{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T06:12:52Z","timestamp":1788502372353,"version":"build-2803163510"},"reference-count":39,"publisher":"BMJ","issue":"8","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"unspecified","delay-in-days":18,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Open Research Fund of the Shanghai Key Lab of Intelligent Information Processing","award":["IIPL-2026-STU-02"],"award-info":[{"award-number":["IIPL-2026-STU-02"]}]},{"name":"Baoshan District Health Commission Key Subject Construction Project","award":["BSZK-2023-A03"],"award-info":[{"award-number":["BSZK-2023-A03"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,8,4]]},"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>A substantial proportion of adults with locally advanced gastric cancer derive limited benefit from neoadjuvant chemotherapy (NAC), with a non-response rate of 30%\u201350%. Artificial intelligence (AI) models that integrate imaging, pathology and clinical data seek to predict pretreatment NAC response to guide decision-making. We conducted a systematic review and meta-analysis to evaluate the predictive performance of AI models for NAC response in adults with gastric cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Systematic review and meta-analysis in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Data sources<\/jats:title>\n                    <jats:p>PubMed, Embase, Scopus, Web of Science and ScienceDirect were searched from inception to 30 June 2025, without language restrictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Eligibility criteria<\/jats:title>\n                    <jats:p>Studies that developed or internally\/externally validated AI models (deep learning or non-linear machine learning) to predict NAC response in adults (\u226518 years) with gastric cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Data extraction and synthesis<\/jats:title>\n                    <jats:p>Data extraction followed the CHARMS (CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies) checklist. Model quality and risk of bias were appraised with the Prediction Model Study Risk of Bias Assessment Tool for AI (PROBAST+AI). Where two or more independent validation datasets reported outcomes\u2014preferably mappable to major pathological response (tumour regression grading 0\u20131\/Becker 1a\u20131b)\u2014we pooled area under the receiver operating characteristic curve (AUC) using random-effects models and quantified heterogeneity with I\u00b2. Certainty of evidence was graded with the Grading of Recommendations Assessment, Development and Evaluation (GRADE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>17 studies met inclusion criteria; 16 (94%) were conducted in China and nine were multicentre. 14 cohorts contributed to internal-validation meta-analyses and 10 to external-validation meta-analyses. Pooled AUC was 0.844 (95% CI 0.812 to 0.877, I\u00b2=17.3%) for internal validation and 0.812 (95% CI 0.775 to 0.848, I\u00b2=52.9%) for external validation. Subgroup analysis indicated that data type was the strongest modifier of pooled area under the curve in external validation (p=0.008, R\u00b2=99.8%). Only two studies directly compared AI models against traditional clinical prediction models with AUC (0.823, 95% CI 0.782 to 0.863 vs 0.598, 95% CI 0.521 to 0.675). By PROBAST+AI, all 17 studies raised high or unclear concerns regarding development quality (13 high, 4 unclear), and risk of bias in evaluation was high in 12 studies, low in 2, and unclear in 3. GRADE-rated certainty of evidence was low for internal validation and very low for external validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Across 17 studies, AI models demonstrated moderate to good discrimination for predicting NAC response in gastric cancer, with pooled AUCs of 0.844 (95% CI 0.812 to 0.877) for internal validation and 0.812 (95% CI 0.775 to 0.848) for external validation. Model-methodology subgroup analyses did not demonstrate robust differences between deep learning and machine-learning approaches, and AI models significantly outperformed traditional clinical assessment. However, GRADE-rated certainty of evidence was low for internal validation and very low for external validation, reflecting high risk of bias on PROBAST+AI, limited external validation, and geographic concentration of studies (16\/17 from China). Pending prospective, multicentre evaluation with harmonised endpoints and routine calibration and decision-curve reporting, these models should serve as decision-support tools rather than standalone arbiters of care.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>PROSPERO registration number<\/jats:title>\n                    <jats:p>CRD420251025470.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-111047","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T12:00:15Z","timestamp":1787227215000},"page":"e111047","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence-driven prediction of neoadjuvant chemotherapy response in adult patients with gastric cancer: a systematic review and meta-analysis"],"prefix":"10.1136","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7800-154X","authenticated-orcid":false,"given":"Yuntian","family":"Deng","sequence":"first","affiliation":[{"name":"Department of General Surgery, Zhongshan Hospital Fudan University, Shanghai, China"},{"name":"Department of General Surgery, GI Surgery, Zhongshan Hospital Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anran","family":"Bao","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Zhongshan Hospital Fudan University, Shanghai, China"},{"name":"Department of General Surgery, GI Surgery, Zhongshan Hospital Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongshan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Zhongshan Hospital Fudan University, Shanghai, China"},{"name":"Department of General Surgery, GI Surgery, Zhongshan Hospital Fudan University, Shanghai, China"},{"name":"Department of General Surgery, Zhongshan Hospital Wusong Branch, Shanghai, China"},{"name":"Baoshan Cancer Center, Shanghai, China"},{"name":"Shanghai Key Laboratory of Intelligent Information Processing, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"2026090322302106000_16.8.e111047.1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21820"},{"key":"2026090322302106000_16.8.e111047.2","unstructured":"National Comprehensive Cancer Network (NCCN) . NCCN clinical practice guidelines in oncology: gastric cancer. NCCN; 2024."},{"key":"2026090322302106000_16.8.e111047.3","unstructured":"Lordick F , Candia Montero L , Castelo-Branco L , et al . ESMO gastric cancer living guideline v1.4. 2024. Available: https:\/\/www.esmo.org\/living-guidelines\/esmo-gastric-cancer-living-guideline"},{"key":"2026090322302106000_16.8.e111047.4","unstructured":"Chinese Society of Clinical Oncology (CSCO) . Guidelines for the diagnosis and treatment of gastric cancer. CSCO; 2024."},{"key":"2026090322302106000_16.8.e111047.5","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1002\/ags3.12717","article-title":"Neoadjuvant chemotherapy for locally advanced gastric cancer in Japan: Consensus meeting at the 77th general meeting of the Japanese Society of Gastroenterological Surgery","volume":"7","author":"Tokunaga","year":"2023","journal-title":"Annals of Gastroent Surgery"},{"key":"2026090322302106000_16.8.e111047.6","doi-asserted-by":"crossref","DOI":"10.1016\/j.xcrm.2023.100931","article-title":"Multiplex immune profiling reveals the role of serum immune proteomics in predicting response to preoperative chemotherapy of gastric cancer","volume":"4","author":"Tang","year":"2023","journal-title":"Cell Rep Med"},{"key":"2026090322302106000_16.8.e111047.7","doi-asserted-by":"publisher","DOI":"10.1007\/s10120-022-01331-8"},{"key":"2026090322302106000_16.8.e111047.8","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.crad.2023.08.023","article-title":"Value of spectral CT parameters in predicting the efficacy of neoadjuvant chemotherapy for gastric cancer","volume":"79","author":"Deng","year":"2024","journal-title":"Clin Radiol"},{"key":"2026090322302106000_16.8.e111047.9","doi-asserted-by":"crossref","first-page":"1437252","DOI":"10.3389\/fonc.2024.1437252","article-title":"Applications of artificial intelligence in digital pathology for gastric cancer","volume":"14","author":"Chen","year":"2024","journal-title":"Front Oncol"},{"key":"2026090322302106000_16.8.e111047.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06221-2"},{"key":"2026090322302106000_16.8.e111047.11","doi-asserted-by":"crossref","DOI":"10.3390\/ijms252111588","article-title":"Recent Advances in Artificial Intelligence to Improve Immunotherapy and the Use of Digital Twins to Identify Prognosis of Patients with Solid Tumors","volume":"25","author":"D\u2019Orsi","year":"2024","journal-title":"Int J Mol Sci"},{"key":"2026090322302106000_16.8.e111047.12","doi-asserted-by":"crossref","DOI":"10.1186\/s12935-025-03756-4","article-title":"The artificial intelligence revolution in gastric cancer management: clinical applications","volume":"25","author":"Li","year":"2025","journal-title":"Cancer Cell Int"},{"key":"2026090322302106000_16.8.e111047.13","first-page":"1980","article-title":"Deep learning radio-clinical signatures for predicting neoadjuvant chemotherapy response and prognosis from pretreatment CT images of locally advanced gastric cancer patients","volume":"109","author":"Hu","year":"2023","journal-title":"Int J Surg"},{"key":"2026090322302106000_16.8.e111047.14","doi-asserted-by":"crossref","DOI":"10.1016\/j.xcrm.2023.101146","article-title":"Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics","volume":"4","author":"Jiang","year":"2023","journal-title":"Cell Rep Med"},{"key":"2026090322302106000_16.8.e111047.15","doi-asserted-by":"crossref","first-page":"7019","DOI":"10.1038\/s41598-023-34291-9","article-title":"Use of machine learning-based integration to develop an immune-related signature for improving prognosis in patients with gastric cancer","volume":"13","author":"Ning","year":"2023","journal-title":"Sci Rep"},{"key":"2026090322302106000_16.8.e111047.16","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-21-0090"},{"key":"2026090322302106000_16.8.e111047.17","doi-asserted-by":"crossref","first-page":"2339","DOI":"10.1007\/s00432-020-03304-9","article-title":"Artificial intelligence in gastric cancer: a systematic review","volume":"146","author":"Jin","year":"2020","journal-title":"J Cancer Res Clin Oncol"},{"key":"2026090322302106000_16.8.e111047.18","doi-asserted-by":"crossref","DOI":"10.1136\/bmjonc-2023-000255","article-title":"Prospective evaluation of artificial intelligence (AI) applications for use in cancer pathways following diagnosis: a systematic review","volume":"3","author":"Macheka","year":"2024","journal-title":"BMJ Oncol"},{"key":"2026090322302106000_16.8.e111047.19","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1001744","article-title":"Critical appraisal and data extraction for systematic reviews of prediction modelling studies: the CHARMS checklist","volume":"11","author":"Moons","year":"2014","journal-title":"PLoS Med"},{"key":"2026090322302106000_16.8.e111047.20","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"2026090322302106000_16.8.e111047.21","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2024-082505","article-title":"PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","year":"2025","journal-title":"BMJ"},{"key":"2026090322302106000_16.8.e111047.22","doi-asserted-by":"publisher","DOI":"10.1177\/0962280218785504"},{"key":"2026090322302106000_16.8.e111047.23","doi-asserted-by":"crossref","first-page":"758863","DOI":"10.3389\/fonc.2022.758863","article-title":"CT-Based Radiomics Showing Generalization to Predict Tumor Regression Grade for Advanced Gastric Cancer Treated With Neoadjuvant Chemotherapy","volume":"12","author":"Chen","year":"2022","journal-title":"Front Oncol"},{"key":"2026090322302106000_16.8.e111047.24","doi-asserted-by":"crossref","DOI":"10.1016\/j.eclinm.2022.101348","article-title":"A CT-based deep learning radiomics nomogram for predicting the response to neoadjuvant chemotherapy in patients with locally advanced gastric cancer: A multicenter cohort study","volume":"46","author":"Cui","year":"2022","journal-title":"EClinicalMedicine"},{"key":"2026090322302106000_16.8.e111047.25","doi-asserted-by":"crossref","DOI":"10.1016\/j.xcrm.2024.101848","article-title":"Interpretable multi-modal artificial intelligence model for predicting gastric cancer response to neoadjuvant chemotherapy","volume":"5","author":"Gao","year":"2024","journal-title":"Cell Rep Med"},{"key":"2026090322302106000_16.8.e111047.26","doi-asserted-by":"crossref","DOI":"10.1186\/s13244-022-01273-w","article-title":"Enhanced CT-based radiomics predicts pathological complete response after neoadjuvant chemotherapy for advanced adenocarcinoma of the esophagogastric junction: a two-center study","volume":"13","author":"Huang","year":"2022","journal-title":"Insights Imaging"},{"key":"2026090322302106000_16.8.e111047.27","doi-asserted-by":"crossref","DOI":"10.3390\/cancers16132445","article-title":"Deep Learning Histology for Prediction of Lymph Node Metastases and Tumor Regression after Neoadjuvant FLOT Therapy of Gastroesophageal Adenocarcinoma","volume":"16","author":"Jung","year":"2024","journal-title":"Cancers (Basel)"},{"key":"2026090322302106000_16.8.e111047.28","doi-asserted-by":"crossref","DOI":"10.1177\/20552076251341740","article-title":"Predicting neoadjuvant chemotherapy response in locally advanced gastric cancer using a machine learning model combining radiomics and clinical biomarkers","volume":"11","author":"Ling","year":"2025","journal-title":"Digit Health"},{"key":"2026090322302106000_16.8.e111047.29","doi-asserted-by":"crossref","DOI":"10.1186\/s13244-023-01584-6","article-title":"Intratumoral and peritumoral radiomics predict pathological response after neoadjuvant chemotherapy against advanced gastric cancer","volume":"15","author":"Liu","year":"2024","journal-title":"Insights Imaging"},{"key":"2026090322302106000_16.8.e111047.30","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.radonc.2022.04.023","article-title":"CT-based radiomics analysis in the prediction of response to neoadjuvant chemotherapy in locally advanced gastric cancer: A dual-center study","volume":"171","author":"Song","year":"2022","journal-title":"Radiother Oncol"},{"key":"2026090322302106000_16.8.e111047.31","doi-asserted-by":"crossref","DOI":"10.1186\/s12885-020-06970-7","article-title":"CT-based radiomics scores predict response to neoadjuvant chemotherapy and survival in patients with gastric cancer","volume":"20","author":"Sun","year":"2020","journal-title":"BMC Cancer"},{"key":"2026090322302106000_16.8.e111047.32","doi-asserted-by":"crossref","unstructured":"Wu J , Wang Q , Wang Z , et al . AutoBRB: An automated belief rule base model for pathologic complete response prediction in gastric cancer. Comput Biol Med 2022;105104. doi:10.1016\/j.compbiomed.2021.105104","DOI":"10.1016\/j.compbiomed.2021.105104"},{"key":"2026090322302106000_16.8.e111047.33","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2021.770758","article-title":"Pretreatment Contrast-Enhanced Computed Tomography Radiomics for Prediction of Pathological Regression Following Neoadjuvant Chemotherapy in Locally Advanced Gastric Cancer: A Preliminary Multicenter Study","volume":"11","author":"Xie","year":"2021","journal-title":"Front Oncol"},{"key":"2026090322302106000_16.8.e111047.34","doi-asserted-by":"crossref","first-page":"8765","DOI":"10.1007\/s00330-021-07962-2","article-title":"Advanced gastric cancer: CT radiomics prediction and early detection of downstaging with neoadjuvant chemotherapy","volume":"31","author":"Xu","year":"2021","journal-title":"Eur Radiol"},{"key":"2026090322302106000_16.8.e111047.35","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1007\/s10120-022-01328-3","article-title":"Deep learning predicts resistance to neoadjuvant chemotherapy for locally advanced gastric cancer: a multicenter study","volume":"25","author":"Zhang","year":"2022","journal-title":"Gastric Cancer"},{"key":"2026090322302106000_16.8.e111047.36","doi-asserted-by":"crossref","first-page":"4115","DOI":"10.4251\/wjgo.v16.i10.4115","article-title":"Computed tomography-based radiomic model for the prediction of neoadjuvant immunochemotherapy response in patients with advanced gastric cancer","volume":"16","author":"Zhang","year":"2024","journal-title":"World J Gastrointest Oncol"},{"key":"2026090322302106000_16.8.e111047.37","doi-asserted-by":"crossref","first-page":"3780","DOI":"10.1007\/s00261-024-04331-7","article-title":"Deep learning nomogram for predicting neoadjuvant chemotherapy response in locally advanced gastric cancer patients","volume":"49","author":"Zhang","year":"2024","journal-title":"Abdom Radiol"},{"key":"2026090322302106000_16.8.e111047.38","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1245\/s10434-023-14424-0","article-title":"Deep Learning Radiomics Nomogram Based on Enhanced CT to Predict the Response of Metastatic Lymph Nodes to Neoadjuvant Chemotherapy in Locally Advanced Gastric Cancer","volume":"31","author":"Zhong","year":"2024","journal-title":"Ann Surg Oncol"},{"key":"2026090322302106000_16.8.e111047.39","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1007\/s10120-023-01407-z","article-title":"Digital histopathological images of biopsy predict response to neoadjuvant chemotherapy for locally advanced gastric cancer","volume":"26","author":"Zhou","year":"2023","journal-title":"Gastric Cancer"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-111047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T05:30:40Z","timestamp":1788499840000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-111047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":39,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,19]]},"published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1136\/bmjopen-2025-111047"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-111047","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}