning method"],"prefix":"10.1097","volume":"138","author":[{"given":"Junling","family":"Wu","sequence":"first","affiliation":[{"name":"Medical School of Chinese PLA, Beijing 100853, China"},{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"Medical School of Chinese PLA, Beijing 100853, China"},{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Medical School of Chinese PLA, Beijing 100853, China"},{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Luan","sequence":"additional","affiliation":[{"name":"Medical School of Chinese PLA, Beijing 100853, China"},{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology and Hepatology, Hainan Hospital of PLA General Hospital, Sanya, Hainan 572013, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxuan","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing 101408, China"},{"name":"Institute of Automation Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shufang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Congyong","family":"Li","sequence":"additional","affiliation":[{"name":"Sixth Health Care Department, Second Medical Center of PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Geriatrics, Hainan Hospital of PLA General Hospital, Sanya, Hainan 572013, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Medical School of Chinese PLA, Beijing 100853, China"},{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Chen","sequence":"additional","affiliation":[{"name":"Medical School of Chinese PLA, Beijing 100853, China"},{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Medical School of Chinese PLA, Beijing 100853, China"},{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yansheng","family":"Li","sequence":"additional","affiliation":[{"name":"DHC Mediway Technology Co., Ltd, Beijing 100089, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kejia","family":"Liu","sequence":"additional","affiliation":[{"name":"DHC Mediway Technology Co., Ltd, Beijing 100089, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghao","family":"Niu","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology and Hepatology, the First Medical Center, Chinese PLA General Hospital, Beijing 100853, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"276","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"R1-20260303","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1097\/CM9.0000000000003253","article-title":"Chinese national clinical practice guidelines on prevention, diagnosis and treatment of early colorectal cancer","volume":"137","author":"Li","year":"2024","journal-title":"Chin Med J"},{"key":"R2-20260303","doi-asserted-by":"crossref","first-page":"e4483","DOI":"10.7717\/peerj.4483","article-title":"Gender, age, and concomitant diseases of melanosis coli in China: A multicenter study of 6,090 cases","volume":"6","author":"Wang","year":"2018","journal-title":"Peerj"},{"key":"R3-20260303","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1159\/000493461","article-title":"Gender, age, and concomitant diseases of colorectal diverticulum in China: A study of 7,964 cases","volume":"37","author":"Wang","year":"2019","journal-title":"Dig Dis"},{"key":"R4-20260303","doi-asserted-by":"crossref","first-page":"8764","DOI":"10.1038\/s41598-021-88376-4","article-title":"Gastroenterology visitation and reminders predict surveillance uptake for patients with adenomas with high-risk features","volume":"11","author":"Myint","year":"2021","journal-title":"Sci Rep"},{"key":"R5-20260303","doi-asserted-by":"crossref","first-page":"1584","DOI":"10.1136\/gutjnl-2013-306453","article-title":"Adherence to surveillance guidelines after removal of colorectal adenomas: A large, community-based study","volume":"64","author":"van Heijningen","year":"2015","journal-title":"Gut"},{"key":"R6-20260303","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.1002\/cncr.27990","article-title":"Use of colonoscopy for polyp surveillance in Medicare beneficiaries","volume":"119","author":"Cooper","year":"2013","journal-title":"Cancer"},{"key":"R7-20260303","first-page":"1","article-title":"Cancer incidence and mortality in China, 2016","volume":"2","author":"Zheng","year":"2022","journal-title":"J Natl Cancer Cent"},{"key":"R8-20260303","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1038\/s41591-018-0335-9","article-title":"Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence","volume":"25","author":"Liang","year":"2019","journal-title":"Nat Med"},{"key":"R9-20260303","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1161\/STROKEAHA.120.030663","article-title":"Automated electronic phenotyping of cardioembolic stroke","volume":"52","author":"Guan","year":"2021","journal-title":"Stroke"},{"key":"R10-20260303","doi-asserted-by":"crossref","first-page":"1880","DOI":"10.1038\/s41467-021-22018-1","article-title":"Multi-task weak supervision enables anatomically-resolved abnormality detection in whole-body FDG-PET\/CT","volume":"12","author":"Eyuboglu","year":"2021","journal-title":"Nat Commun"},{"key":"R11-20260303","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1016\/j.cgh.2019.10.013","article-title":"Development of an automated algorithm to generate guideline-based recommendations for follow-up colonoscopy","volume":"18","author":"Karwa","year":"2020","journal-title":"Clin Gastroenterol Hepatol"},{"key":"R12-20260303","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/s41746-020-0221-y","article-title":"An overview of clinical decision support systems: Benefits, risks, and strategies for success","volume":"3","author":"Sutton","year":"2020","journal-title":"NPJ Digit Med"},{"key":"R13-20260303","first-page":"1","article-title":"Expert consensus on management strategies for precancerous lesions and conditions of colorectal cancer in China","year":"2022","journal-title":"Chin J Dig Endosc"},{"key":"R14-20260303","doi-asserted-by":"crossref","first-page":"2950","DOI":"10.1109\/JBHI.2020.2977925","article-title":"Natural language processing for mimicking clinical trial recruitment in critical care: A semi-automated simulation based on the LeoPARDS trial","volume":"24","author":"Tissot","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"R15-20260303","doi-asserted-by":"crossref","first-page":"103984","DOI":"10.1016\/j.jbi.2021.103984","article-title":"Classifying social determinants of health from unstructured electronic health records using deep learning-based natural language processing","volume":"127","author":"Han","year":"2022","journal-title":"J Biomed Inform"},{"key":"R16-20260303","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1016\/j.cgh.2013.11.025","article-title":"Clinical decision support with natural language processing facilitates determination of colonoscopy surveillance intervals","volume":"12","author":"Imler","year":"2014","journal-title":"Clin Gastroenterol Hepatol"},{"key":"R17-20260303","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1016\/j.gie.2021.05.036","article-title":"Automated identification and assignment of colonoscopy surveillance recommendations for individuals with colorectal polyps","volume":"94","author":"Peterson","year":"2021","journal-title":"Gastrointest Endosc"},{"key":"R18-20260303","doi-asserted-by":"crossref","first-page":"2255","DOI":"10.1001\/jama.2023.22557","article-title":"Automation bias and assistive AI: Risk of harm from AI-driven clinical decision support","volume":"330","author":"Khera","year":"2023","journal-title":"JAMA"},{"key":"R19-20260303","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1136\/amiajnl-2013-002381","article-title":"A comprehensive study of named entity recognition in Chinese clinical text","volume":"21","author":"Lei","year":"2014","journal-title":"J Am Med Inform Assoc"},{"key":"R20-20260303","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.cmpb.2016.11.009","article-title":"Detecting negation and scope in Chinese clinical notes using character and word embedding","volume":"140","author":"Kang","year":"2017","journal-title":"Comput Methods Programs Biomed"},{"key":"R21-20260303","doi-asserted-by":"crossref","first-page":"103435","DOI":"10.1016\/j.jbi.2020.103435","article-title":"Towards Chinese clinical named entity recognition by dynamic embedding using domain-specific knowledge","volume":"106","author":"Li","year":"2020","journal-title":"J Biomed Inform"},{"key":"R22-20260303","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1186\/s12911-019-0762-7","article-title":"A deep learning model incorporating part of speech and self-matching attention for named entity recognition of Chinese electronic medical records","volume":"19","author":"Cai","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"R23-20260303","doi-asserted-by":"crossref","first-page":"102282","DOI":"10.1016\/j.artmed.2022.102282","article-title":"Chinese clinical named entity recognition via multi-head self-attention based BiLSTM-CRF","volume":"127","author":"An","year":"2022","journal-title":"Artif Intell Med"},{"key":"R24-20260303","doi-asserted-by":"crossref","first-page":"101139","DOI":"10.1016\/j.imu.2022.101139","article-title":"Comparison of BERT implementations for natural language processing of narrative medical documents","volume":"36","author":"Turchin","year":"2023","journal-title":"Inf Med Unlocked"},{"key":"R25-20260303","doi-asserted-by":"crossref","first-page":"100729","DOI":"10.1016\/j.patter.2023.100729","article-title":"Fine-tuning large neural language models for biomedical natural language processing","volume":"4","author":"Tinn","year":"2023","journal-title":"Patterns (N Y)"},{"key":"R26-20260303","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1186\/s12911-022-02059-2","article-title":"Named entity recognition of Chinese electronic medical records based on a hybrid neural network and medical MC-BERT","volume":"22","author":"Chen","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"key":"R27-20260303","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41746-021-00455-y","article-title":"Med-BERT: Pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction","volume":"4","author":"Rasmy","year":"2021","journal-title":"NPJ Digit Med"},{"key":"R29-20260303","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1186\/s40537-021-00492-0","article-title":"Text data augmentation for deep learning","volume":"8","author":"Shorten","year":"2021","journal-title":"J Big Data"}],"container-title":["Chinese Medical Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/CM9.0000000000003469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T19:01:51Z","timestamp":1772564511000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/CM9.0000000000003469"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":28,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/cm9.0000000000003469","relation":{},"ISSN":["0366-6999","2542-5641"],"issn-type":[{"value":"0366-6999","type":"print"},{"value":"2542-5641","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,23]]},"assertion":[{"value":"2024-06-03","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}}]}}