Zakariya Mohammed Salih Mohammed

Eswatini faces one of the highest HIV infection rates globally, largely due to a lack of comprehensive understanding of transmission and prevention methods. This study, utilizing data from the Eswatini Multiple Indicator Cluster Survey 2020-2021, aimed to identify factors associated with knowledge of HIV/AIDS among individuals aged 15-49. A total of 3665 respondents were analyzed using a retrospective cross-sectional methodology and survey logistics regression. The findings indicated that age, education, media engagement, and Internet usage significantly correlated with comprehensive HIV knowledge. Notably, individuals aged 30-44 had higher odds of knowledge compared to those aged 45-49, while higher education increased knowledge odds over twofold. Additionally, regular reading of newspapers and Internet usage were linked to greater awareness. The study suggests that HIV prevention programs should target adolescents and marginalized groups in Eswatini.

Globally, childhood wasting has been a major public health issue for decades and its burden has been overwhelmingly borne by low- and middle-income countries. In Yemen, ongoing conflict and economic hardship have contributed to alarmingly high rates of childhood wasting. This study aimed to identify factors associated with wasting among Yemeni children under five aged based on the 2022–2023 Yemen Multiple Indicator Cluster Survey (MICS). A total of 18,389 children were investigated. Univariable and multivariable survey logistic regression models were used to examine the association of the study factors with childhood wasting. The results of the study reveal that male children, those in the first two years of life, children from low-income households and those without access to designated handwashing facilities had higher odds of childhood wasting. These findings give the policy markers a valuable direction for public health work targeting childhood malnutrition in Yemen.

This article examined the trends and burden of mental disorders in South Sudan, including their prevalence across states/administrative areas and associated mortality. The study used retrospective secondary data from the South Sudan National Demographic Health Information System (DHIS), a dataset of non-communicable diseases (NCDs). Mental disorder cases were diagnosed by medical personnel and classified according to the Diagnostic and Statistical Manual of Mental Disorders (DSM). Exploratory Data Analysis (EDA), particularly descriptive statistical methods, was employed for data analysis and visualisation, while R statistical software (R Markdown) was used to examine trends and burden. The analysis provided evidence for data-driven interventions, planning, strategy development, surveillance, and effective monitoring and evaluation of mental health programmes. The findings indicated that approximately 3,000 out of every 100,000 reported NCD cases were related to mental disorders, while 5 per cent of NCD-related deaths were associated with mental disorders. Out of every 100,000 people visiting health facilities, 19,397 had experienced mental disorders, with a higher prevalence among women than men. A significant number of cases were also reported among children under five years of age. Furthermore, mental disorder cases had increased at an estimated average rate of 32 per cent over the previous three years. The study concluded that mental disorders accounted for a significant proportion of the NCD burden in South Sudan. It contributed to the understanding of mental disorders, trends and burden of diseases, health planning and management, and the application of descriptive statistical analysis in public health research. The findings provided valuable evidence for policymakers, health planners, and programme managers seeking to strengthen mental health services and interventions in South Sudan.

This study presents an exploratory data analysis and visualisation of mental health data in South Sudan, a total of 72,414 reported cases collected between 2020 and 2022 from the National Ministry of Health via the DHIS 2. The Demographic Health Information System 2 (DHIS 2) is a data collection tool that collects data from the health facilities across the country. The mental health statistical analysis covers data for acute stress, depression, psychosis, grief, post-traumatic stress disorder, substance and drug abuse, suicide attempts, other mental health conditions and other significant mental health complaints. The study identifies trends in mental health data needed by the health providers. The detailed data analysis will facilitate data-driven interventions, planning, and monitoring of the mental health programme. The diagnosis of mental health cases was classified using the Diagnostic and Statistical Manual of Mental Disorders (DSM). The exploratory data analysis (EDA) conducted using R statistical software (R Markdown) provides good visualisations and tabulations of the mental health data. Substance & drugs abuse, post-traumatic stress disorders, suicide attempts, grief, depression and acute stress are the common mental problems in South Sudan. The data show that the acute mental health cases are increasing at a rate of 41 per cent annually. The findings are useful for re-programming mental health interventions and increasing public awareness about mental health.

Customer churn is a critical challenge for subscription-based businesses, often exacerbated by imbalanced datasets that hinder predictive accuracy. This study evaluates various oversampling techniques, K-means SMOTE, SMOTE, and ADASYN, that generate synthetic samples to balance datasets. The objective is to assess the impact of these oversampling techniques on the performance of machine learning (ML) classifiers, including gradient boosting (GB), random forest (RF), naive Bayes (NB), and support vector machines (SVM). Findings reveal that K-means SMOTE is the most effective at improving model performance, while GB consistently outperforms other classifiers in churn prediction. These findings provide valuable insights into optimizing data balancing and predictive models, offering a robust framework to enhance customer retention strategies.

Complex survey designs, such as UNICEF’s Multiple Indicator Cluster Surveys (MICS), often generate sparse cells across strata, leading to inflated odds ratios (ORs), wide confidence intervals (CIs), and convergence failures in survey-weighted logistic regression (SLR). Using Sudan MICS 2014 data on 16,679 households, this study aims to demonstrate a practical workflow to mitigate sparse-data bias: (1) SLR for population-representative estimates, (2) Firth penalized logistic regression (FPLR) to reduce bias from sparse cells, and (3) geographic collapsing of states into broader regions to improve stability. Results highlight implausibly large state-level ORs under SLR (e.g., OR=153.19 for Central Darfur) were substantially reduced after FPLR and regional collapsing. Substantively, strong gradients in handwashing facility access emerged by education, wealth, and geography, while sex of household head showed no effect. This study illustrates that combining design-based estimation, penalized likelihood, and collapsing strategies yields more stable inference in complex surveys with sparse data, offering practical guidance for applied researchers.

Background: Iron deficiency anemia (IDA) represents a significant public health concern, particularly among female populations. Various demographic factors, including age and socioeconomic status, have a substantial impact on overall health outcomes, contributing to the prevalence of IDA. The primary objective of this study was to assess the knowledge and awareness of iron deficiency anemia among the adult population and to examine its correlation with various sociodemographic factors. Methods: A cross-sectional study was conducted in the Northern Region of Saudi Arabia between October and December 2024. Data were collected using a structured questionnaire from 385 participants aged 18 years and older. The Chi-square test was utilized to assess the association between categorical variables. Results: In this study, 42.5% of participants demonstrated good knowledge of IDA, 48.1% had moderate knowledge, and 9.4% showed poor knowledge. Knowledge levels were significantly associated with gender, age, education, and self-perceived IDA status. Women, older individuals, and those with higher levels of education had a greater knowledge of IDA. Regarding attitude, 93% of participants had a positive attitude, while only 7% exhibited a negative attitude. Interestingly, none of the explanatory variables were significantly linked to attitude, suggesting that positive attitude toward IDA was consistent across all demographic groups. Conclusions: This study highlights the need for targeted health initiatives focusing on diet, supplementation, symptom recognition, and prevention to effectively reduce the burden of IDA. Prioritizing education through symposiums and medical programs in high-prevalence regions is crucial.

Under-five mortality remains a significant public health challenge in the Central African Republic (CAR), yet research on the region-specific determinants of this issue is limited. This study explores the use of machine learning (ML) models to predict under-five mortality in CAR using data from the 2018–2019 Multiple Indicator Cluster Survey (MICS). Advanced ML models, including CatBoost (CATB), Light Gradient Boosting (LGB), Extreme Gradient Boosting (XGBoost), and Extreme Gradient Boosting Random Forest (XGBRF), were compared with traditional logistic regression, with model performance evaluated using accuracy metrics such as the Area Under the Curve (AUC), F1 score, Precision, Recall, and Matthews Correlation Coefficient (MCC). CATB outperformed all models, achieving an AUC of 0.973, accuracy of 0.946, F1 score of 0.951, and MCC of 0.897, demonstrating its robust predictive power. The study identified key factors influencing under-five mortality in CAR, such as birth type, maternal education, birth order, birth interval, and birth weight. It suggests that using advanced ML models, particularly CATBoost, can improve identifying region-specific risk factors and inform targeted interventions to reduce child mortality in CAR.