{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:09:29Z","timestamp":1792084169712,"version":"4.4.0"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>\n                      Gastric cancer (GC) remains a major public health concern in Asia. Risk prediction tailored to regional biological features such as\n                      <jats:italic>Helicobacter pylori<\/jats:italic>\n                      (\n                      <jats:italic>H. pylori<\/jats:italic>\n                      ) status and high-risk mucosal findings such as atrophic gastritis (AG) and intestinal metaplasia (IM) may help improve the screening workflow.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using a large, real-world, nationwide screening cohort with available endoscopic AG\/IM codes, we developed 2-year GC risk prediction models that integrate AG\/IM with regional demographic and lifestyle factors. We compared a conventional Cox proportional hazards model (CPHM) with the following machine learning (ML) approaches: extreme gradient boosting (XGBoost), decision tree (DT), and logistic regression (LR). Discrimination and calibration were evaluated through internal and external validations. Model interpretability was assessed using Shapley Additive Explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The XGBoost model demonstrated the best overall performance, achieving an AUROC of 0.764 (95% CI, 0.755\u20130.767), a sensitivity of 0.607 (95% CI, 0.560\u20130.650), and a specificity of 0.746 (95% CI, 0.744\u20130.750) in the internal validation. In the external validation cohort, XGBoost also showed the highest discrimination with an AUROC of 0.708 (95% CI, 0.682\u20130.884), a sensitivity of 0.666 (95% CI, 0.470\u20130.830), and a specificity of 0.597 (95% CI, 0.590\u20130.600). SHAP analysis consistently identified Helicobacter pylori infection, age, sex, smoking, and atrophic gastritis\/intestinal metaplasia (AG\/IM) as the major contributors to increased predicted gastric cancer risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This externally validated and interpretable short-term GC risk model incorporating endoscopically ascertained AG\/IM could provide a practical approach for informing risk-adapted screening workflows. The model could help identify individuals at a higher predicted risk for prospective evaluation and closer clinical review. In addition, SHAP clarifies the main contributors to each prediction by highlighting factors most strongly associated with a higher predicted risk.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1732072","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T05:22:46Z","timestamp":1773638566000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SHAP-explained machine-learning model for high-risk gastric cancer identification"],"prefix":"10.3389","volume":"16","author":[{"given":"Hyun Jin","family":"Oh","sequence":"first","affiliation":[{"name":"Division of Gastroenterology, Department of Internal Medicine, Center for Cancer Prevention and Detection, National Cancer Center","place":["Goyang, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung Ho","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine, College of Medicine, Chung-Ang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae Kwan","family":"Jun","sequence":"additional","affiliation":[{"name":"National Cancer Control Institute, National Cancer Center","place":["Goyang, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mina","family":"Suh","sequence":"additional","affiliation":[{"name":"National Cancer Control Institute, National Cancer Center","place":["Goyang, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kui Son","family":"Choi","sequence":"additional","affiliation":[{"name":"National Cancer Control Institute, National Cancer Center","place":["Goyang, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Il Ju","family":"Choi","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology, Department of Internal Medicine, Center for Gastric Cancer, National Cancer Center","place":["Goyang, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bomi","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine, College of Medicine, Chung-Ang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA: A Cancer J For Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.gtc.2013.01.002","article-title":"Gastric cancer: overview","volume":"42","author":"Correa","year":"2013","journal-title":"Gastroenterol Clinics North America"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1097\/00042737-200608000-00004","article-title":"Early diagnosis of early gastric cancer","volume":"18","author":"Tan","year":"2006","journal-title":"Eur J Gastroenterol Hepatol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2017.01.029","article-title":"Effectiveness of the Korean National Cancer Screening Program in reducing gastric cancer mortality","volume":"152","author":"Jun","year":"2017","journal-title":"Gastroenterology"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.lanwpc.2023.100741","article-title":"Radiographic and endoscopic screening to reduce gastric cancer mortality: a systematic review and meta-analysis","volume":"35","author":"Hibino","year":"2023","journal-title":"Lancet Regional Health\u2013Western Pacific"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2024.11.001","article-title":"AGA clinical practice update on screening and surveillance in individuals at increased risk for gastric cancer in the United States: expert review","volume":"168","author":"Shah","year":"2025","journal-title":"Gastroenterology"},{"key":"B7","article-title":"Human gastric carcinogenesis: a multistep and multifactorial process\u2014first American Cancer Society award lecture on cancer epidemiology and prevention","volume":"52","author":"Correa","year":"1992","journal-title":"Cancer Res"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.4143\/crt.2023.447","article-title":"Cancer statistics in Korea: incidence, mortality, survival, and prevalence in 2020","volume":"55","author":"Kang","year":"2023","journal-title":"Cancer Res Treatment: Off J Korean Cancer Assoc"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2024.11.001","article-title":"AGA clinical practice update on screening and surveillance in individuals at increased risk for gastric cancer in the United States: expert review","volume":"168","author":"Shah","year":"2024","journal-title":"Gastroenterology"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1055\/a-2529-5025","article-title":"Management of epithelial precancerous conditions and early neoplasia of the stomach (MAPS III): European Society of Gastrointestinal Endoscopy (ESGE), European Helicobacter and Microbiota Study Group (EHMSG) and European Society of Pathology (ESP) Guideline update 2025","volume":"57","author":"Dinis-Ribeiro","year":"2025","journal-title":"Endoscopy"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.7704\/kjhugr.2024.0039","article-title":"Performance of the national cancer screening program for gastric cancer in Korea","volume":"24","author":"Kim","year":"2024","journal-title":"Korean J Helicobacter Up Gastrointest Res"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2025.40.e43","article-title":"Cost utility analysis of national cancer screening program for gastric cancer in Korea: A Markov model analysis","volume":"40","author":"Bae","year":"2025","journal-title":"J Korean Med Sci"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.4093\/dmj.2022.0193","article-title":"Current trends of big data research using the Korean National Health Information Database","volume":"46","author":"Kim","year":"2022","journal-title":"Diabetes Metab J"},{"key":"B14","volume-title":"National health screening statistics","year":""},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","author":"He","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"B17","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10462-024-10759-6","article-title":"A survey on imbalanced learning: latest research, applications and future directions","volume":"57","author":"Chen","year":"2024","journal-title":"Artif Intell Rev"},{"key":"B18","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1080\/24699322.2019.1649074","article-title":"Clustering-based undersampling with random over sampling examples and support vector machine for imbalanced classification of breast cancer diagnosis","volume":"24","author":"Zhang","year":"2019","journal-title":"Comput Assisted Surg"},{"key":"B19","first-page":"17","volume-title":"The Asia-Pacific perspective: Redefining obesity and its treatment","year":"2000"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1016\/S0140-6736(04)15856-X","article-title":"Appropriate BMI for Asian populations","volume":"363","author":"Shiwaku","year":"2004","journal-title":"Lancet"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab501","article-title":"Stable iterative variable selection","volume":"37","author":"Mahmoudian","year":"2021","journal-title":"Bioinformatics"},{"key":"B22","first-page":"1","article-title":"Model-agnostic interpretability with shapley values","author":"Messalas","year":"2019"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1080\/14737159.2023.2277377","article-title":"A systematic review and meta-analysis on the relative and attributable risk of Helicobacter pylori infection and cardia and non-cardia gastric cancer","volume":"23","author":"Gu","year":"2023","journal-title":"Expert Rev Mol Diagn"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03793-6","article-title":"Global lifetime estimates of expected and preventable gastric cancers across 185 countries","volume":"31","author":"Park","year":"2025","journal-title":"Nat Med"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2019.12.001","article-title":"AGA technical review on gastric intestinal metaplasia-natural history and clinical outcomes","volume":"158","author":"Gawron","year":"2020","journal-title":"Gastroenterol."},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1136\/jcp.2003.11270","article-title":"A follow up model for patients with atrophic chronic gastritis and intestinal metaplasia","volume":"57","author":"Dinis-Ribeiro","year":"2004","journal-title":"J Clin Pathol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3390\/pr11082324","article-title":"Critical analysis of risk factors and machine-learning-based gastric cancer risk prediction models: A systematic review","volume":"11","author":"Fan","year":"2023","journal-title":"Processes"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1732072\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T05:22:48Z","timestamp":1773638568000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1732072\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":27,"alternative-id":["10.3389\/fonc.2026.1732072"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1732072","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"article-number":"1732072"}}