BPG is committed to discovery and dissemination of knowledge
Review
Copyright ©The Author(s) 2026. Published by Baishideng Publishing Group Inc. All rights reserved.
Artif Intell Gastroenterol. Jan 8, 2026; 7(1): 115498
Published online Jan 8, 2026. doi: 10.35712/aig.v7.i1.115498
Multimodal artificial intelligence integrates imaging, endoscopic, and omics data for intelligent decision-making in individualized gastrointestinal tumor treatment
Hui Nian, Yi-Bin Wu, Yu Bai, Zhi-Long Zhang, Xiao-Huang Tu, Qi-Zhi Liu, De-Hua Zhou, Qian-Cheng Du
Hui Nian, Zhi-Long Zhang, Qian-Cheng Du, Department of Thoracic Surgery, Shanghai Xuhui Central Hospital, Shanghai 200031, China
Yi-Bin Wu, Yu Bai, Department of Intensive Care Unit, Shanghai Xuhui Central Hospital, Shanghai 200031, China
Xiao-Huang Tu, Qi-Zhi Liu, De-Hua Zhou, Department of Gastrointestinal Surgery, Shanghai Fourth People’s Hospital Affiliated to Tongji University School of Medicine, Shanghai 200434, China
Co-corresponding authors: De-Hua Zhou and Qian-Cheng Du.
Author contributions: Nian H contributed to project conception, research design, drafting the initial manuscript, and project administration; Bai Y contributed to methodology design, formal analysis, literature curation, and critical review and revision of the manuscript; Zhang ZL and Wu YB conducted literature investigation and visualization, including figure preparation; Tu XH and Liu QZ provided resources, software support, and performed experimental validation; Zhou DH oversaw the entire research process and contributed to manuscript revision and finalization; Du QC served as the corresponding author, providing overall supervision, performing key revisions, and giving final approval of the manuscript; all authors have read and approved the final version of the manuscript. In this study, Zhou DH and Du QC are designated as co-corresponding authors for the following reasons. First, Zhou DH oversaw the entire research process, including project conception and design, data integration, and manuscript revision and finalization, thereby ensuring the methodological rigor and scientific validity of the work. Du QC also provided comprehensive oversight, contributed critical intellectual revisions, and gave final approval of the version to be published, playing a pivotal role in maintaining the manuscript’s academic quality and guiding it through the publication process. Second, the author contribution statement explicitly indicates that both "contributed equally," reflecting their parallel engagement in leadership, cross-departmental coordination-particularly between thoracic surgery and intensive care-and the integration of multi-center data. This co-corresponding arrangement not only reinforces shared accountability but also enhances transparency in interdisciplinary collaboration, aligns with international journal standards regarding corresponding authorship, and supports the credibility and reproducibility of the findings. In conclusion, the joint corresponding authorship reflects their indispensable academic leadership and equivalent scholarly contributions, thereby upholding the integrity and ethical standards of the research.
Supported by Xuhui District Health Commission, No. SHXH202214.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Qian-Cheng Du, MD, Department of Thoracic Surgery, Shanghai Xuhui Central Hospital, No. 366 Longchuan North Road, Xuhui District, Shanghai 200031, China. duqc1991106@sina.com
Received: October 20, 2025
Revised: November 4, 2025
Accepted: December 18, 2025
Published online: January 8, 2026
Processing time: 80 Days and 18.1 Hours
Abstract

Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity. Multimodal artificial intelligence (AI) addresses this challenge by integrating diverse data sources-including computed tomography (CT), magnetic resonance imaging (MRI), endoscopic imaging, and genomic profiles-to enable intelligent decision-making for individualized therapy. This approach leverages AI algorithms to fuse imaging, endoscopic, and omics data, facilitating comprehensive characterization of tumor biology, prediction of treatment response, and optimization of therapeutic strategies. By combining CT and MRI for structural assessment, endoscopic data for real-time visual inspection, and genomic information for molecular profiling, multimodal AI enhances the accuracy of patient stratification and treatment personalization. The clinical implementation of this technology demonstrates potential for improving patient outcomes, advancing precision oncology, and supporting individualized care in gastrointestinal cancers. Ultimately, multimodal AI serves as a transformative tool in oncology, bridging data integration with clinical application to effectively tailor therapies.

Keywords: Multimodal artificial intelligence; Gastrointestinal tumors; Individualized therapy; Intelligent diagnosis; Treatment optimization; Prognostic prediction; Data fusion; Deep learning; Precision medicine

Core Tip: This review highlights that multimodal artificial intelligence (AI), by integrating imaging, endoscopic, and multi-omics data, is revolutionizing the intelligent decision-making process for individualized gastrointestinal tumor therapy. It enhances precision across the entire clinical spectrum-from improving early detection and accurate staging, to optimizing treatment planning and prognostic assessment. The key to its success lies in effectively addressing challenges related to data fusion, model interpretability, and multicenter validation. Ultimately, multimodal AI serves as a pivotal translational bridge, connecting complex data analysis with actionable clinical insights to advance precision oncology.