{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T06:59:31Z","timestamp":1780815571626,"version":"3.54.1"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T00:00:00Z","timestamp":1770163200000},"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. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background and aims<\/jats:title>\n                    <jats:p>\n                      Endoscopic visualization for the diagnosis of\n                      <jats:italic>Helicobacter pylori<\/jats:italic>\n                      (HP) infection status is highly important for helping endoscopists quickly understand the status of gastric background mucosa and assisting in subsequent diagnosis and treatment. In this study, a deep learning algorithm was designed to construct a three-class classification model of HP infection status, providing a new approach to address the subjectivity in the interpretation of endoscopic features.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The clinical data of patients who completed gastroscopy were collected, and 16 endoscopic features were evaluated and recorded. On the basis of the status of HP infection, the patients were classified into three groups: the current HP infection group (CI), the previous HP infection group (PI), and the negative HP infection group (NI), with 1,000 patients screened in each group. In this study, an HP infection classification model based on the transformer network was constructed, which uses a self-attention mechanism to capture feature associations for the task of HP infection classification and recognition. Model interpretability was achieved by screening key features through SHapley Additive exPlanations (SHAP) value analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 3,000 subjects were included in the study, and comparative analysis revealed that the 1D-transformer model demonstrated superior performance in the HP recognition task. The accuracy, specificity, sensitivity, and F1_scores produced by the model were 98.9\u202f\u00b1\u202f0.28, 98.8\u202f\u00b1\u202f0.14, 99.4\u202f\u00b1\u202f0.27, and 98.9\u202f\u00b1\u202f0.28, respectively. In addition, it has better performance than other algorithms and models. In terms of model interpretability, this study highlights the importance rankings of different features in model decision-making and the directions of their influence. The results show that map redness (SHAP value of 0.220), xanxoma (SHAP value of 0.101), atrophy (SHAP value of 0.065), and intestinal metaplasia (SHAP value of 0.008) are key features for identifying the PI. Diffuse redness (SHAP 0.186), thickened folds (SHAP 0.126), mucus coverage (SHAP 0.094), and nodular changes (SHAP 0.043) are key features for identifying CI. The presence of RAC (SHAP 0.262) and ridge redness (SHAP 0.026) are key features for identifying NI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study applies a 1D-transformer model to the task of classifying HP infection status, and compared with other models, it can precisely screen out populations with three different HP infection statuses, with higher performance and reliability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1765267","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T06:40:40Z","timestamp":1770187240000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Rapid diagnosis of Helicobacter pylori infection status based on endoscopic features and deep learning algorithms"],"prefix":"10.3389","volume":"14","author":[{"given":"Xinying","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Gastroenterology, Beijing Tiantan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianyu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Information and Communication, Huazhong University of Science and Technology","place":["Wuhan, Hubei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"He","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Beijing Tiantan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1038\/s41572-023-00431-8","article-title":"Helicobacter pylori infection","volume":"9","author":"Malfertheiner","year":"2023","journal-title":"Nat Rev Dis Primers"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/S2468-1253(23)00070-5","article-title":"Global prevalence of Helicobacter pylori infection between 1980 and 2022: a systematic review and meta-analysis","volume":"8","author":"Li","year":"2023","journal-title":"Lancet Gastroenterol Hepatol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2895","DOI":"10.3390\/ijms24032895","article-title":"Helicobacter pylori and gastric Cancer: pathogenetic mechanisms","volume":"24","author":"Salvatori","year":"2023","journal-title":"Int J Mol Sci"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s13045-024-01654-2","article-title":"Helicobacter pylori and gastric cancer: mechanisms and new perspectives","volume":"18","author":"Duan","year":"2025","journal-title":"J Hematol Oncol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1001\/jama.2024.14887","article-title":"Collaborators of Taiwan community-based integrated screening group. Screening for Helicobacter pylori to prevent gastric Cancer: a pragmatic randomized clinical trial","volume":"332","author":"Lee","year":"2024","journal-title":"JAMA"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1053\/j.gastro.2022.03.039","article-title":"Effect of Helicobacter pylori eradication on gastric cancer prevention: updated report from a randomized controlled trial with 26.5 years of follow-up","volume":"163","author":"Yan","year":"2022","journal-title":"Gastroenterology"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"3250","DOI":"10.1038\/s41591-024-03153-w","article-title":"Gastric cancer prevention by community eradication of Helicobacter pylori: a cluster-randomized controlled trial","volume":"30","author":"Pan","year":"2024","journal-title":"Nat Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-1-0716-1302-3_1","article-title":"An overview of Helicobacter pylori infection","volume":"2283","author":"FitzGerald","year":"2021","journal-title":"Methods Mol Biol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"57817","DOI":"10.3389\/fcimb.2023.1257817","article-title":"Helicobacter pylori infection: a dynamic process from diagnosis to treatment","volume":"12","author":"Sun","year":"2023","journal-title":"Front Cell Infect Microbiol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"13380","DOI":"10.1038\/s41598-023-40179-5","article-title":"Application of artificial intelligence in endoscopic image analysis for the diagnosis of a gastric cancer pathogen-Helicobacter pylori infection","volume":"13","author":"Lin","year":"2023","journal-title":"Sci Rep"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1111\/den.13890","article-title":"Current status and future perspective of artificial intelligence applications in endoscopic diagnosis and management of gastric cancer","volume":"33","author":"Hirasawa","year":"2021","journal-title":"Dig Endosc"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1186\/s12876-024-03389-3","article-title":"Development and application of an artificial intelligence-assisted endoscopy system for diagnosis of Helicobacter pylori infection: a multicenter randomized controlled study","volume":"24","author":"Zou","year":"2024","journal-title":"BMC Gastroenterol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1016\/j.dld.2023.02.010","article-title":"Assessment of Helicobacter pylori infection by deep learning based on endoscopic videos in real time","volume":"55","author":"Li","year":"2023","journal-title":"Dig Liver Dis"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e13080","DOI":"10.1111\/hel.13080","article-title":"Diagnostic performance of linked color imaging for gastric cancer by Helicobacter pylori infection status: a subanalysis of the large-scale, multicenter randomized controlled trial LCI-FIND","volume":"29","author":"Kato","year":"2024","journal-title":"Helicobacter"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1039\/d3ay02250a","article-title":"A deep learning method for multi-task intelligent detection of oral cancer based on optical fiber Raman spectroscopy","volume":"16","author":"Li","year":"2024","journal-title":"Anal Methods"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1111\/j.1523-5378.2011.00889.x","article-title":"Low prevalence of Helicobacter pylori-negative gastric cancer among Japanese","volume":"16","author":"Matsuo","year":"2011","journal-title":"Helicobacter"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1111\/j.1365-2036.2005.02360.x","article-title":"Morphological changes in human gastric tumours after eradication therapy of Helicobacter pylori in a short-term follow-up","volume":"21","author":"Ito","year":"2005","journal-title":"Aliment Pharmacol Ther"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"5461","DOI":"10.3748\/wjg.v20.i18.5461","article-title":"Helicobacter pylori associated chronic gastritis, clinical syndromes, precancerous lesions, and pathogenesis of gastric cancer development","volume":"20","author":"Watari","year":"2014","journal-title":"World J Gastroenterol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e12669","DOI":"10.1111\/hel.12669","article-title":"Previous Helicobacter pylori infection-induced atrophic gastritis: a distinct disease entity in an understudied population without a history of eradication","volume":"25","author":"Kishikawa","year":"2020","journal-title":"Helicobacter"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1016\/j.vgie.2020.08.013","article-title":"Artificial intelligence in gastrointestinal endoscopy","volume":"5","author":"Pannala","year":"2020","journal-title":"VideoGIE"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1111\/den.13486","article-title":"Validity of endoscopic features for the diagnosis of Helicobacter pylori infection status based on the Kyoto classification of gastritis","volume":"32","author":"Yoshii","year":"2020","journal-title":"Dig Endosc"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1111\/den.13808","article-title":"Regular arrangement of collecting venules and the kimura-Takemoto classification for the endoscopic diagnosis of Helicobacter pylori infection: evaluation in a Western setting","volume":"33","author":"Ebigbo","year":"2021","journal-title":"Dig Endosc"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1016\/j.gie.2022.11.008","article-title":"Establishment of a modified Kyoto classification scoring model and its significance in the diagnosis of Helicobacter pylori current infection","volume":"97","author":"Wang","year":"2023","journal-title":"Gastrointest Endosc"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"439","DOI":"10.3904\/kjim.2023.300","article-title":"Predicting Helicobacter pylori infection from endoscopic features","volume":"39","author":"Seo","year":"2024","journal-title":"Korean J Intern Med"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"338","DOI":"10.5009\/gnl19418","article-title":"Characteristics and early diagnosis of gastric Cancer discovered after Helicobacter pylori eradication","volume":"15","author":"Ito","year":"2021","journal-title":"Gut Liver"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1765267\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:56:08Z","timestamp":1771926968000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1765267\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,4]]},"references-count":25,"alternative-id":["10.3389\/fpubh.2026.1765267"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1765267","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,4]]},"article-number":"1765267"}}