Dataset Information

The increasing prevalence of HIV/Helicobacter pylori co-infection over time, along with the evolution of antiretroviral therapy (ART).

ABSTRACT: Helicobacter pylori (H. pylori) is one of the most common human bacterial infections with prevalence rates between 10-80% depending upon geographical location, age and socioeconomic status. H. pylori is commonly found in patients complaining of dyspepsia and is a common cause of gastritis. During the course of their infection, people living with HIV (PLHIV) often have a variety of gastrointestinal symptoms including dyspepsia and while previous studies have reported HIV and H. pylori co-infection, there has been little data clarifying the factors influencing this. The aim of this case-control study was to document the prevalence of H. pylori co-infection within the HIV community as well as to describe endoscopic findings, gastritis topography and histology, along with patient demographic characteristics across three different periods of time during which antiretroviral therapy (ART) has evolved, from pre- highly active antiretroviral therapy (HAART) to early and modern HAART eras. These data were compared to well-matched HIV negative controls. Two hundred and twelve PLHIV were compared with 1,617 controls who underwent their first esophagogastroduodenoscopy (EGD) to investigate dyspepsia. The prevalence of H. pylori co-infection among PLHIV was significantly higher in the early (30.2%) and modern HAART period (34.4%) compared with those with coinfection from the pre-HAART period (18.2%). The higher rates seen in patients from the HAART eras were similar to those observed among HIV negative controls (38.5%). This prevalence increase among co-infected patients was in contrast to the fall in prevalence observed among controls, from 60.7% in the early period to 52.9% in the second observed period. The three PLHIV co-infected subgroups differed regarding gastritis topography, morphology and pathology. This study suggests that ART has an important impact on the endoscopic and histological features of gastritis among HIV/H. pylori co-infected individuals, raising the possibility that H. pylori-induced gastritis could be an immune restoration disease.

SUBMITTER: Radovanovic Spurnic A

PROVIDER: S-EPMC5452935 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAlthough 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.ObjectiveWe 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.MethodsWe 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.ResultsThe 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.ConclusionThis 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.

Dataset Information

The increasing prevalence of HIV/Helicobacter pylori co-infection over time, along with the evolution of antiretroviral therapy (ART).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets