[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-355134-105":59,"doc-detail-355134-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","prommf_kron-a-multimodal-deep-learning-model-for-immunotherapy-response-prediction-in-stomach-adenocarcinoma","ProMMF_Kron: a multimodal deep learning model for immunotherapy response prediction in stomach adenocarcinoma","","Immune checkpoint inhibitor (ICI) therapy improves anti-tumor immunity, yet predicting individual patient response remains difficult due to immune-related adverse events. Microsatellite instability (MSI), a biomarker linked to high mutation burden and neoantigen production, can forecast immunotherapy benefit, but tools for gastric adenocarcinoma (STAD) are still needed. This study develops ProMMF_Kron, a two-stage multimodal model integrating molecular profiles and pathology images for MSI-versus-MSS discrimination and robust generalization.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/prommf_kron-a-multimodal-deep-learning-model-for-immunotherapy-response-prediction-in-stomach-adenocarcinoma/355134/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/prommf_kron-a-multimodal-deep-learning-model-for-immunotherapy-response-prediction-in-stomach-adenocarcinoma/355134.png","ImageObject",300,407,{"name":92,"@type":93},"Asher","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-27","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does ProMMF_Kron address in gastric adenocarcinoma immunotherapy?","Question",{"text":112,"@type":113},"It targets the challenge of accurately predicting patient response to immune checkpoint inhibitor (ICI) therapy, especially given the clinical risk of immune-related adverse events and the molecular heterogeneity in gastric adenocarcinoma.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does ProMMF_Kron combine molecular data and pathology images?",{"text":117,"@type":113},"It uses a two-stage feature fusion strategy: it extracts key features from molecular profiles and pathological images separately, then fuses them with a fusion architecture that incorporates Kronecker product operations and back-projection modules to enable interaction between gene-expression and image features.",{"name":119,"@type":110,"acceptedAnswer":120},"How well does the model perform at distinguishing MSI from MSS?",{"text":121,"@type":113},"Experimental results show strong discrimination between MSI and MSS, with an AUC of 0.96 (95% CI: 0.89–1.00) on independent test datasets, outperforming single-modality and other multimodal fusion approaches.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},355134,1790193043,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},687197207639,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","TYPE Original Research PUBLISHED 10 February 2026  \nDOI 10.3389/fimmu.2026.1602846  \nOPEN ACCESS  \nEDITED BY  \nArka Bhowmik,  \nMemorial Sloan Kettering Cancer Center, United States  \nREVIEWED BY  \nEmir Oncu,  \nYildiz Technical University, Türkiye Kanchi Doshi,  \nThakur College of Engineering and Technology, India  \n*CORRESPONDENCE  \nXiuqin Liu  \n [b0001428@ustb.edu.cn](b0001428@ustb.edu.cn)  \n†These authors have contributed equally to this work and share ﬁrst authorship  \nRECEIVED 30 March 2025  \nREVISED 10 October 2025  \nACCEPTED 19 January 2026  \nPUBLISHED 10 February 2026  \nCITATION  \nWang C, Liu W, Ai D and Liu X (2026)  \nProMMF_Kron: a multimodal deep learning model for immunotherapy response prediction in stomach adenocarcinoma. Front. Immunol. 17:1602846 .  \ndoi: 10.3389/fimmu.2026.1602846  \nCOPYRIGHT  \n© 2026 Wang, Liu, Ai and Liu. This is an openaccess article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nProMMF_Kron: a multimodal deep learning model for immunotherapy response prediction in stomach adenocarcinoma  \nChenchen Wang †, Weikun Liu †, Dongmei Ai and Xiuqin Liu* School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, China  \nBackground: Immune checkpoint inhibitor (ICI) therapy has signiﬁcantly improved treatment outcomes for various cancers by enhancing T cellmediated anti-tumor immune responses . However, accurately predicting patient response to ICI treatment remains a major challenge due to the risk of immune-related adverse events. Microsatellite instability (MSI), as an important molecular biomarker characterized by high mutation rates and abundant tumor neoantigen production, has been demonstrated to effectively predict clinical beneﬁts from immunotherapy. In gastric adenocarcinoma (STAD) patients, approximately 22% exhibit the MSI subtype while the majority are microsatellite stable (MSS) . This signiﬁcant molecular heterogeneity underscores the urgent need to develop reliable predictive tools.  \nMethods: To address this problem, we developed a multimodal deep learning model named ProMMF_Kron based on a multicenter dataset comprising 282 patients. The model employs a two stage feature fusion strategy: ﬁrst extracting key features from both molecular proﬁles and pathological images through differential gene analysis and a pretrained deep convolutional neural network, respectively; then designing a sophisticated fusion architecture incorporating Kronecker product operations and back-projection modules to achieve efﬁcient interaction between gene expression features and pathological image features. The dataset was partitioned into training, validation, and testing sets at a ratio of 6:2:2 .  \nResults: Experimental results demonstrate that the ProMMF_Kron model effectively distinguishes between MSI and MSS subtypes (MSI versus MSS) and exhibits competitive predictive performance on independent test datasets, achieving an AUC of 0.96 (95% CI: 0.89-1.00), outperforming traditional single-modality prediction models (3.2% AUC improvement) and other multimodal fusion approaches (4 . 3% AUC improvement) . Further validation conﬁrms the model ’ s excellent stability and generalization capability, maintaining high predictive accuracy on colorectal cancer (CRC) dataset.  \nFrontiers in Immunology 01 [frontiersin.org](frontiersin.org)  \nDiscussion: Through bioinformatics analysis and feature visualization techniques, this study also reveals potential associations between key molecular biomarkers and critical immune regulatory pathways, providing a powerful decision-support tool for precision immunotherapy in gastr","cbCaiuilswYvMvD4","https://ap.wps.com/l/cbCaiuilswYvMvD4","pdf",4952682,13,"English","# Background\n## Immune checkpoint inhibition and response prediction challenges\n## MSI as a biomarker in gastric adenocarcinoma\n# Methods\n## ProMMF_Kron model design and two-stage feature fusion\n## Data partitioning strategy\n# Results\n## MSI vs MSS discrimination performance\n## Validation, stability, and external generalization\n# Discussion\n## Biomarker associations and decision-support value\n## Clinical translation potential","[{\"question\":\"What problem does ProMMF_Kron address in gastric adenocarcinoma immunotherapy?\",\"answer\":\"It targets the challenge of accurately predicting patient response to immune checkpoint inhibitor (ICI) therapy, especially given the clinical risk of immune-related adverse events and the molecular heterogeneity in gastric adenocarcinoma.\"},{\"question\":\"How does ProMMF_Kron combine molecular data and pathology images?\",\"answer\":\"It uses a two-stage feature fusion strategy: it extracts key features from molecular profiles and pathological images separately, then fuses them with a fusion architecture that incorporates Kronecker product operations and back-projection modules to enable interaction between gene-expression and image features.\"},{\"question\":\"How well does the model perform at distinguishing MSI from MSS?\",\"answer\":\"Experimental results show strong discrimination between MSI and MSS, with an AUC of 0.96 (95% CI: 0.89–1.00) on independent test datasets, outperforming single-modality and other multimodal fusion approaches.\"}]","ProMMF_Kron: a multimodal deep learning model for immunotherapy response prediction in stomach adenocarcinoma | PDF",1790116263,33,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/74e28b0e0610a546d246f42ef02dbd22.webp",983,1389,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/96a7cbdb8abd4e2035d00fa73fc9e5a4.webp",982,1388,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/28108d391de8f83a0460b4e900a66862.webp",981,1386,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1350635d7c89544795f075069b42f134.webp",980,1385]