Background/Objectives: Early childhood anemia is a severe public health concern and the most common blood disorder worldwide, especially in emerging countries. This study examines the sources of childhood anemia in Ghana through various societal, parental, and child characteristics. Methods: This research used data from the 2022 Ghana Demographic and Health Survey (GDHS-2022), which comprised 9353 children. Using STATA 13 and R 4.4.2 software, we analyzed maternal, social, and child factors using a model-building procedure, logistic regression analysis, and machine learning (ML) algorithms. The analyses comprised machine learning methods including decision trees, K-nearest neighbor (KNN), logistic regression, and random forest (RF). We used discrimination and calibration parameters to evaluate the performance of each machine learning algorithm. Results: Key predictors of childhood anemia are the father’s education, socioeconomic status, iron intake during pregnancy, the mother’s education, and the baby’s postnatal checkup within two months. With accuracy (94.74%), sensitivity (82.5%), specificity (50.78%), and AUC (86.62%), the random forest model was proven to be the most effective machine learning predictive model. The logistic regression model appeared second with accuracy (67.35%), sensitivity (76.16%), specificity (56.05%), and AUC (72.47%). Conclusions: Machine learning can accurately predict childhood anemia based on child and paternal characteristics. Focused interventions to enhance maternal health, parental education, and family economic status could reduce the prevalence of early childhood anemia and improve long-term pediatric health in Ghana. Early intervention and identifying high-risk youngsters may be made easier with the application of machine learning techniques, which will eventually lead to a healthier generation in the future.

Background and Objective: This study examines the factors associated with child undernutrition among children under five in Ethiopia, Kenya, Madagascar, and Tanzania. It uses the Composite Index of Anthropometric Failure to measure the full burden of undernutrition, combining weight-for-height (WHZ), weight-for-age (WAZ), and height-for-age (HAZ) indicators. This approach captures children facing multiple forms of failure that single indicators miss. Methods: The study analyzed 37,570 children using nationally representative Demographic and Health Survey (DHS) data for Ethiopia 2019, Kenya 2022, Madagascar 2021, and Tanzania 2022. A binary logistic regression model identified key predictors of child undernutrition across countries. Results: The prevalence of anthropometric failure ranged from 24% to 44%. Higher parental education, child’s age, socioeconomic status, child’s sex, and a postnatal checkup within 2 months were associated with a lower odds of anthropometric failure. Children of educated mothers in Ethiopia (AOR = 0.547) and Tanzania (AOR = 0.606) had better outcomes. Educated fathers in Kenya (AOR = 0.589) and Madagascar (AOR = 0.369) reduced the risk of child undernutrition. Children aged 13–24 months had a higher risk in all countries. In Madagascar (AOR = 0.309), children who received a postnatal checkup had a decreased risk of malnutrition. Children from rich households in Ethiopia (AOR = 0.645) and from middle (AOR = 0.683) and rich (AOR = 0.535) households in Kenya had significantly lower odds of undernutrition. In comparison, female children had lower odds of anthropometric failure in all four countries. Conclusions: Viewed through a nutrition equity lens, these findings underscore the importance of recognizing how the intersectionality of anthropometric failures disproportionately affects children from poorer households and communities with limited access to education and postnatal care. This study advances existing knowledge by using the Composite Index of Anthropometric Failure to show overlapping and hidden forms of undernutrition. The findings identify child age, parental education, postnatal checkup, child sex, and socioeconomic status as shared priorities for reducing undernutrition. The results provide country-specific insights for designing integrated, evidence-based nutrition interventions in Eastern Africa.

Objective: To investigate differentials and determinants of neonatal mortality in Pakistan. Method: The cross-sectional data-based study was conducted at Lahore College for Women University, Lahore, Pakistan from February to July 2019, and comprised data obtained from the Pakistan Demographic and Health Survey 2017-18 which related to the period from November 22, 2017, to April 30, 2018. Neonatal mortality rates were computed to observe the differentials in relation to various categories of socio-demographic factors. Cox proportional hazard model was used to identify significant factors affecting neonatal mortality. Results: Hazard of neonatal mortality significantly decreased as household size increased (hazard ratio: 0.41 and 0.36). Household with improved toilet facility had significantly lower chances (hazard ratio: 0.57) of neonatal death compared to that with unimproved toilet facility. Significantly elevated risk (hazard ratio: 5.56) of neonate death was observed in case of multiple births. Children had better chances (hazard ratio: 0.32 and 0.34) of surviving in neonatal period as duration of birth spacing increased (24-35 months; 36 or more months). Conclusion: Household size, improved toilet facilities, multiple births and preceding birth intervals had significant effect on neonatal mortality.

Healthcare access is a fundamental human right, yet barriers often negatively impact health, particularly in developing countries like Pakistan, where maternal mortality remains a crisis. This study aimed to identify factors influencing healthcare access barriers among married women aged 15–49 years using spatial analysis. Methods: Data were drawn from the 2017-18 Pakistan Demographic and Health Survey (PDHS), which included an unweighted sample of 8127 women. Healthcare access barriers were identified as the outcome variable. Results: A spatial analysis using ArcGIS 10.7.1 and SaTScan identified clustered distributions, with concentration areas identified in Gilgit Baltistan, Khyber Pakhtunkhwa (KPK), Federally Administered Tribal Areas (FATA), Punjab, and Balochistan. SaTScan highlighted primary clusters in FATA, Southern KPK, Northern Balochistan, and Eastern Punjab. Geographically Weighted Regression identified women who had five or more living children, respondents who did not have four or more antenatal care (ANC) visits, respondents who experienced a lower income (wealth index), respondents who did not participate in decision-making, respondents with a primary education, and respondents who accepted domestic violence as the significant predictors of healthcare access barriers. Conclusions: To improve women’s healthcare access, integrated policy interventions are needed, addressing socioeconomic disparities, strengthening national health policies, empowering women, and expanding healthcare accessibility. Strengthening health insurance and economic empowerment is crucial for achieving Sustainable Development Goals.

Background: Pakistan has an inadequate vital event registration system, leading to fewer than half of all births being registered, and this issue is further exacerbated by systematic recall errors and omission of births. This study aims to evaluate direct and indirect methods of fertility estimation to analyze the trends and patterns of fertility rates in Pakistan from 1990 to 2018. Design/methodology/approach: Indirect methods are utilized in this study to evaluate the direction and extent of changes in total and age-specific fertility rates, and these findings are compared to direct estimates. The study draws data on livebirths from four waves of the Pakistan Demographic and Health Survey that took place between 1990 and 2018. To ensure the quality of data, graphical methods and Whipple and Myers indices are employed. Additionally, the Brass Relational Gompertz model was used to analyze the data. Results: The Relational Gompertz model revealed that total fertility rates (TFRs) were higher than direct estimates by 0.4 children and age-specific fertility rates (ASFR) were higher for all age groups except the oldest. The difference was more significant among younger women aged 15–24, and less so for age groups 29 and above. The gap in estimated fertility between direct and indirect methods decreased with age. Conclusion: The indirect method is an invaluable tool in situations where direct measurement of fertility rates is challenging or impossible. By utilizing this method, policymakers can gain important insights into the fertility patterns and trends of a population, which is crucial for making informed decisions on fertility planning.