biostudies-literatureUnknown16(1)Higgins KHelicobacter pylori (H. pylori) is the most common carcinogenic pathogen globally and the leading cause of gastric cancer. Here, we develop a reinforcement learning-based AI Clinician system to personalise treatment selection and evaluate its ability to improve eradication success compared to clinician-prescribed therapies. The model is trained and internally validated on 38,049 patients from the retrospective European Registry on Helicobacter pylori Management (Hp-EuReg), using independent state deep Q-learning (isDQN) to recommend optimal therapies based on patient characteristics such as age, sex, antibiotic allergies, country, and pre-treatment indication. In internal validation using real-world Hp-EuReg data, AI-recommended therapies achieve a 94.1% success rate (95% CI: 93.2-95.0%) vNature communications6472https://www.ebi.ac.uk/biostudies/studies/S-EPMC12259899biostudies-literatureThe Helicobacter pylori AI-clinician harnesses artificial intelligence to personalise H. pylori treatment recommendations.PMC12259899Laponogov IHiggins KMartins APescino JAMatysiak-Budnik TMarco AMSouthern JCabeza-Segura MLeja MFernandez-Esparrach GPolaka IMartin JKupcinskas JCoimbra MPereira ACCastillo JHoning JFerreira RMVeselkov DMarti EJMaravic ZFigueiredo CSpaander MCWFontes FSedola SCarneiro FDinis-Ribeiro MCuatrecasas MAIDA CONSORTIUMBarros RJonaitis PVeselkov KMoreira LKanonnikoff TFJonaitis LNyssen OPGisbert JPfalseThe Helicobacter pylori AI-clinician harnesses artificial intelligence to personalise H. pylori treatment recommendations.Helicobacter pylori (H. pylori) is the most common carcinogenic pathogen globally and the leading cause of gastric cancer. Here, we develop a reinforcement learning-based AI Clinician system to personalise treatment selection and evaluate its ability to improve eradication success compared to clinician-prescribed therapies. The model is trained and internally validated on 38,049 patients from the retrospective European Registry on Helicobacter pylori Management (Hp-EuReg), using independent state deep Q-learning (isDQN) to recommend optimal therapies based on patient characteristics such as age, sex, antibiotic allergies, country, and pre-treatment indication. In internal validation using real-world Hp-EuReg data, AI-recommended therapies achieve a 94.1% success rate (95% CI: 93.2-95.0%) v2025-01-01T00:00:00Z2025 Jul2026-07-15T08:57:59.323Z2026-07-03T03:10:07.407ZS-EPMC122598994065961210.1038/s41467-025-61329-5