Increased Prevalence of Cestode Infection Associated with History of Deworming among Primary School Children in Ethiopia

Decreased Weight-for-Age Associated with Mass Deworming among Young Ethiopian Schoolchildren in Jimma Town, Southwest Ethiopia: A School-Based Cross-Sectional Study

School-based mass deworming programs are implemented to reduce soil-transmitted helminth (STH) infection prevalence and intensity among school-aged children. However, previous studies debate the impact of deworming beyond the removal of worms. Hence, this study aimed to examine the effect of mass deworming on nutritional indicators in young Ethiopian schoolchildren. A school-based cross-sectional study was conducted among 1,036 participants from April to May 2020 in Jimma Town, Ethiopia. An interviewer-based questionnaire was administered to the children to gather data on sociodemographic, lifestyle variables, and deworming status. Anthropometric measurements were taken for the height and weight of the children. Stool samples were collected and analyzed for STH infection using direct wet mount microscopy and the Kato-Katz technique. In multivariate logistic regression analysis, deworming within the past 6 months or 1 year was not significantly associated with underweight, stunting, and thinning. However, deworming within the past year was significantly associated with decreased weight-for-age z-score (adjusted mean difference = -0.245; 95% CI: -0.413 to -0.076; P = 0.004). Deworming in the past 6 months demonstrated a nonsignificant trend toward increased stunting (adjusted odds ratio = 1.258; 95% CI: 0.923-1.714; P = 0.145). This study provides evidence that deworming in the past 6 months or 1 year was not significantly associated with underweight, stunting, and thinning. However, deworming within the past year was associated with a significantly decreased weight-for-age z-score in young Ethiopian schoolchildren of Jimma Town after adjustment for confounding variables.

The epidemiology of human Taenia solium infections: A systematic review of the distribution in Eastern and Southern Africa

BACKGROUND

Taenia solium is a tapeworm that causes taeniosis in humans and cysticercosis in humans and pigs. Within Eastern and Southern Africa (ESA), information on the presence of human taeniosis and cysticercosis seems scarce. This systematic review aimed to describe the current information available and gaps in the epidemiology of human T. solium infections in ESA.

METHODS/PRINCIPLE FINDINGS

Scientific literature published between 1st January 2000 and 20th June 2022 in international databases [MEDLINE (Ovid), Embase (Ovid), Global Health (Ovid), Scopus (Elsevier), African Index Medicus (via WHO Global Index Medicus), and Open Grey] was systematically reviewed for ESA. The study area included 27 countries that make up the ESA region. Information on either taeniosis, cysticercosis or NCC was available for 16 of 27 countries within the region and a total of 113 reports were retained for the review. Most case reports for cysticercosis and NCC were from South Africa, while Tanzania had the most aggregated cysticercosis reports. Eleven countries reported on NCC with seven countries reporting data on NCC and epilepsy. Unconfirmed human T. solium taeniosis cases were reported in nine countries while two countries (Madagascar and Zambia) reported confirmed T. solium cases. The cysticercosis seroprevalence ranged between 0.7-40.8% on antigen (Ag) ELISA and between 13.1-45.3% on antibody (Ab) ELISA. Based on immunoblot tests the Ab seroprevalence was between 1.7-39.3%, while the proportion of NCC-suggestive lesions on brain CT scans was between 1.0-76% depending on the study population. The human taeniosis prevalence based on microscopy ranged between 0.1-14.7%. Based on Copro Ag-ELISA studies conducted in Kenya, Rwanda, Tanzania, and Zambia, the highest prevalence of 19.7% was reported in Kenya.

CONCLUSIONS

Despite the public health and economic impact of T. solium in ESA, there are still large gaps in knowledge about the occurrence of the parasite, and the resulting One Health disease complex, and monitoring of T. solium taeniosis and cysticercosis is mostly not in place.

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

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.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-022-07625-7.

Machine learning-based risk factor analysis and prevalence prediction of intestinal parasitic infections using epidemiological survey data

Background

Previous epidemiological studies have examined the prevalence and risk factors for a variety of parasitic illnesses, including protozoan and soil-transmitted helminth (STH, e.g., hookworms and roundworms) infections. Despite advancements in machine learning for data analysis, the majority of these studies use traditional logistic regression to identify significant risk factors.

Methods

In this study, we used data from a survey of 54 risk factors for intestinal parasitosis in 954 Ethiopian school children. We investigated whether machine learning approaches can supplement traditional logistic regression in identifying intestinal parasite infection risk factors. We used feature selection methods such as InfoGain (IG), ReliefF (ReF), Joint Mutual Information (JMI), and Minimum Redundancy Maximum Relevance (MRMR). Additionally, we predicted children’s parasitic infection status using classifiers such as Logistic Regression (LR), Support Vector Machines (SVM), Random Forests (RF) and XGBoost (XGB), and compared their accuracy and area under the receiver operating characteristic curve (AUROC) scores. For optimal model training, we performed tenfold cross-validation and tuned the classifier hyperparameters. We balanced our dataset using the Synthetic Minority Oversampling (SMOTE) method. Additionally, we used association rule learning to establish a link between risk factors and parasitic infections.

Key findings

Our study demonstrated that machine learning could be used in conjunction with logistic regression. Using machine learning, we developed models that accurately predicted four parasitic infections: any parasitic infection at 79.9% accuracy, helminth infection at 84.9%, any STH infection at 95.9%, and protozoan infection at 94.2%. The Random Forests (RF) and Support Vector Machines (SVM) classifiers achieved the highest accuracy when top 20 risk factors were considered using Joint Mutual Information (JMI) or all features were used. The best predictors of infection were socioeconomic, demographic, and hematological characteristics.

Conclusions

We demonstrated that feature selection and association rule learning are useful strategies for detecting risk factors for parasite infection. Additionally, we showed that advanced classifiers might be utilized to predict children’s parasitic infection status. When combined with standard logistic regression models, machine learning techniques can identify novel risk factors and predict infection risk.

In developing countries such as Ethiopia, intestinal parasites are a significant public health problem. These parasites are detrimental to the health of schoolchildren. Numerous risk factors for parasitic infections have been identified using uni- and multi-variate logistic regression. However, logistic regression has inherent limitations when applied to data sets with a large number of risk factors. We used machine learning techniques in conjunction with logistic regression models to identify relevant risk factors for parasitic infections in a dataset of 954 Ethiopian schoolchildren with 54 different risk factors for parasitic infections. Additionally, we developed predictive models of parasitic infection. Compared to logistic regression, we discovered that machine learning techniques identified novel risk factors and had higher predictive accuracy. Furthermore, we discovered that infection prediction could be aided by combining socioeconomic, health, and hematological characteristics. As a result, we concluded that advanced machine learning methods should be used in conjunction with logistic regression to study parasitic infections.