{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T23:43:41Z","timestamp":1786146221823,"version":"build-2736575974"},"reference-count":36,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n \n Gastric cancer (GC) is one of the most common malignant tumors worldwide, with\n Helicobacter pylori<\/jats:italic>\n \u2013associated intestinal-type gastric cancer (IGC) being the most prevalent subtype, accounting for approximately 85% of cases. Because most patients are diagnosed at intermediate or advanced stages, early screening and accurate stage stratification of IGC progression remain major clinical challenges.\n <\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop an interpretable machine learning (ML) model that leverages routine laboratory indicators to perform stage-specific diagnosis for patients across different stages of IGC.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Data from 2180 patients with known\n H pylori<\/jats:italic>\n infection status were collected at 2 centers and included healthy controls (HCs), nonatrophic gastritis, atrophic gastritis, intestinal metaplasia, and GC. After excluding cases with severe (>25%) missing data, 1784 patients were included for model development and validation. Data imputation and feature selection were performed, and synthetic minority oversampling technique (SMOTE) augmentation was applied to the internal training dataset to improve the diagnostic performance of the model. Six ML algorithms were developed. Model performance and clinical decision-making utility were evaluated using multiple metrics and approaches, while Shapley Additive Explanations (SHAP)\u2013based interpretability was used to identify key indicators and provide threshold reference values for them. Finally, a web-based tool was developed based on the Streamlit platform.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Through feature selection, 27 features were ultimately retained for final model construction. Among the 6 algorithms, CatBoost (categorical boosting) demonstrated the best performance, achieving an internal validation accuracy of 80.91%, sensitivity of 78.57%, and specificity of 95.27%. In the Guangdong Provincial People\u2019s Hospital (GDPH) and Shengli Oilfield Central Hospital (SOCH) external validation cohorts, CatBoost maintained robust performance, with accuracies of 79.96% and 83.37%, sensitivities of 76.82% and 84.91%, specificities of 93.14% and 95.73%, and area under the curves (AUCs) of 0.94 and 0.97, respectively. Confusion matrix analysis showed that the model was particularly reliable in identifying extreme disease states, including HCs and GC, whereas misclassifications mainly occurred between adjacent intermediate pathological stages. Calibration curves and Brier scores indicated good agreement between predicted and observed outcomes. Decision curve analysis (DCA) further confirmed the clinical net benefit across relevant threshold ranges. SHAP-based interpretability analysis identified monocyte count (MONO%), albumin\/globulin ratio (A\/G), basophil percentage (BASO%), platelet distribution width (PDW), total bilirubin (DBIL), neutrophil count (NEUT#), age, lymphocyte count (LYMPH#), creatinine (CREA), and aspartate aminotransferase (AST) as important contributors, reflecting inflammatory, hematological, nutritional, and metabolic changes during IGC progression. Based on these features, a lightweight predictive model was developed and deployed as a web-based application to facilitate translational and practical applications.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n \n This study developed an interpretable ML model based on routine laboratory data for stage-specific prediction of\n H pylori<\/jats:italic>\n \u2013associated IGC progression, with promising applicability as an auxiliary diagnostic tool.\n <\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/94837","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T23:11:46Z","timestamp":1786144306000},"page":"e94837-e94837","source":"Crossref","is-referenced-by-count":0,"title":["Development and Validation of an Interpretable Machine Learning Model for Staging Helicobacter pylori\u2013Initiated Intestinal-Type Gastric Cancer in the Correa Cascade: Cross-Sectional Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4656-2995","authenticated-orcid":false,"given":"Jiawei","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6983-4425","authenticated-orcid":false,"given":"Huijin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5889-592X","authenticated-orcid":false,"given":"Wenwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9705-4010","authenticated-orcid":false,"given":"Alfred Chin Yen","family":"Tay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4853-5015","authenticated-orcid":false,"given":"Barry J","family":"Marshall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9245-0356","authenticated-orcid":false,"given":"Cong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5339-7484","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"issue":"7","key":"R1","doi-asserted-by":"publisher","first-page":"4854","DOI":"10.1097\/JS9.0000000000002464","article-title":"Trends and projections of the burden of gastric cancer in China and G20 countries: a comparative study based on the Global Burden of Disease database 2021","volume":"111","author":"Yang","journal-title":"Int J Surg"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.jncc.2024.01.006","article-title":"Cancer incidence and mortality in China, 2022","volume":"4","author":"Han","journal-title":"J Natl Cancer Cent"},{"issue":"24","key":"R3","first-page":"6735","volume":"52","author":"Correa","journal-title":"Cancer Res"},{"issue":"10","key":"R4","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1136\/gutjnl-2013-306253","article-title":"CCL20\/CCR6-mediated migration of regulatory T cells to the Helicobacter pylori-infected human gastric mucosa","volume":"63","author":"Cook","journal-title":"Gut"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-025-04310-9","article-title":"Deep learning-aided optical biopsy achieves whole-chain diagnosis of Correa cascade of gastric cancer: a prospective study","volume":"23","author":"Liu","journal-title":"BMC Med"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1186\/s12876-025-03898-9","article-title":"Unveiling gastric precancerous stages: metabolomic insights for early detection and intervention","volume":"25","author":"Zhang","journal-title":"BMC Gastroenterol"},{"issue":"9","key":"R7","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1055\/s-0034-1392882","article-title":"Endoscopic submucosal dissection: European Society of Gastrointestinal Endoscopy (ESGE) guideline","volume":"47","author":"Pimentel-Nunes","journal-title":"Endoscopy"},{"issue":"4","key":"R8","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1055\/a-0859-1883","article-title":"Management of epithelial precancerous conditions and lesions in the stomach (MAPS II): European Society of Gastrointestinal Endoscopy (ESGE), European Helicobacter and Microbiota Study Group (EHMSG), European Society of Pathology (ESP), and Sociedade Portuguesa de Endoscopia Digestiva (SPED) guideline update 2019","volume":"51","author":"Pimentel-Nunes","journal-title":"Endoscopy"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bios.2024.116530","article-title":"Identification of chronic non-atrophic gastritis and intestinal metaplasia stages in the Correa\u2019s cascade through machine learning analyses of SERS spectral signature of non-invasively-collected human gastric fluid samples","volume":"262","author":"Si","journal-title":"Biosens Bioelectron"},{"issue":"12","key":"R10","doi-asserted-by":"publisher","DOI":"10.1038\/s41419-021-04396-y","article-title":"Interactions between gastric microbiota and metabolites in gastric cancer","volume":"12","author":"Dai","journal-title":"Cell Death Dis"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2021.103631","article-title":"Accurate diagnosis and prognosis prediction of gastric cancer using deep learning on digital pathological images: a retrospective multicentre study","volume":"73","author":"Huang","journal-title":"EBioMedicine"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18147-8","article-title":"Clinically applicable histopathological diagnosis system for gastric cancer detection using deep learning","volume":"11","author":"Song","journal-title":"Nat Commun"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.1186\/s12876-017-0685-7","article-title":"The red distribution width and the platelet distribution width as prognostic predictors in gastric cancer","volume":"17","author":"Cheng","journal-title":"BMC Gastroenterol"},{"issue":"3","key":"R14","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1097\/SLA.0000000000002971","article-title":"Clinical importance of mean corpuscular volume as a prognostic marker after esophagectomy for esophageal cancer: a retrospective study","volume":"271","author":"Yoshida","journal-title":"Ann Surg"},{"issue":"11","key":"R15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0165133","article-title":"Pretreatment hematocrit is superior to hemoglobin as a prognostic factor for triple negative breast cancer","volume":"11","author":"Chen","journal-title":"PLoS One"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","first-page":"1595","DOI":"10.1159\/000489207","article-title":"The neutrophil to lymphocyte ratio may predict benefit from chemotherapy in lung cancer","volume":"46","author":"Liu","journal-title":"Cell Physiol Biochem"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1143154","article-title":"Single and combined use of the platelet-lymphocyte ratio, neutrophil-lymphocyte ratio, and systemic immune-inflammation index in gastric cancer diagnosis","volume":"13","author":"Zhang","journal-title":"Front Oncol"},{"issue":"84-91","key":"R18","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.ijsu.2015.07.681","article-title":"The prognostic role of neutrophils to lymphocytes ratio and platelet count in gastric cancer: a meta-analysis","volume":"21","author":"Xin-Ji","journal-title":"Int J Surg"},{"issue":"4","key":"R19","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1007\/s12032-009-9335-4","article-title":"The effect of peripheral blood values on prognosis of patients with locally advanced gastric cancer before treatment","volume":"27","author":"Aliustaoglu","journal-title":"Med Oncol"},{"issue":"8","key":"R20","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.3748\/wjg.v10.i8.1115","article-title":"C-reactive protein, procalcitonin, interleukin-6, vascular endothelial growth factor and oxidative metabolites in diagnosis of infection and staging in patients with gastric cancer","volume":"10","author":"Ilhan","journal-title":"World J Gastroenterol"},{"issue":"6","key":"R21","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1093\/aje\/kwr345","article-title":"White blood cell count and risk of gastric cancer incidence in a general Japanese population: the Hisayama study","volume":"175","author":"Iida","journal-title":"Am J Epidemiol"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01766-0","article-title":"Development and validation of an interpretable risk prediction model for the early classification of thalassemia","volume":"8","author":"Lai","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2025-101575","article-title":"Rapid discrimination of and non-tuberculous mycobacteria disease via interpretive machine learning analysis of routine laboratory tests","volume":"32","author":"Tang","journal-title":"BMJ Health Care Inform"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3172477","article-title":"Identification tool for gastric cancer based on integration of 33 clinical available blood indices through deep learning","volume":"10","author":"Zhang","journal-title":"IEEE Access"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","DOI":"10.1186\/s12933-024-02503-9","article-title":"Machine learning for predicting in-hospital mortality in elderly patients with heart failure combined with hypertension: a multicenter retrospective study","volume":"23","author":"Liu","journal-title":"Cardiovasc Diabetol"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102051","article-title":"Development and validation of an artificial intelligence model for the early classification of the aetiology of meningitis and encephalitis: a retrospective observational study","volume":"61","author":"Choi","journal-title":"EClinicalMedicine"},{"key":"R27","unstructured":"Correa cascade prediction. Streamlit. URL: https:\/\/hp-igc.streamlit.app\/ [Accessed 25-07-2026]"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2025.1602191","article-title":"Identifying gastric intestinal metaplasia risk based on clinical indicators: a machine learning predictive model based on the SHAP methodology","volume":"16","author":"Wang","journal-title":"Front Pharmacol"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-48769-y","article-title":"Prediction of future gastric cancer risk using a machine learning algorithm and comprehensive medical check-up data: a case-control study","volume":"9","author":"Taninaga","journal-title":"Sci Rep"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-025-14204-x","article-title":"Exploring the potential of machine learning in gastric cancer: prognostic biomarkers, subtyping, and stratification","volume":"25","author":"Rafiepoor","journal-title":"BMC Cancer"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241240905","article-title":"Predicting early gastric cancer risk using machine learning: a population-based retrospective study","volume":"10","author":"Ke","journal-title":"Digit Health"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2025.1718614","article-title":"Validation and interpretation of machine-learning models for rapid identification of active tuberculosis infection using routine laboratory indicators","volume":"15","author":"Liu","journal-title":"Front Cell Infect Microbiol"},{"issue":"3","key":"R33","doi-asserted-by":"publisher","first-page":"5281","DOI":"10.18632\/oncotarget.14136","article-title":"Low lymphocyte-to-white blood cell ratio and high monocyte-to-white blood cell ratio predict poor prognosis in gastric cancer","volume":"8","author":"Feng","journal-title":"Oncotarget"},{"issue":"11","key":"R34","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.1093\/annonc\/mdu274","article-title":"Low albumin-to-globulin ratio associated with cancer incidence and mortality in generally healthy adults","volume":"25","author":"Suh","journal-title":"Ann Oncol"},{"issue":"5","key":"R35","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1038\/s41571-023-00747-0","article-title":"Global burden of gastric cancer: epidemiological trends, risk factors, screening and prevention","volume":"20","author":"Thrift","journal-title":"Nat Rev Clin Oncol"},{"key":"R36","unstructured":"4forfull\/IGC. GitHub. URL: https:\/\/github.com\/4forfull\/IGC [Accessed 30-07-2026]"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T23:11:53Z","timestamp":1786144313000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e94837"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":36,"URL":"https:\/\/doi.org\/10.2196\/94837","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]},"article-number":"v28i7e94837"}}