[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-357371-105":3,"detail-sidebar-cat-0-en-105":85,"doc-detail-357371-en":135},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":84},105,"en","artificial-intelligence-in-endoscopic-prediction-of-submucosal-invasion-in-gastric-neoplasms-systematic-review-and-meta-analysis","Artificial intelligence in endoscopic prediction of submucosal invasion in gastric neoplasms: systematic review and meta-analysis","","Accurate assessment of submucosal (SM) invasion in gastric neoplasms is crucial for curative endoscopic management, but conventional endoscopy shows moderate accuracy and operator dependence. This PRISMA-DTA systematic review and meta-analysis evaluates AI-driven endoscopic systems using machine-learning or deep-learning models with histopathology as the reference standard. Pooled results across validation cohorts show sensitivity 0.75, specificity 0.84, and AUC 0.87. Externally validated models perform worse than internal ones, suggesting overfitting, and regional effects are observed.",{"@graph":14,"@context":77},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/artificial-intelligence-in-endoscopic-prediction-of-submucosal-invasion-in-gastric-neoplasms-systematic-review-and-meta-analysis/357371/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/artificial-intelligence-in-endoscopic-prediction-of-submucosal-invasion-in-gastric-neoplasms-systematic-review-and-meta-analysis/357371.png","ImageObject",300,407,{"name":42,"@type":43},"Mary Man","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",14,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69,73],{"name":60,"@type":61,"acceptedAnswer":62},"What does the study evaluate about AI in gastric endoscopy?","Question",{"text":63,"@type":64},"It assesses the diagnostic capability of AI-driven endoscopic systems for identifying submucosal (SM) invasion depth in gastric neoplasms using histopathology as the reference standard.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How were the included studies selected and analyzed?",{"text":68,"@type":64},"A PRISMA-DTA systematic review and meta-analysis identified studies using machine-learning or deep-learning models applied to endoscopic imaging, and 2×2 validation-set data were pooled with hierarchical models to estimate sensitivity, specificity, and AUC.",{"name":70,"@type":61,"acceptedAnswer":71},"What performance did the AI systems achieve for predicting SM invasion?",{"text":72,"@type":64},"Across seven studies with sufficient data, AI systems showed pooled sensitivity of 0.75 and specificity of 0.84, with high discriminatory ability (AUC = 0.87).",{"name":74,"@type":61,"acceptedAnswer":75},"Why might external validation results differ from internal validation?",{"text":76,"@type":64},"The review reports that externally validated models had lower sensitivity than internally validated models (0.72 vs. 0.79), indicating potential overfitting. It also notes regional differences in specificity.","https://schema.org",{"og:url":32,"og:type":79,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":81,"canonical":32},"index,follow",{"doc_id":83,"site_id":7},357371,1790366492,{"code":4,"msg":86,"data":87},"success",[88,92,96,100,105,110,115,119,124,127,131],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},"Exam",70,"exam",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},5,"Comic",60,"comic",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},6,"Technology",50,"technology",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},7,"Healthcare",40,"healthcare",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":117,"slug":118},8,30,"research-report",{"id":120,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":122,"slug":123},9,"Religion & Spirituality",20,"religion-spirituality",{"id":122,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":122,"slug":126},"World Cup","world-cup",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":128,"slug":130},10,"Lifestyle","lifestyle",{"id":132,"doc_module":4,"doc_module_name":25,"category_name":133,"show_sort_weight":101,"slug":134},19,"General","general",{"code":4,"msg":86,"data":136},{"doc_id":83,"user_id":137,"nickname":42,"user_avatar":138,"doc_module":4,"category_id":116,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":139,"file_id":140,"file_url":141,"file_type":142,"file_size":143,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":144,"language":145,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":146,"faqs":147,"seo_title":148,"seo_description":12,"update_tm":149,"read_time":150,"preview_page_count":33,"preview_urls":151},7421720224475,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Clinics 81 (2026) 101010  \nContents lists available at ScienceDirect  \nClinics  \njournal [homepage:](homepage: www.elsevier.com/locate/clinsp)[ www.elsevier.com/locate/clinsp](homepage: www.elsevier.com/locate/clinsp)  \n| Review articles\u003Cbr>Artificial intelligence in endoscopic prediction of submucosal invasion in gastric neoplasms: systematic review and meta-analysis\u003Cbr>*\u003Cbr>Dan Long , Jinrong Zeng, Qiu Jianting\u003Cbr>Department of Gastroenterology, The Second Hospital of Longyan, Longyan Fujian, China |  |  | |\n| --- | --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Edited by: Jos´e Maria Soares Junior |  | Background: Accurate assessment of Submucosal (SM) invasion in gastric neoplasms is vital for curative endoscopic management, yet conventional endoscopy remains moderately accurate and operator dependent. Whether AI can deliver reliable, generalizable depth prediction is unknown.\u003Cbr>Aim: This investigation establishes the diagnostic capability of AI-driven endoscopic systems for identifying SM invasion. Methods: A PRISMA-DTA systematic review and meta-analysis identified studies that used machinelearning or deep-learning models applied to endoscopic imaging with histopathology as the reference standard. Validation-set 2 × 2 data were pooled using hierarchical models to estimate sensitivity, specificity, and AUC, and heterogeneity was assessed through subgroup analyses.\u003Cbr>Results: Eight studies were included in the systematic review; seven studies provided sufficient data (including ten cohorts for the meta-analysis). AI systems demonstrated a pooled sensitivity of 0.75 (95% CI 0.69–0.81) and a specificity of 0.84 (95% CI 0.79–0.87). Discriminatory ability was high (AUC = 0.87, 95% CI 0.84–0.90), providing a conservative, transportable estimate of performance based on validation cohorts. Heterogeneity was substantial. Externally validated models showed lower sensitivity than internally validated models (0.72 vs. 0.79; p \u003C 0.001), revealing overfitting. Korean cohorts demonstrated higher specificity than studies from other regions (0.87 vs. 0.79; p \u003C 0.001). Fagan's analysis showed that a positive AI result increased post-test probability from 25% to 61%, while a negative result reduced it to 9%.\u003Cbr>Conclusions: AI-assisted endoscopic assessment establishes a high-accuracy framework for identifying SM invasion and opens the door to more consistent treatment selection in early gastric cancer. International external validation and unified invasion definitions remain essential for dependable clinical use. |  |\n| Keywords:\u003Cbr>Artificial intelligence Endoscopy\u003Cbr>Gastric neoplasms Submucosal invasion\u003Cbr>Diagnostic accuracy |  |  |  |\n\nIntroduction  \nGastric cancer remains a major global health burden, ranking among the leading causes of cancer-related mortality despite declining incidence in some regions. Early Gastric Cancer (EGC), defined as a tumor confined to the mucosa or submucosa regardless of lymph node status, carries an excellent prognosis when appropriately treated, making accurate staging of invasion depth clinically pivotal. Submucosal (SM) invasion beyond 500 µm (T1b2) substantially increases the risk of lymph node metastasis and shifts management from endoscopic therapy toward gastrectomy with lymphadenectomy. Consequently, reliable pre‑treatment assessment of SM involvement is central to selecting optimal, organ‑preserving strategies for gastric neoplasms.1,2  \nEndoscopic Submucosal Dissection (ESD) has become an established curative option for selected superficial gastric neoplasms, enabling  \nresection as a single piece with low local recurrence and acceptable complication profiles. Guideline-based indications for ESD rely heavily on predictions of tumor size, histology, ulceration, and especially depth of invasion, which determine the risk of non-curative resection and the need for additional surgery. However, conventional White-Light Endoscopy (WLE) and Endoscopic Ultrasound (EUS) have onl","cbCaijtCYxoIibeU","https://ap.wps.com/l/cbCaijtCYxoIibeU","pdf",3245866,11,"English","# Introduction\n## Endoscopic management needs accurate SM invasion depth\n## Limitations of conventional WLE and EUS\n## Role of operator experience\n## Emergence of AI and deep learning in endoscopy","[{\"question\":\"What does the study evaluate about AI in gastric endoscopy?\",\"answer\":\"It assesses the diagnostic capability of AI-driven endoscopic systems for identifying submucosal (SM) invasion depth in gastric neoplasms using histopathology as the reference standard.\"},{\"question\":\"How were the included studies selected and analyzed?\",\"answer\":\"A PRISMA-DTA systematic review and meta-analysis identified studies using machine-learning or deep-learning models applied to endoscopic imaging, and 2×2 validation-set data were pooled with hierarchical models to estimate sensitivity, specificity, and AUC.\"},{\"question\":\"What performance did the AI systems achieve for predicting SM invasion?\",\"answer\":\"Across seven studies with sufficient data, AI systems showed pooled sensitivity of 0.75 and specificity of 0.84, with high discriminatory ability (AUC = 0.87).\"},{\"question\":\"Why might external validation results differ from internal validation?\",\"answer\":\"The review reports that externally validated models had lower sensitivity than internally validated models (0.72 vs. 0.79), indicating potential overfitting. It also notes regional differences in specificity.\"}]","Artificial intelligence in endoscopic prediction of submucosal invasion in gastric neoplasms: systematic review and meta-analysis | PDF",1790129814,28,[152,156,160,164],{"page_no":22,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/185fb64f7e0210de7f9910ccaaf10c01.webp",983,1310,{"page_no":26,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/311d2b944d30e2dbe08ab68f56a11b5a.webp",982,1309,{"page_no":30,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b775087e0ee78132295070528dd271c3.webp",981,1308,{"page_no":33,"url":165,"width":166,"height":167},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0a1905ef6de50ca3515a7986ee37d989.webp",980,1306]