The 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%) versus 88.1% (95% CI: 87.7-88.4%) for clinician-prescribed therapies not aligned with AI suggestions-an improvement of 6.0%. Results are replicated in an external validation cohort (n = 7186), confirming generalisability. The AI system identifies optimal treatment strategies in key subgroups: 65% (n = 24,923) are recommended bismuth-based therapies, and 15% (n = 5898) non-bismuth quadruple therapies. Random forest modelling identifies region and concurrent medications as patient-specific drivers of AI recommendations. With nearly half the global population likely to contract H. pylori, this approach lays the foundation for future prospective clinical validation and shows the potential of AI to support clinical decision-making, enhance outcomes, and reduce gastric cancer burden.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-07-14
DOI
https://doi.org/10.1038/s41467-025-61329-5
Citations
6
Primary Topic
Helicobacter pylori-related gastroenterology studies
Type
article
Field-Weighted Citation Impact
12.04

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

The Helicobacter pylori AI-clinician harnesses artificial intelligence to personalise H. pylori treatment recommendations

Tamara Matysiak-Budnik, Manuel Cabeza-Segura, Rita Barros, Míriam Cuatrecasas et al.
6 citations
Nature Communications
Helicobacter pylori-related gastroenterology studies
12.04
article

The Helicobacter pylori AI-clinician harnesses artificial intelligence to personalise H. pylori treatment recommendations

Tamara Matysiak-Budnik, Manuel Cabeza-Segura, Rita Barros, Míriam Cuatrecasas, Glòria Fernández‐Esparrach, Javier P. Gisbert, Mário Jorge Dinis-Ribeiro, Mārcis Leja, Ana Martins, Manon C.W. Spaander, Fátima Carneiro, K M Higgins, Elena Jiménez-Martí, Miguel Coimbra, Rui M. Ferreira, Joshua Southern, Jérôme C. Martin, Ivan Laponogov, Tania Fleitas, Céu Figueiredo, Laimas Virginijus Jonaitis, Kirill Veselkov, Dennis A. Veselkov, Juozas Kupčinskas, Filipa Fontes, Paulius Jonaitis, Judith Honing, Ana Miralles-Marco, Olga P. Nyssen, Inese Poļaka, Junior Andrea Pescino, Ana Carina Pereira, Letícia Moreira, Stefano Sedola, Zorana Maravic
article en
6 citations

Abstract

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%) versus 88.1% (95% CI: 87.7-88.4%) for clinician-prescribed therapies not aligned with AI suggestions-an improvement of 6.0%. Results are replicated in an external validation cohort (n = 7186), confirming generalisability. The AI system identifies optimal treatment strategies in key subgroups: 65% (n = 24,923) are recommended bismuth-based therapies, and 15% (n = 5898) non-bismuth quadruple therapies. Random forest modelling identifies region and concurrent medications as patient-specific drivers of AI recommendations. With nearly half the global population likely to contract H. pylori, this approach lays the foundation for future prospective clinical validation and shows the potential of AI to support clinical decision-making, enhance outcomes, and reduce gastric cancer burden.

Nature CommunicationsVol. 16(1)
Lithuanian University of Health Sciences (LT), Universitat de València (ES), Universidade do Porto (PT), European CanCer Organisation (BE), Instituto de Salud Carlos III (ES), Erasmus MC (NL), Centre Hospitalier Universitaire de Nantes (FR), Yale University (US), Departament de Salut (ES), Instituto Português de Oncologia Francisco Gentil (PT), Stratec (Belgium) (BE), Hospital Clínic de Barcelona (ES), Institute for Systems Engineering and Computers (PT), Hospital Universitario de La Princesa (ES), Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (ES), INCLIVA Health Research Institute (ES), Centro de Investigación Biomédica en Red de Cáncer (ES), i3S - Instituto de Investigação e Inovação em Saúde, Universidade do Porto (PT), Consorci Institut D'Investigacions Biomediques August Pi I Sunyer (ES), Imperial College London (GB), Universidad Autónoma de Madrid (ES), Universitat de Barcelona (ES), University of Latvia (LV)
UK Research and Innovation, European Commission, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas, HORIZON EUROPE Framework Programme
Peace, Justice and strong institutions
Openalex Percentile: Top 1%
Helicobacter pylori-related gastroenterology studies
12.04
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.