Application of machine learning methods for predicting under-five mortality: analysis of Nigerian demographic health survey 2018 dataset

BACKGROUND

Under-five mortality remains a significant public health issue in developing countries. This study aimed to assess the effectiveness of various machine learning algorithms in predicting under-five mortality in Nigeria and identify the most relevant predictors.

METHODS

The study used nationally representative data from the 2018 Nigeria Demographic and Health Survey. The study evaluated the performance of the machine learning models such as the artificial neural network, k-nearest neighbourhood, Support Vector Machine, Naïve Bayes, Random Forest, and Logistic Regression using the true positive rate, false positive rate, accuracy, precision, F-measure, Matthew's correlation coefficient, and the Area Under the Receiver Operating Characteristics.

RESULTS

The study found that machine learning models can accurately predict under-five mortality, with the Random Forest and Artificial Neural Network algorithms emerging as the best models, both achieving an accuracy of 89.47% and an AUROC of 96%. The results show that under-five mortality rates vary significantly across different characteristics, with wealth index, maternal education, antenatal visits, place of delivery, employment status of the woman, number of children ever born, and region found to be the top determinants of under-five mortality in Nigeria.

CONCLUSIONS

The findings suggest that machine learning models can be useful in predicting U5M in Nigeria with high accuracy. The study emphasizes the importance of addressing social, economic, and demographic disparities among the population in Nigeria. The study's findings can inform policymakers and health workers about developing targeted interventions to reduce under-five mortality in Nigeria.

Effects of short birth interval on different forms of child mortality in Bangladesh: Application of propensity score matching technique with inverse probability of treatment weighting

BACKGROUND

The prevalence of Short Birth Interval (SBI) is higher in Low- and Middle-Income countries (LMICs), including Bangladesh. Previous studies in LMICs have estimated the effects of SBI on child mortality by comparing two unequal groups of mothers based on their socio-economic status. This approach may lead to overestimation or underestimation of the true effect of birth interval on child mortality, particularly when sample sizes are relatively small.

OBJECTIVE

We determined the effects of SBI on several forms of child mortality in Bangladesh by comparing two equal groups created by applying the propensity score matching technique.

METHODS

This study analyzed data from 5,941 mothers and 1,594 health facilities extracted from the 2017/18 Bangladesh Demographic and Health Survey and the 2017 Bangladesh Health Facility Survey. The exposure variable was SBI (defined as the interval between two subsequent births <33 months: yes, no), while the outcome variables were neonatal mortality (defined as mortality within 28 days of birth: yes, no), infant mortality (defined as mortality within 1 year of birth: yes, no), and under-five mortality (defined as mortality within 5 years of birth: yes, no). Multilevel Poisson regression based on inverse probability treatment weights was used to determine the association between exposure and outcome variables.

RESULTS

The prevalence rates of neonatal, infant, and under-five mortality were 48.8, 30.8, and 23.1 per 1000 live births, respectively. Newborns of SBI mothers were found to have a 63% higher likelihood of neonatal mortality (aPR, 1.63; 95% CI, 1.08-2.46) compared to newborns of non-SBI mothers. Furthermore, the prevalence of infant mortality and under-five mortality was 1.45 times higher (aPR, 1.45; 95% CI, 1.01-2.08) and 2.82 times higher (aPR, 2.82; 95% CI, 2.16-3.70), respectively, among babies born in a short interval of their immediately preceding sibling as compared to babies born in a normal interval of their immediately preceding sibling.

CONCLUSIONS

Findings of this study indicate that SBI is an important predictor of child mortality. Consequently, around 1 million children born in a short interval every year in Bangladesh are at risk of dying before reaching their fifth birthday. This indicates a challenge for Bangladesh to achieve the SDG 3 target to reduce neonatal and under-five mortality to 12 and 25 deaths per 1000 live births, respectively. Hence, awareness-building programs about the adverse effects of SBI and strengthening existing healthcare facilities are important.

A Systematic Review of Factors Associated with Under-Five Child Mortality

BACKGROUND

Preventing the life of the newborn and reducing the entrenched disparity of childhood mortality across different levels is one of the crucial public health problems, especially in underdeveloped and developing countries in the world. Sustainable development goals (SDGs)-3.2 is aimed at terminating all preventable under-five child mortality and shrinking it to 25 per 1000 live births or lower than this by 2030. Several factors have been shown to be linked with childhood mortality.

OBJECTIVE

This review is aimed at pointing out the significant determinants related to under-five child mortality by a systematic review of the literature.

METHODS

EMBASE, PubMed, Scopus database, and Google Scholar search engine were used for the systematic search of the literature. Special keywords and Boolean operators were used to point out the relevant studies for the review. Original research articles and peer-reviewed papers published in the English language till August 10, 2022, were included in the analysis and synthesis of the results. As per the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines, out of 299 studies identified from different sources, only 22 articles were ascertained for this study. Eligible articles were appraised in detail, and relevant information was extracted and then integrated into the systematic review.

RESULTS

Mother's education, size of child at birth, age of mother at childbirth, place of residence, birth interval, sex of child, type of birth (single or multiple), and birth order, along with other socioeconomic, maternal, child, health facility utilization, and community level variables, were observed as important covariates of under-five mortality.

CONCLUSION

Women's education and easy access to quality healthcare facilities should be the apex priority to lessen childhood mortality.

Geographic variation and factors associated with under-five mortality in Ethiopia. A spatial and multilevel analysis of Ethiopian mini demographic and health survey 2019

BACKGROUND

The distribution of under-five mortality (U5M) worldwide is uneven and the burden is higher in Sub-Saharan African countries, which account for more than 53% of the global under-five mortality. In Ethiopia, though U5M decreased substantially between 1990 and 2019, it remains excessively high and unevenly distributed. Therefore, this study aimed to assess geographic variation and factors associated with under-five mortality (U5M) in Ethiopia.

METHODS

We sourced data from the most recent nationally representative 2019 Ethiopian Mini-Demographic and Health Survey for this study. A sample size of 5,695 total births was considered. Descriptive, analytical analysis and spatial analysis were conducted using STATA version 16. Both multilevel and spatial analyses were employed to ascertain the factors associated with U5M in Ethiopia.

RESULTS

The U5M was 5.9% with a 95% CI 5.4% to 6.6%. Based on the multivariable multilevel logistic regression model results, the following characteristics were associated with under-five mortality: family size (AOR = 0.92, 95% CI: 0.84,0.99), number of under-five children in the family (AOR = 0.17, 95% CI: 0.14, 0.21), multiple birth (AOR = 14.4, 95% CI: 8.5, 24.3), children who were breastfed for less than 6 months (AOR = 5.04, 95% CI: 3.81, 6.67), people whose main roof is palm (AOR = 0.57, 95% CI: 0.34, 0.96), under-five children who are the sixth or more child to be born (AOR = 2.46, 95% CI: 1.49, 4.06), institutional delivery (AOR = 0.57, 95% CI: 0.41, 0.81), resident of Somali and Afar region (AOR = 3.46, 95% CI: 1.58, 7.55) and (AOR = 2.54, 95% CI: 1.10, 5.85), respectively. Spatial analysis revealed that hot spot areas of under-five mortality were located in the Dire Dawa and Somali regions.

CONCLUSION

Under-five mortality in Ethiopia is high and unacceptable when compared to the 2030 sustainable development target, which aims for 25 per 1000 live births. Breastfeeding for less than 6 months, twin births, institutional delivery and high-risk areas of under-five mortality (Somali and Dire Dawa) are modifiable risk factors. Therefore, maternal and community education on the advantages of breastfeeding and institutional delivery is highly recommended. Women who deliver twins should be given special attention. An effective strategy should be designed for intervention in under-five mortality hot spot areas such as Somali and Dire Dawa.

Effect of health extension service on under-five child mortality and determinants of under-five child mortality in Derra district, Oromia regional state, Ethiopia: A cross-sectional study

Objectives:

Under-five child mortality is the highest in Ethiopia even though it decreased steadily in the last two decades. Hence, this study aimed to identify the risk factors and effects of Health Extension Service on under-five child mortality per mother in Derra district, Ethiopia.

Methods:

The study used a three-stage sampling technique and a random sample of 446 mothers. Cross-sectional data were collected using a structured interview and analyzed using descriptive and inferential (propensity score and Poisson regression) analysis.

Results:

One-fourth (23.5%) of mothers experienced at least one under-five child mortality in the last 13 years and the propensity score analysis also indicated that utilizing and model in the Health Extension program reduced under-five child mortality per mother by 29.84% and 15.71%, respectively. The Poisson regression model identified that kebeles, not utilized health extension program (incidence rate ratio 2.25, 95% confidence interval (1.33, 3.85)), not model in health extension program (incidence rate ratio 1.79, 95% confidence interval (1.07, 3.18)), primary educational level (incidence rate ratio 0.14, 95% confidence interval (0.18, 0.91)), mother aged at first birth less than 20 years (incidence rate ratio 1.82, 95% confidence interval (1.90, 3.05)), source of drinking water not pipped (incidence rate ratio 2.36, 95% confidence interval (1.20, 3.18)), and child delivered at home (incidence rate ratio 2.48, 95% confidence interval (1.26, 4.8)) significantly influence under-five child mortality per mother at 5% level of significance.

Conclusion:

Health extension service utilization reduced under-five child mortality per mother, and education level, source of drinking water, place of child delivery, and place of residence (kebele) were significant risk factors for under-five child mortality per mother. The health sectors and district health offices should work on health extension program to increase the community awareness of basic preventive and promotive health services and minimize risk factors of under-five child mortality.