{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T00:20:44Z","timestamp":1792714844901,"version":"4.5.0"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T00:00:00Z","timestamp":1771372800000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background and aims<\/jats:title>\n                    <jats:p>The early, non-invasive detection of chronic atrophic gastritis (CAG), a precancerous lesion, remains a clinical challenge. While serological biomarkers are promising alternatives to endoscopy for screening, their predictive accuracy using conventional methods is suboptimal. This study aimed to identify key predictors of CAG and to comparatively develop multiple machine learning (ML) models, evaluating whether ML offers a definitive advantage and identifying a reliable model for triaging patients to endoscopy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this retrospective diagnostic study (conducted from January to October 2020), 222 subjects (CAG prevalence: 30.6%) were stratified randomly into a training set (80%) and an independent test set (20%). Feature selection was performed exclusively on the training set using multivariate logistic regression, which identified four independent predictors: PGI, the PGI\/PGII ratio, age, and anti-\n                      <jats:italic>H. pylori<\/jats:italic>\n                      antibody status. Using these predictors, eight models\u2014including Logistic Regression (as baseline), Elastic Net, Support Vector Machine, Neural Network, and tree-based ensembles\u2014were trained and optimized via 5-fold cross-validation. Model performance was rigorously evaluated on the held-out test set using discrimination (AUC, sensitivity, specificity), calibration (Brier score), and clinical utility (Decision Curve Analysis).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Multivariable analysis identified the four predictors, with anti-\n                      <jats:italic>H. pylori<\/jats:italic>\n                      antibody positivity associated with an approximately four-fold higher odds of CAG. On the independent test set, the Elastic Net (AUC\u202f=\u202f0.823) and Logistic Regression (AUC\u202f=\u202f0.810) models demonstrated the highest and most robust discriminative performance, showing excellent sensitivity (0.923) and negative predictive value (&amp;gt;0.95) for ruling out CAG. Statistical comparison confirmed that their AUCs were significantly higher than those of the severely overfitted tree-based models (e.g., Random Forest), but not significantly different from other complex models like Support Vector Machine. Decision Curve Analysis confirmed the superior net clinical benefit of the Elastic Net and Logistic Regression models across a wide range of decision thresholds.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Simple, interpretable linear models (Elastic Net and Logistic Regression) based on four routine clinical parameters provide a robust tool for the non-invasive identification of CAG in a clinical population referred for endoscopic evaluation. They show particular strength in ruling out disease, supporting their potential role as a triage tool. In this setting, they demonstrated more consistent performance than more complex machine learning algorithms. External validation in broader populations is warranted to confirm generalizability before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1757004","type":"journal-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T06:57:06Z","timestamp":1771397826000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning models using serum gastric biomarkers for the non-invasive prediction of atrophic gastritis: a comparative study"],"prefix":"10.3389","volume":"13","author":[{"given":"Dong","family":"Li","sequence":"first","affiliation":[{"name":"Department of Gastroenterology, No. 971 Hospital of the People\u2019s Liberation Army Navy","place":["Qingdao, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitao","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, No. 971 Hospital of the People\u2019s Liberation Army Navy","place":["Qingdao, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baihan","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, No. 971 Hospital of the People\u2019s Liberation Army Navy","place":["Qingdao, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongfang","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, No. 971 Hospital of the People\u2019s Liberation Army Navy","place":["Qingdao, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingxue","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, No. 971 Hospital of the People\u2019s Liberation Army Navy","place":["Qingdao, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhu","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, No. 971 Hospital of the People\u2019s Liberation Army Navy","place":["Qingdao, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"15","DOI":"10.5152\/eajm.2010.05","article-title":"Usefulness of serum pepsinogen levels as a screening test for atrophic gastritis and gastric cancer","volume":"42","author":"Agkoc","year":"2010","journal-title":"Eurasian J Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1111\/j.1443-9573.2007.00271.x","article-title":"Screening of atrophic gastritis and gastric cancer by serum pepsinogen, gastrin-17 and Helicobacter pylori immunoglobulin G antibodies","volume":"8","author":"Cao","year":"2007","journal-title":"J Dig Dis"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.ajg.2023.11.004","article-title":"Correlation of chronic atrophic gastritis with gastric-specific circulating biomarkers","volume":"25","author":"Yu","year":"2024","journal-title":"Arab J Gastroenterol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e0142080","DOI":"10.1371\/journal.pone.0142080","article-title":"Significance of serum pepsinogens as a biomarker for gastric cancer and atrophic gastritis screening: a systematic review and meta-analysis","volume":"10","author":"Huang","year":"2015","journal-title":"PLoS One"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1007\/s12033-022-00589-8","article-title":"miR-196a-5p correlates with chronic atrophic gastritis progression to gastric cancer and induces malignant biological behaviors of gastric cancer cells by targeting ACER2","volume":"65","author":"Zheng","year":"2023","journal-title":"Mol Biotechnol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1111\/apt.14471","article-title":"Serum pepsinogen 1 and anti-Helicobacter pylori IgG antibodies as predictors of gastric cancer risk in Finnish males","volume":"47","author":"Song","year":"2018","journal-title":"Aliment Pharmacol Ther"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"980399","DOI":"10.3389\/fcimb.2022.980399","article-title":"Association of serum pepsinogens and gastrin-17 with Helicobacter pylori infection assessed by urea breath test","volume":"12","author":"Zhou","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"259","DOI":"10.3109\/00365521.2013.869352","article-title":"Serum anti-Helicobacter pylori immunoglobulin G titer correlates with grade of histological gastritis, mucosal bacterial density, and levels of serum biomarkers","volume":"49","author":"Tu","year":"2014","journal-title":"Scand J Gastroenterol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1186\/s12876-025-03996-8","article-title":"The potential value of serum pepsinogen and gastrin-17 for the diagnosis of chronic atrophic gastritis at different stages of severity: a clinical diagnostic study","volume":"25","author":"Zhang","year":"2025","journal-title":"BMC Gastroenterol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"853","DOI":"10.3748\/wjg.15.853","article-title":"Serum biomarker tests are useful in delineating between patients with gastric atrophy and normal, healthy stomach","volume":"15","author":"Iijima","year":"2009","journal-title":"World J Gastroenterol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e076587","DOI":"10.1136\/bmjopen-2023-076587","article-title":"Development and validation of a risk prediction model for pulmonary tuberculosis among presumptive tuberculosis cases in Ethiopia","volume":"13","author":"Wolde","year":"2023","journal-title":"BMJ Open"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"2223","DOI":"10.2147\/JHC.S438346","article-title":"Nomogram for estimation of acute liver failure risk in spontaneous ruptured hepatocellular carcinoma","volume":"10","author":"Zhao","year":"2023","journal-title":"J Hepatocell Carcinoma"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e24205","DOI":"10.1002\/clc.24205","article-title":"The differences between patients with nonalcoholic fatty liver disease (NAFLD) and those without NAFLD, as well as predictors of functional coronary artery ischemia in patients with NAFLD","volume":"47","author":"Li","year":"2024","journal-title":"Clin Cardiol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"652574","DOI":"10.3389\/fonc.2021.652574","article-title":"Diagnostic value of serum pepsinogen levels for screening gastric cancer and atrophic gastritis in asymptomatic individuals: a cross-sectional study","volume":"11","author":"Tong","year":"2021","journal-title":"Front Oncol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1080\/1354750X.2024.2400927","article-title":"The diagnostic value of serum trefoil factor 3 and pepsinogen combination in chronic atrophic gastritis: a retrospective study based on a gastric cancer screening cohort in the community population","volume":"29","author":"Zhao","year":"2024","journal-title":"Biomarkers"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1448","DOI":"10.1080\/00365520802273025","article-title":"Serum biomarkers provide an accurate method for diagnosis of atrophic gastritis in a general population: the Kalixanda study","volume":"43","author":"Storskrubb","year":"2008","journal-title":"Scand J Gastroenterol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1111\/apt.14248","article-title":"Systematic review with meta-analysis: diagnostic performance of the combination of pepsinogen, gastrin-17 and anti-Helicobacter pylori antibodies serum assays for the diagnosis of atrophic gastritis","volume":"46","author":"Zagari","year":"2017","journal-title":"Aliment Pharmacol Ther"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1016\/j.chest.2021.04.048","article-title":"Predicting lymph node metastasis in non-small cell lung cancer: prospective external and temporal validation of the HAL and HOMER models","volume":"160","author":"Martinez-Zayas","year":"2021","journal-title":"Chest"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.2106\/JBJS.20.01640","article-title":"Machine learning algorithms predict functional improvement after hip arthroscopy for femoroacetabular impingement syndrome in athletes","volume":"103","author":"Kunze","year":"2021","journal-title":"J Bone Joint Surg Am"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e2011809","DOI":"10.1001\/jamanetworkopen.2020.11809","article-title":"Validation of progression-free survival rate at 6 months and objective response for estimating overall survival in immune checkpoint inhibitor trials: a systematic review and meta-analysis","volume":"3","author":"Kok","year":"2020","journal-title":"JAMA Netw Open"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1136\/postgradmedj-2020-139183","article-title":"Serum pepsinogen levels and OLGA\/OLGIM staging in the assessment of atrophic gastritis types","volume":"98","author":"Ogutmen Koc","year":"2022","journal-title":"Postgrad Med J"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1002\/ijc.33801","article-title":"Association of Helicobacter pylori and gastric atrophy with adenocarcinoma of the esophagogastric junction in Taixing, China","volume":"150","author":"Gao","year":"2022","journal-title":"Int J Cancer"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"6894248","DOI":"10.1155\/2021\/6894248","article-title":"The diagnostic value of serum Gastrin-17 and pepsinogen for gastric cancer screening in eastern China","volume":"2021","author":"Shen","year":"2021","journal-title":"Gastroenterol Res Pract"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/s11255-020-02391-4","article-title":"Serum osmolarity as a potential predictor for contrast-induced nephropathy following elective coronary angiography","volume":"52","author":"Kanbay","year":"2020","journal-title":"Int Urol Nephrol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1007\/s10554-023-02839-5","article-title":"Coronary X-ray angiography segmentation using artificial intelligence: a multicentric validation study of a deep learning model","volume":"39","author":"Nobre Menezes","year":"2023","journal-title":"Int J Cardiovasc Imaging"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1757004\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T11:32:51Z","timestamp":1771932771000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1757004\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,18]]},"references-count":25,"alternative-id":["10.3389\/fmed.2026.1757004"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1757004","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,18]]},"article-number":"1757004"}}