Helicobacter pylori (H. pylori) risk factor analysis and prevalence prediction: a machine learning-based approach

Abstract

Background Although previous epidemiological studies have examined the potential risk factors that increase the likelihood of acquiring Helicobacter pylori infections, most of these analyses have utilized conventional statistical models, including logistic regression, and have not benefited from advanced machine learning techniques. Objective We examined H. pylori infection risk factors among school children using machine learning algorithms to identify important risk factors as well as to determine whether machine learning can be used to predict H. pylori infection status. Methods We applied feature selection and classification algorithms to data from a school-based cross-sectional survey in Ethiopia. The data set included 954 school children with 27 sociodemographic and lifestyle variables. We conducted five runs of tenfold cross-validation on the data. We combined the results of these runs for each combination of feature selection (e.g., Information Gain) and classification (e.g., Support Vector Machines) algorithms. Results The XGBoost classifier had the highest accuracy in predicting H. pylori infection status with an accuracy of 77%—a 13% improvement from the baseline accuracy of guessing the most frequent class (64% of the samples were H. Pylori negative.) K-Nearest Neighbors showed the worst performance across all classifiers. A similar performance was observed using the F1-score and area under the receiver operating curve (AUROC) classifier evaluation metrics. Among all features, place of residence (with urban residence increasing risk) was the most common risk factor for H. pylori infection, regardless of the feature selection method choice. Additionally, our machine learning algorithms identified other important risk factors for H. pylori infection, such as; electricity usage in the home, toilet type, and waste disposal location. Using a 75% cutoff for robustness, machine learning identified five of the eight significant features found by traditional multivariate logistic regression. However, when a lower robustness threshold is used, machine learning approaches identified more H. pylori risk factors than multivariate logistic regression and suggested risk factors not detected by logistic regression. Conclusion This study provides evidence that machine learning approaches are positioned to uncover H. pylori infection risk factors and predict H. pylori infection status. These approaches identify similar risk factors and predict infection with comparable accuracy to logistic regression, thus they could be used as an alternative method.

Lifestyle-based nomogram for identifying the Chaoshan inhabitants of China at high risk of Helicobacter pylori infection

“…Some researchers have developed machine-learning tools to predict HP infection. Logistic regression analysis with K-nearest neighbor (KNN), Least Absolute Shrinkage and Selection Operator (LASSO), support vector machine (SVM), random forest (RF), naive Bayes (NB), and XGBoost (XGB) algorithms have been used to predict HP infections based on lifestyle, behavior, socioeconomic, hygiene, and sanitation factors [ 31 ]. AUCs of 0.76–0.79 have been achieved by XBG, NB, RF, SVM, KNN, and LASSO algorithms [ 31 ].…”

“…Logistic regression analysis with K-nearest neighbor (KNN), Least Absolute Shrinkage and Selection Operator (LASSO), support vector machine (SVM), random forest (RF), naive Bayes (NB), and XGBoost (XGB) algorithms have been used to predict HP infections based on lifestyle, behavior, socioeconomic, hygiene, and sanitation factors [ 31 ]. AUCs of 0.76–0.79 have been achieved by XBG, NB, RF, SVM, KNN, and LASSO algorithms [ 31 ]. Despite being valid, the screening tools developed in these studies employed some parameters that are more difficult to obtain in the general population.…”

Therapeutic eradication choices inHelicobacter pyloriinfection in children

“…[2][3][4][5] The global prevalence of H. pylori infection is approximately around 50%, but infection rates vary between developed and developing countries, often ranging between 20% and 80%. 6 According to an epidemiological study conducted by Zamani et al, H. pylori infection was more prevalent in developing (50.8%) compared to developed (34.7%) countries. Furthermore, the prevalence of the infection is higher in adults than children (48.6% versus 32.6%, respectively).…”

Towards Clinical Prediction with Transparency: An Explainable AI Approach to Survival Modelling in Residential Aged Care

“…Machine learning algorithms accommodate many more variables than traditional statistical models. By accurately representing the complex interactions and non-linear relationships that exist in most clinical data, machine learning can generate deeper insights into underlying data relationships, potentially leading to the discovery of novel risk factors [35, 36, 33, 34]. Machine learning approaches in survival analysis, however, are not without limitations.…”