{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T21:33:46Z","timestamp":1776375226143,"version":"3.51.2"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"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>White light endoscopy is the most pivotal tool for detecting early gastric neoplasms. Previous artificial intelligence (AI) systems were primarily unexplainable, affecting their clinical credibility and acceptability. We aimed to develop an explainable AI named ENDOANGEL-ED (explainable diagnosis) to solve this problem. A total of 4482 images and 296 videos with focal lesions from 3279 patients from eight hospitals were used for training, validating, and testing ENDOANGEL-ED. A traditional sole deep learning (DL) model was trained using the same dataset. The performance of ENDOANGEL-ED and sole DL was evaluated on six levels: internal and external images, internal and external videos, consecutive videos, and man\u2013machine comparison with 77 endoscopists in videos. Furthermore, a multi-reader, multi-case study was conducted to evaluate the ENDOANGEL-ED\u2019s effectiveness. A scale was used to compare the overall acceptance of endoscopists to traditional and explainable AI systems. The ENDOANGEL-ED showed high performance in the image and video tests. In man\u2013machine comparison, the accuracy of ENDOANGEL-ED was significantly higher than that of all endoscopists in internal (81.10% vs. 70.61%, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001) and external videos (88.24% vs. 78.49%, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). With ENDOANGEL-ED\u2019s assistance, the accuracy of endoscopists significantly improved (70.61% vs. 79.63%, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). Compared with the traditional AI, the explainable AI increased the endoscopists\u2019 trust and acceptance (4.42 vs. 3.74, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001; 4.52 vs. 4.00, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). In conclusion, we developed a real-time explainable AI that showed high performance, higher clinical credibility, and acceptance than traditional DL models and greatly improved the diagnostic ability of endoscopists.<\/jats:p>","DOI":"10.1038\/s41746-023-00813-y","type":"journal-article","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T04:03:22Z","timestamp":1681272202000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Explainable artificial intelligence incorporated with domain knowledge diagnosing early gastric neoplasms under white light endoscopy"],"prefix":"10.1038","volume":"6","author":[{"given":"Zehua","family":"Dong","sequence":"first","affiliation":[]},{"given":"Junxiao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yanxia","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yunchao","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Xiaoquan","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Dexin","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Renduo","family":"Shang","sequence":"additional","affiliation":[]},{"given":"Youming","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Lihui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Mengjiao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiao","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Yijie","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Hongliu","family":"Du","sequence":"additional","affiliation":[]},{"given":"Zihua","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Liwen","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Lianlian","family":"Wu","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":[[2023,4,12]]},"reference":[{"key":"813_CR1","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1016\/S0140-6736(20)31288-5","volume":"396","author":"EC Smyth","year":"2020","unstructured":"Smyth, E. C., Nilsson, M., Grabsch, H. I., van Grieken, N. C. & Lordick, F. Gastric cancer. Lancet 396, 635\u2013648 (2020).","journal-title":"Lancet"},{"key":"813_CR2","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","volume":"71","author":"H Sung","year":"2021","unstructured":"Sung, H. et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J. Clin. 71, 209\u2013249 (2021).","journal-title":"CA Cancer J. Clin."},{"key":"813_CR3","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.3748\/wjg.14.1149","volume":"14","author":"G Maconi","year":"2008","unstructured":"Maconi, G., Manes, G. & Porro, G. B. Role of symptoms in diagnosis and outcome of gastric cancer. World J. Gastroenterol. 14, 1149\u20131155 (2008).","journal-title":"World J. Gastroenterol."},{"key":"813_CR4","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s10120-016-0601-9","volume":"20","author":"T Sano","year":"2017","unstructured":"Sano, T. et al. Proposal of a new stage grouping of gastric cancer for TNM classification: International Gastric Cancer Association staging project. Gastric Cancer 20, 217\u2013225 (2017).","journal-title":"Gastric Cancer"},{"key":"813_CR5","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1055\/a-1104-5245","volume":"52","author":"A S\u0103ftoiu","year":"2020","unstructured":"S\u0103ftoiu, A. et al. Role of gastrointestinal endoscopy in the screening of digestive tract cancers in Europe: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement. Endoscopy 52, 293\u2013304 (2020).","journal-title":"Endoscopy"},{"key":"813_CR6","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1177\/2050640615624631","volume":"4","author":"MD Rutter","year":"2016","unstructured":"Rutter, M. D. et al. The European Society of Gastrointestinal Endoscopy Quality Improvement Initiative: developing performance measures. U. Eur. Gastroenterol. J. 4, 30\u201341 (2016).","journal-title":"U. Eur. Gastroenterol. J."},{"key":"813_CR7","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1016\/j.bpg.2015.05.010","volume":"29","author":"M Kaise","year":"2015","unstructured":"Kaise, M. Advanced endoscopic imaging for early gastric cancer. Best. Pract. Res. Clin. Gastroenterol. 29, 575\u2013587 (2015).","journal-title":"Best. Pract. Res. Clin. Gastroenterol."},{"key":"813_CR8","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-018-0305-z","volume":"2","author":"KH Yu","year":"2018","unstructured":"Yu, K. H., Beam, A. L. & Kohane, I. S. Artificial intelligence in healthcare. Nat. Biomed. Eng. 2, 719\u2013731 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"813_CR9","doi-asserted-by":"publisher","first-page":"9444","DOI":"10.1007\/s00464-022-09420-6","volume":"36","author":"XL Yuan","year":"2022","unstructured":"Yuan, X. L. et al. Artificial intelligence for diagnosing gastric lesions under white-light endoscopy. Surg. Endosc. 36, 9444\u20139453 (2022).","journal-title":"Surg. Endosc."},{"key":"813_CR10","doi-asserted-by":"publisher","first-page":"103146","DOI":"10.1016\/j.ebiom.2020.103146","volume":"62","author":"D Tang","year":"2020","unstructured":"Tang, D. et al. Development and validation of a real-time artificial intelligence-assisted system for detecting early gastric cancer: a multicentre retrospective diagnostic study. EBioMedicine 62, 103146 (2020).","journal-title":"EBioMedicine"},{"key":"813_CR11","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/j.gie.2021.09.017","volume":"95","author":"L Wu","year":"2022","unstructured":"Wu, L. et al. Real-time artificial intelligence for detecting focal lesions and diagnosing neoplasms of the stomach by white-light endoscopy (with videos). Gastrointest. Endosc. 95, 269\u2013280.e266 (2022).","journal-title":"Gastrointest. Endosc."},{"key":"813_CR12","doi-asserted-by":"publisher","first-page":"eaay7120","DOI":"10.1126\/scirobotics.aay7120","volume":"4","author":"D Gunning","year":"2019","unstructured":"Gunning, D. et al. XAI-Explainable artificial intelligence. Sci. Robot 4, eaay7120 (2019).","journal-title":"Sci. Robot"},{"key":"813_CR13","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":"813_CR14","doi-asserted-by":"publisher","first-page":"1636","DOI":"10.1038\/s41562-021-01146-0","volume":"5","author":"R Cadario","year":"2021","unstructured":"Cadario, R., Longoni, C. & Morewedge, C. K. Understanding, explaining, and utilizing medical artificial intelligence. Nat. Hum. Behav. 5, 1636\u20131642 (2021).","journal-title":"Nat. Hum. Behav."},{"key":"813_CR15","doi-asserted-by":"crossref","unstructured":"Giuste, F. et al. Explainable artificial intelligence methods in combating pandemics: a systematic review. IEEE Rev. Biomed. Eng. 16, 5\u201321 (2023).","DOI":"10.1109\/RBME.2022.3185953"},{"key":"813_CR16","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1001\/jamacardio.2021.2746","volume":"6","author":"JW Hughes","year":"2021","unstructured":"Hughes, J. W. et al. Performance of a convolutional neural network and explainability technique for 12-lead electrocardiogram interpretation. JAMA Cardiol. 6, 1285\u20131295 (2021).","journal-title":"JAMA Cardiol."},{"key":"813_CR17","doi-asserted-by":"publisher","first-page":"674055","DOI":"10.3389\/fnins.2021.674055","volume":"15","author":"A Lombardi","year":"2021","unstructured":"Lombardi, A. et al. Explainable deep learning for personalized age prediction with brain morphology. Front. Neurosci. 15, 674055 (2021).","journal-title":"Front. Neurosci."},{"key":"813_CR18","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s00125-021-05617-x","volume":"65","author":"FG Preston","year":"2022","unstructured":"Preston, F. G. et al. Artificial intelligence utilising corneal confocal microscopy for the diagnosis of peripheral neuropathy in diabetes mellitus and prediabetes. Diabetologia 65, 457\u2013466 (2022).","journal-title":"Diabetologia"},{"key":"813_CR19","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1111\/den.13787","volume":"33","author":"Y Hwang","year":"2021","unstructured":"Hwang, Y. et al. Improved classification and localization approach to small bowel capsule endoscopy using convolutional neural network. Dig. Endosc. 33, 598\u2013607 (2021).","journal-title":"Dig. Endosc."},{"key":"813_CR20","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1111\/den.13688","volume":"33","author":"Y Ikenoyama","year":"2021","unstructured":"Ikenoyama, Y. et al. Detecting early gastric cancer: comparison between the diagnostic ability of convolutional neural networks and endoscopists. Dig. Endosc. 33, 141\u2013150 (2021).","journal-title":"Dig. Endosc."},{"key":"813_CR21","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi, A. & Berrada, M. Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138\u201352160 (2018).","journal-title":"IEEE Access"},{"key":"813_CR22","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.inffus.2021.11.003","volume":"81","author":"Y-L Chou","year":"2022","unstructured":"Chou, Y.-L., Moreira, C., Bruza, P., Ouyang, C. & Jorge, J. Counterfactuals and causability in explainable artificial intelligence: theory, algorithms, and applications. Inf. Fusion 81, 59\u201383 (2022).","journal-title":"Inf. Fusion"},{"key":"813_CR23","unstructured":"Center For Medical Decive Evaluation.NMPA; www.cmde.org.cn\/CL0004\/23452.html."},{"key":"813_CR24","unstructured":"Guidance for Industry and Food and Drug Administration Staff; www.fda.gov\/media\/109618\/download."},{"key":"813_CR25","doi-asserted-by":"crossref","unstructured":"Savage, N. Breaking into the black box of artificial intelligence. Nature (2022).","DOI":"10.1038\/d41586-022-00858-1"},{"key":"813_CR26","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","volume":"53","author":"A Khan","year":"2020","unstructured":"Khan, A., Sohail, A., Zahoora, U. & Qureshi, A. S. A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 53, 5455\u20135516 (2020).","journal-title":"Artif. Intell. Rev."},{"key":"813_CR27","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 779\u2013788 (2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"813_CR28","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1055\/a-1731-9535","volume":"54","author":"Z Dong","year":"2022","unstructured":"Dong, Z. et al. A deep learning-based system for real-time image reporting during esophagogastroduodenoscopy: a multicenter study. Endoscopy 54, 771\u2013777 (2022).","journal-title":"Endoscopy"},{"key":"813_CR29","unstructured":"Akiba, T., Suzuki, S. & Fukuda, K. Extremely large minibatch sgd: training resnet-50 on imagenet in 15min. Preprint at arXiv preprint arXiv:1711.04325 (2017)."},{"key":"813_CR30","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.gie.2021.06.033","volume":"95","author":"L Wu","year":"2022","unstructured":"Wu, L. et al. Deep learning system compared with expert endoscopists in predicting early gastric cancer and its invasion depth and differentiation status (with videos). Gastrointest. Endosc. 95, 92\u2013104.e103 (2022).","journal-title":"Gastrointest. Endosc."},{"key":"813_CR31","doi-asserted-by":"publisher","first-page":"760634","DOI":"10.3389\/fmed.2022.760634","volume":"9","author":"L Tian","year":"2022","unstructured":"Tian, L. et al. Endoscopists\u2019 acceptance on the implementation of artificial intelligence in gastrointestinal endoscopy: development and case analysis of a scale. Front. Med. (Lausanne) 9, 760634 (2022).","journal-title":"Front. Med. (Lausanne)"}],"updated-by":[{"DOI":"10.1038\/s41746-023-00855-2","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T00:00:00Z","timestamp":1686009600000}}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00813-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00813-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00813-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T06:05:38Z","timestamp":1686117938000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00813-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,12]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["813"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00813-y","relation":{"correction":[{"id-type":"doi","id":"10.1038\/s41746-023-00855-2","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,12]]},"assertion":[{"value":"26 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2023","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41746-023-00855-2","URL":"https:\/\/doi.org\/10.1038\/s41746-023-00855-2","order":7,"name":"change_details","label":"Change Details","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":"64"}}