[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121926-en":3,"doc-seo-121926-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121926,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",7,"Healthcare","Machine learning models in predicting failure of Helicobacter pylori treatment - A two country validation study","Clarithromycin-containing Helicobacter pylori triple therapy failure rates have declined, but treatment success has deteriorated globally. This two-country validation study evaluates how 11 machine learning algorithms predict failure using pre-treatment clinical parameters. Training used 84,609 Hong Kong adults treated in 2003–2013; internal validation used 27,736 similar Hong Kong patients in 2014–2017; external validation used 18,050 UK patients in 2012–2017. Extra-Tree achieved the best AUC, sensitivity, and specificity in both cohorts, identifying patients at high risk with simple baseline features.","Received: 14 October 2023 | Revised: 29 December 2023 | Accepted: 9 January 2024  \nDOI: 10. 1111/hel.13051  \nOR I G I NAL ART I C L E  \nMachine learning models in predicting failure of Helicobacter pylori treatment: A two country validation study  \nFang Jiang1,2 | Thomas K. L. Lui1 | Chengsheng Ju2 | Chuan-Guo Guo1,3 | Ka Shing Cheung1 | Wallis C. Y. Lau2 | Wai K. Leung1  \n1Department of Medicine, School of Clinical Medicine, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong, China  \n2Research Department of Practice and Policy, UCL School of Pharmacy, London, UK  \n3 Department of Gastroenterology, Beijing Friendship Hospital, Capital Medical University, Beijing, China  \nCorrespondence  \nWai K. Leung, Department of Medicine, School of Clinical Medicine, Li Ka Shing Faculty of Medicine, University of Hong Kong, Pokfulam, Hong Kong, China. Email: waikleung@hku. hk  \nAbstract  \nBackground: The success rate of clarithromycin-containing Helicobacter pylori treatment had declined globally. This study aims to explore the role of different machine learning algorithms in predicting failure of H. pylori treatment.  \nMaterials and Methods: We included 84,609 adult patients who had received the first course of clarithromycin-containing triple therapy for H. pylori in Hong Kong from 2003 to 2013 as training set. Results were validated in patients who had received similar triple therapy with 27,736 Hong Kong patients between 2014 and 2017 (internal cohort); and 18,050 UK patients between 2012 and 2017 (external cohort) . The performance of 11 available machine learning algorithms were used to predict the failure of triple therapy. The performance was determined by the area under receiver operating characteristic curve (AUC) .  \nResults: The treatment failure rates in the training, internal and external validation cohort was 5.9%, 9. 5%, and 6. 1%, respectively. In the internal validation set, Extra-Tree (ET) Classifier had the best AUC (0 . 88; 95% CI, 0.87–0. 88), sensitivity (79. 6%; 95% CI, 79.0–80. 2) and specificity (79.4%; 95% CI, 79.0–79. 8) . In the external validation set, ET Classifier also had the best AUC (0 . 85; 95% CI, 0 .85–0. 86), sensitivity (80 . 1%; 95% CI, 79.5–80.9), and specificity (80 . 2%; 95% CI, 78.8–81. 3) . Top features of importance used by ET Classifier in predicting treatment failure included time interval between antibiotic use and triple therapy (48 . 8%), age (29. 1%) and triple therapy regime (6 . 28%) .  \nConclusions: Machine learning algorithm, based on simple baseline clinical parameters, could help to identify patients at high risk of failure from clarithromycincontaining triple therapy for H. pylori.  \nK E Y WO R D S  \nartificial intelligence, Helicobacter pylori, machine learning algorithms, triple therapy  \nFang Jiang and Thomas K L Lui contributed equally.  \nThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.  \n© 2024 The Authors. Helicobacter published by John Wiley & Sons Ltd.  \n2 of 10  \nJIANG  \net al.  \n1 | INTRODUCTION  \nDespite the improvement of general hygienic condition and socioeconomic development, our updated meta-analysis showed that approximately 48.9% of the world population are still infected with Helicobacter pylori.1 The prevalence of H. pylori infection varies greatly among different geographic regions and is generally more prevalent in low-to-mid income countries and region with low universal health coverage.2–4  \nH. pylori colonizes the gastric mucosa and is the principal cause of gastroduodenal diseases including chronic gastritis, peptic ulcer disease, and gastric cancer. 5,6 In Hong Kong, the most commonly used first-line eradication treatment for H. pylori is clarithromycincontaining triple therapy consisting of clarithromycin, p","cbCainZT3m3Yd1Im","https://ap.wps.com/l/cbCainZT3m3Yd1Im","pdf",1411526,1,10,"English","en",105,"# Introduction\n# Methods\n## Data source\n# Results\n# Conclusions","[{\"question\":\"What clinical problem does this study address?\",\"answer\":\"The study addresses rising failure rates of clarithromycin-containing Helicobacter pylori triple therapy and the need to identify high-risk patients early using routine pretreatment information.\"},{\"question\":\"How was the dataset for training and validation constructed?\",\"answer\":\"Training used 84,609 Hong Kong adult patients treated in 2003–2013. Validation included an internal Hong Kong cohort of 27,736 patients (2014–2017) and an external UK cohort of 18,050 patients (2012–2017).\"},{\"question\":\"Which machine learning algorithm performed best and what features mattered most?\",\"answer\":\"The Extra-Tree (ET) classifier showed the best AUC, sensitivity, and specificity in both internal and external validation sets. Its top feature importance included time interval between antibiotic use and triple therapy, age, and the triple therapy regime.\"}]","Machine learning models in predicting failure of Helicobacter pylori treatment - A two country validation study | PDF",1785807775,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-models-in-predicting-failure-of-helicobacter-pylori-treatment-a-two-country-validation-study","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-models-in-predicting-failure-of-helicobacter-pylori-treatment-a-two-country-validation-study/121926/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What clinical problem does this study address?","Question",{"text":75,"@type":76},"The study addresses rising failure rates of clarithromycin-containing Helicobacter pylori triple therapy and the need to identify high-risk patients early using routine pretreatment information.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the dataset for training and validation constructed?",{"text":80,"@type":76},"Training used 84,609 Hong Kong adult patients treated in 2003–2013. Validation included an internal Hong Kong cohort of 27,736 patients (2014–2017) and an external UK cohort of 18,050 patients (2012–2017).",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning algorithm performed best and what features mattered most?",{"text":84,"@type":76},"The Extra-Tree (ET) classifier showed the best AUC, sensitivity, and specificity in both internal and external validation sets. Its top feature importance included time interval between antibiotic use and triple therapy, age, and the triple therapy regime.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,118,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]