{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T15:17:52Z","timestamp":1770909472133,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T00:00:00Z","timestamp":1671408000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T00:00:00Z","timestamp":1671408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Bleeding risk factors for gastroesophageal varices (GEV) detected by endoscopy in cirrhotic patients determine the prophylactical treatment patients will undergo in the following 2 years. We propose a methodology for measuring the risk factors. We create an artificial intelligence system (ENDOANGEL-GEV) containing six models to segment GEV and to classify the grades (grades 1\u20133) and red color signs (RC, RC0-RC3) of varices. It also summarizes changes in the above results with region in real time. ENDOANGEL-GEV is trained using 6034 images from 1156 cirrhotic patients across three hospitals (dataset 1) and validated on multicenter datasets with 11009 images from 141 videos (dataset 2) and in a prospective study recruiting 161 cirrhotic patients from Renmin Hospital of Wuhan University (dataset 3). In dataset 1, ENDOANGEL-GEV achieves intersection over union values of 0.8087 for segmenting esophageal varices and 0.8141 for gastric varices. In dataset 2, the system maintains fairly accuracy across images from three hospitals. In dataset 3, ENDOANGEL-GEV surpasses attended endoscopists in detecting RC of GEV and classifying grades (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). When ranking the risk of patients combined with the Child\u2012Pugh score, ENDOANGEL-GEV outperforms endoscopists for esophageal varices (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001) and shows comparable performance for gastric varices (<jats:italic>p<\/jats:italic>\u2009=\u20090.152). Compared with endoscopists, ENDOANGEL-GEV may help 12.31% (16\/130) more patients receive the right intervention. We establish an interpretable system for the endoscopic diagnosis and risk stratification of GEV. It will assist in detecting the first bleeding risk factors accurately and expanding the scope of quantitative measurement of diseases.<\/jats:p>","DOI":"10.1038\/s41746-022-00729-z","type":"journal-article","created":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T07:07:04Z","timestamp":1671433624000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding"],"prefix":"10.1038","volume":"5","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[]},{"given":"Zhengqiang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Mingkai","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Shi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Lianlian","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Liwen","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Xiaoda","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Jiao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Mengjuan","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Yijie","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Renquan","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Chenxia","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xun","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1882-7060","authenticated-orcid":false,"given":"Honggang","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,19]]},"reference":[{"key":"729_CR1","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1016\/S0140-6736(18)31875-0","volume":"393","author":"C Villanueva","year":"2019","unstructured":"Villanueva, C. et al. \u03b2 blockers to prevent decompensation of cirrhosis in patients with clinically significant portal hypertension (PREDESCI): a randomised, double-blind, placebo-controlled, multicentre trial. Lancet 393, 1597\u20131608 (2019).","journal-title":"Lancet"},{"key":"729_CR2","doi-asserted-by":"crossref","unstructured":"European Association for the Study of the Liver. EASL Clinical Practice Guidelines for the management of patients with decompensated cirrhosis. J. Hepatol. 69, 406\u2013460 (2018).","DOI":"10.1016\/j.jhep.2018.08.009"},{"key":"729_CR3","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1056\/NEJMra0901512","volume":"362","author":"G Garcia-Tsao","year":"2010","unstructured":"Garcia-Tsao, G. & Bosch, J. Management of varices and variceal hemorrhage in cirrhosis. N. Engl. J. Med. 362, 823\u2013832 (2010).","journal-title":"N. Engl. J. Med."},{"key":"729_CR4","doi-asserted-by":"publisher","first-page":"2173","DOI":"10.1002\/hep.28824","volume":"64","author":"JG Abraldes","year":"2016","unstructured":"Abraldes, J. G. et al. Noninvasive tools and risk of clinically significant portal hypertension and varices in compensated cirrhosis: the \u201cAnticipate\u201d study. Hepatology 64, 2173\u20132184 (2016).","journal-title":"Hepatology"},{"key":"729_CR5","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1016\/j.jhep.2015.11.039","volume":"64","author":"J Bosch","year":"2016","unstructured":"Bosch, J. & Sauerbruch, T. Esophageal varices: stage-dependent treatment algorithm. J. Hepatol. 64, 746\u2013748 (2016).","journal-title":"J. Hepatol."},{"key":"729_CR6","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.1136\/gutjnl-2015-309262","volume":"64","author":"D Tripathi","year":"2015","unstructured":"Tripathi, D. et al. U.K. guidelines on the management of variceal haemorrhage in cirrhotic patients. Gut 64, 1680\u20131704 (2015).","journal-title":"Gut"},{"key":"729_CR7","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1002\/hep.28906","volume":"65","author":"G Garcia-Tsao","year":"2017","unstructured":"Garcia-Tsao, G., Abraldes, J. G., Berzigotti, A. & Bosch, J. Portal hypertensive bleeding in cirrhosis: Risk stratification, diagnosis, and management: 2016 practice guidance by the American Association for the study of liver diseases. Hepatology 65, 310\u2013335 (2017).","journal-title":"Hepatology"},{"key":"729_CR8","doi-asserted-by":"crossref","unstructured":"North Italian Endoscopic Club for the Study and Treatment of Esophageal Varices. Prediction of the first variceal hemorrhage in patients with cirrhosis of the liver and esophageal varices. A prospective multicenter study. N Engl J. Med. 319, 983\u2013989 (1988).","DOI":"10.1056\/NEJM198810133191505"},{"key":"729_CR9","doi-asserted-by":"publisher","first-page":"2915","DOI":"10.1111\/j.1572-0241.2000.03204.x","volume":"95","author":"C Merkel","year":"2000","unstructured":"Merkel, C. et al. Prognostic indicators of risk for first variceal bleeding in cirrhosis: a multicenter study in 711 patients to validate and improve the North Italian Endoscopic Club (NIEC) index. Am. J. Gastroenterol. 95, 2915\u20132920 (2000).","journal-title":"Am. J. Gastroenterol."},{"key":"729_CR10","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1016\/j.gie.2020.06.058","volume":"93","author":"M Chen","year":"2021","unstructured":"Chen, M. et al. Automated and real-time validation of gastroesophageal varices under esophagogastroduodenoscopy using a deep convolutional neural network: a multicenter retrospective study (with video). Gastrointest. Endosc. 93, 422\u2013432.e423 (2021).","journal-title":"Gastrointest. Endosc."},{"key":"729_CR11","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1093\/gastro\/gox007","volume":"5","author":"I Haq","year":"2017","unstructured":"Haq, I. & Tripathi, D. Recent advances in the management of variceal bleeding. Gastroenterol. Rep. (Oxf.) 5, 113\u2013126 (2017).","journal-title":"Gastroenterol. Rep. (Oxf.)"},{"key":"729_CR12","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.dld.2013.12.010","volume":"46","author":"V Jairath","year":"2014","unstructured":"Jairath, V. et al. Acute variceal haemorrhage in the United Kingdom: patient characteristics, management and outcomes in a nationwide audit. Dig. Liver Dis. 46, 419\u2013426 (2014).","journal-title":"Dig. Liver Dis."},{"key":"729_CR13","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1016\/S2468-1253(19)30413-3","volume":"5","author":"D Gong","year":"2020","unstructured":"Gong, D. et al. Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled study. Lancet Gastroenterol. Hepatol. 5, 352\u2013361 (2020).","journal-title":"Lancet Gastroenterol. Hepatol."},{"key":"729_CR14","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.1136\/gutjnl-2018-317366","volume":"68","author":"L Wu","year":"2019","unstructured":"Wu, L. et al. Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy. Gut 68, 2161\u20132169 (2019).","journal-title":"Gut"},{"key":"729_CR15","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1016\/j.crad.2022.01.046","volume":"77","author":"H Liu","year":"2022","unstructured":"Liu, H. et al. Establishment of a non-invasive prediction model for the risk of oesophageal variceal bleeding using radiomics based on CT. Clin. Radio. 77, 368\u2013376 (2022).","journal-title":"Clin. Radio."},{"key":"729_CR16","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/s12072-021-10292-6","volume":"16","author":"Y Yan","year":"2022","unstructured":"Yan, Y. et al. A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients. Hepatol. Int 16, 423\u2013432 (2022).","journal-title":"Hepatol. Int"},{"key":"729_CR17","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.1016\/j.cgh.2019.01.025","volume":"17","author":"TS Dong","year":"2019","unstructured":"Dong, T. S. et al. Machine Learning-based Development and Validation of a Scoring System for Screening High-Risk Esophageal Varices. Clin. Gastroenterol. Hepatol. 17, 1894\u20131901.e1891 (2019).","journal-title":"Clin. Gastroenterol. Hepatol."},{"key":"729_CR18","doi-asserted-by":"publisher","first-page":"3355","DOI":"10.1007\/s00330-020-07430-3","volume":"31","author":"CM Lee","year":"2021","unstructured":"Lee, C. M. et al. An index based on deep learning-measured spleen volume on CT for the assessment of high-risk varix in B-viral compensated cirrhosis. Eur. Radio. 31, 3355\u20133365 (2021).","journal-title":"Eur. Radio."},{"key":"729_CR19","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.future.2019.04.031","volume":"100","author":"S Ding","year":"2019","unstructured":"Ding, S., Li, L., Li, Z., Wang, H. & Zhang, Y. Smart electronic gastroscope system using a cloud\u2013edge collaborative framework. Future Gener. Comput. Syst. 100, 395\u2013407 (2019).","journal-title":"Future Gener. Comput. Syst."},{"key":"729_CR20","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/538020a","volume":"538","author":"D Castelvecchi","year":"2016","unstructured":"Castelvecchi, D. Can we open the black box of AI? Nature 538, 20\u201323 (2016).","journal-title":"Nature"},{"key":"729_CR21","doi-asserted-by":"publisher","first-page":"e654","DOI":"10.1016\/S2589-7500(21)00133-3","volume":"3","author":"HS Muti","year":"2021","unstructured":"Muti, H. S. et al. Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer: a retrospective multicentre cohort study. Lancet Digit Health 3, e654\u2013e664 (2021).","journal-title":"Lancet Digit Health"},{"key":"729_CR22","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41746-021-00427-2","volume":"4","author":"E Wulczyn","year":"2021","unstructured":"Wulczyn, E. et al. Interpretable survival prediction for colorectal cancer using deep learning. NPJ Digit. Med. 4, 71 (2021).","journal-title":"NPJ Digit. Med."},{"key":"729_CR23","doi-asserted-by":"publisher","first-page":"e665","DOI":"10.1016\/S2589-7500(21)00134-5","volume":"3","author":"G Zhang","year":"2021","unstructured":"Zhang, G. et al. Clinically relevant deep learning for detection and quantification of geographic atrophy from optical coherence tomography: a model development and external validation study. Lancet Digit Health 3, e665\u2013e675 (2021).","journal-title":"Lancet Digit Health"},{"key":"729_CR24","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1016\/j.jhep.2015.05.022","volume":"63","author":"R de Franchis","year":"2015","unstructured":"de Franchis, R. Expanding consensus in portal hypertension: report of the Baveno VI Consensus Workshop: Stratifying risk and individualizing care for portal hypertension. J. Hepatol. 63, 743\u2013752 (2015).","journal-title":"J. Hepatol."},{"key":"729_CR25","doi-asserted-by":"crossref","first-page":"109","DOI":"10.4103\/1319-3767.164185","volume":"22","author":"S Ramanathan","year":"2016","unstructured":"Ramanathan, S. et al. Correlation of HVPG level with ctp score, MELD Score, ascites, size of varices, and etiology in cirrhotic patients. Saudi J. Gastroenterol. 22, 109\u2013115 (2016).","journal-title":"Saudi J. Gastroenterol."},{"key":"729_CR26","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1002\/hep.1840050313","volume":"5","author":"G Garcia-Tsao","year":"1985","unstructured":"Garcia-Tsao, G. et al. Portal pressure, presence of gastroesophageal varices and variceal bleeding. Hepatology 5, 419\u2013424 (1985).","journal-title":"Hepatology"},{"key":"729_CR27","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1016\/j.gie.2019.11.026","volume":"91","author":"J Zhou","year":"2020","unstructured":"Zhou, J. et al. A novel artificial intelligence system for the assessment of bowel preparation (with video). Gastrointest. Endosc. 91, 428\u2013435.e422 (2020).","journal-title":"Gastrointest. Endosc."},{"key":"729_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.1443-1661.2009.00929.x","volume":"22","author":"T Tajiri","year":"2010","unstructured":"Tajiri, T. et al. General rules for recording endoscopic findings of esophagogastric varices (2nd edition). Dig. Endosc. 22, 1\u20139 (2010).","journal-title":"Dig. Endosc."},{"key":"729_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N. & Liang, J. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support 3\u201311 (Springer, 2018).","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"729_CR30","unstructured":"Smith, A. Using Artificial Intelligence and Algorithms. https:\/\/www.ftc.gov\/business-guidance\/blog\/2020\/04\/using-artificial-intelligence-and-algorithms. (2020)."},{"key":"729_CR31","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1038\/s41591-021-01461-z","volume":"27","author":"S Kundu","year":"2021","unstructured":"Kundu, S. AI in medicine must be explainable. Nat. Med. 27, 1328 (2021).","journal-title":"Nat. Med."},{"key":"729_CR32","unstructured":"Tonekaboni, S., Joshi, S., McCradden, M. D. & Goldenberg, A. What clinicians want: contextualizing explainable machine learning for clinical end use. In Machine learning for healthcare conference. (PMLR) 359\u2013380 (2019)."},{"key":"729_CR33","doi-asserted-by":"publisher","unstructured":"Brennen, A. What Do People Really Want When They Say They Want\" Explainable AI?\" We Asked 60 Stakeholders. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems. 1\u20137 https:\/\/doi.org\/10.1145\/3334480.3383047. (2020).","DOI":"10.1145\/3334480.3383047"},{"key":"729_CR34","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/S0016-5107(81)73224-3","volume":"27","author":"K Beppu","year":"1981","unstructured":"Beppu, K. et al. Prediction of variceal hemorrhage by esophageal endoscopy. Gastrointest. Endosc. 27, 213\u2013218 (1981).","journal-title":"Gastrointest. Endosc."},{"key":"729_CR35","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1016\/j.jvir.2017.10.014","volume":"29","author":"JD Morrison","year":"2018","unstructured":"Morrison, J. D. et al. Gastric Varices Bleed at Lower Portosystemic Pressure Gradients than Esophageal Varices. J. Vasc. Inter. Radio. 29, 636\u2013641 (2018).","journal-title":"J. Vasc. Inter. Radio."},{"key":"729_CR36","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1016\/j.cld.2014.07.005","volume":"18","author":"WE Saad","year":"2014","unstructured":"Saad, W. E. Endovascular management of gastric varices. Clin. Liver Dis. 18, 829\u2013851 (2014).","journal-title":"Clin. Liver Dis."},{"key":"729_CR37","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1053\/j.gastro.2020.04.062","volume":"159","author":"A Repici","year":"2020","unstructured":"Repici, A. et al. Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial. Gastroenterology 159, 512\u2013520.e517 (2020).","journal-title":"Gastroenterology"},{"key":"729_CR38","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1038\/s41591-020-1034-x","volume":"26","author":"X Liu","year":"2020","unstructured":"Liu, X., Cruz Rivera, S., Moher, D., Calvert, M. J. & Denniston, A. K. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat. Med. 26, 1364\u20131374 (2020).","journal-title":"Nat. Med."},{"key":"729_CR39","doi-asserted-by":"crossref","unstructured":"Wang, W.-T., Wu, Y.-L., Tang, C.-Y. & Hor, M.-K. Adaptive density-based spatial clustering of applications with noise (DBSCAN) according to data. In 2015 International Conference on Machine Learning and Cybernetics (ICMLC). (IEEE) 1, 445\u2013451 (2015).","DOI":"10.1109\/ICMLC.2015.7340962"},{"key":"729_CR40","doi-asserted-by":"crossref","unstructured":"Wu, L., et al. Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial. Endoscopy. 12, 1199\u20131207 (2021).","DOI":"10.1055\/a-1350-5583"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00729-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00729-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00729-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,3]],"date-time":"2023-12-03T06:08:38Z","timestamp":1701583718000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00729-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,19]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["729"],"URL":"https:\/\/doi.org\/10.1038\/s41746-022-00729-z","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,19]]},"assertion":[{"value":"4 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"183"}}