Identifying Factors Associated with Neonatal Mortality in Sub-Saharan Africa Using Machine Learning

Overview

Journal AMIA Annu Symp Proc

Specialty Medical Informatics

Date 2021 May 3

PMID 33936472

Citations 9

Authors

William Ogallo

Skyler Speakman

Victor Akinwande

Kush R Varshney

Aisha Walcott-Bryant

Charity Wayua

Komminist Weldemariam

Claire-Helene Mershon

Nosa Orobaton

Affiliations

Soon will be listed here.

Abstract

This study aimed at identifying the factors associated with neonatal mortality. We analyzed the Demographic and Health Survey (DHS) datasets from 10 Sub-Saharan countries. For each survey, we trained machine learning models to identify women who had experienced a neonatal death within the 5 years prior to the survey being administered. We then inspected the models by visualizing the features that were important for each model, and how, on average, changing the values of the features affected the risk of neonatal mortality. We confirmed the known positive correlation between birth frequency and neonatal mortality and identified an unexpected negative correlation between household size and neonatal mortality. We further established that mothers living in smaller households have a higher risk of neonatal mortality compared to mothers living in larger households; and that factors such as the age and gender of the head of the household may influence the association between household size and neonatal mortality.

Citing Articles

Predicting home delivery and identifying its determinants among women aged 15-49 years in sub-Saharan African countries using a Demographic and Health Surveys 2016-2023: a machine learning algorithm.

Zegeye A, Tilahun B, Fekadie M, Addisu E, Wassie B, Alelign B BMC Public Health. 2025; 25(1):302.

PMID: 39856651 PMC: 11760118. DOI: 10.1186/s12889-025-21334-1.

Prediction of stunting and its socioeconomic determinants among adolescent girls in Ethiopia using machine learning algorithms.

Zemariam A, Abate B, Alamaw A, Lake E, Yilak G, Ayele M PLoS One. 2025; 20(1):e0316452.

PMID: 39854425 PMC: 11760002. DOI: 10.1371/journal.pone.0316452.

Population modifiable risk factors associated with neonatal mortality in 35 sub-Saharan Africa countries: analysis of data from demographic and health surveys.

Ahmed K, Thapa S, Hassen T, Tegegne T, Dadi A, Odo D EClinicalMedicine. 2024; 73:102682.

PMID: 39007064 PMC: 11245992. DOI: 10.1016/j.eclinm.2024.102682.

Employing supervised machine learning algorithms for classification and prediction of anemia among youth girls in Ethiopia.

Zemariam A, Yimer A, Abebe G, Wondie W, Abate B, Alamaw A Sci Rep. 2024; 14(1):9080.

PMID: 38643324 PMC: 11032364. DOI: 10.1038/s41598-024-60027-4.

Predicting facility-based delivery in Zanzibar: The vulnerability of machine learning algorithms to adversarial attacks.

Tsai Y, Fulcher I, Li T, Sukums F, Hedt-Gauthier B Heliyon. 2023; 9(5):e16244.

PMID: 37234636 PMC: 10205516. DOI: 10.1016/j.heliyon.2023.e16244.

References

Kaguthi G, Nduba V, Borgdorff M, Verver S . Predictors of post neonatal mortality in Western Kenya: a cohort study. Pan Afr Med J. 2019; 31:114. PMC: 6462392. DOI: 10.11604/pamj.2018.31.114.16725. View

Nasejje J, Mwambi H . Application of random survival forests in understanding the determinants of under-five child mortality in Uganda in the presence of covariates that satisfy the proportional and non-proportional hazards assumption. BMC Res Notes. 2017; 10(1):459. PMC: 5590231. DOI: 10.1186/s13104-017-2775-6. View

Mekonnen Y, Tensou B, Telake D, Degefie T, Bekele A . Neonatal mortality in Ethiopia: trends and determinants. BMC Public Health. 2013; 13:483. PMC: 3659057. DOI: 10.1186/1471-2458-13-483. View

Tesfaye B, Atique S, Elias N, Dibaba L, Shabbir S, Kebede M . Determinants and development of a web-based child mortality prediction model in resource-limited settings: A data mining approach. Comput Methods Programs Biomed. 2017; 140:45-51. DOI: 10.1016/j.cmpb.2016.11.013. View

Grady S, Frake A, Zhang Q, Bene M, Jordan D, Vertalka J . Neonatal mortality in East Africa and West Africa: a geographic analysis of district-level demographic and health survey data. Geospat Health. 2017; 12(1):501. DOI: 10.4081/gh.2017.501. View

Barros A, Victora C . Measuring coverage in MNCH: determining and interpreting inequalities in coverage of maternal, newborn, and child health interventions. PLoS Med. 2013; 10(5):e1001390. PMC: 3646214. DOI: 10.1371/journal.pmed.1001390. View

Bellizzi S, Bassat Q, Ali M, Sobel H, Temmerman M . Effect of Puerperal Infections on Early Neonatal Mortality: A Secondary Analysis of Six Demographic and Health Surveys. PLoS One. 2017; 12(1):e0170856. PMC: 5266333. DOI: 10.1371/journal.pone.0170856. View

Mengesha H, Wuneh A, Lerebo W, Tekle T . Survival of neonates and predictors of their mortality in Tigray region, Northern Ethiopia: prospective cohort study. BMC Pregnancy Childbirth. 2016; 16(1):202. PMC: 4971662. DOI: 10.1186/s12884-016-0994-9. View

Natekin A, Knoll A . Gradient boosting machines, a tutorial. Front Neurorobot. 2014; 7:21. PMC: 3885826. DOI: 10.3389/fnbot.2013.00021. View

10.

Kraamwinkel N, Ekbrand H, Davia S, Daoud A . The influence of maternal agency on severe child undernutrition in conflict-ridden Nigeria: Modeling heterogeneous treatment effects with machine learning. PLoS One. 2019; 14(1):e0208937. PMC: 6326456. DOI: 10.1371/journal.pone.0208937. View

11.

Cleland J, Sathar Z . The Effect of birth spacing on childhood mortality in Pakistan. Popul Stud (Camb). 2011; 38(3):401-18. DOI: 10.1080/00324728.1984.10410300. View

12.

Belachew A, Tewabe T, Dessie G . Neonatal mortality and its association with antenatal care visits among live births in Ethiopia: a systematic review and meta-analysis. J Matern Fetal Neonatal Med. 2020; 35(2):348-355. DOI: 10.1080/14767058.2020.1718093. View

13.

Tiruye T, Chojenta C, Harris M, Holliday E, Loxton D . The Role of Maternal Intimate Partner Violence Victimization on Neonatal Mortality in Ethiopia. J Interpers Violence. 2020; 36(23-24):10938-10958. DOI: 10.1177/0886260519897331. View

14.

Dwomoh D, Amuasi S, Agyabeng K, Incoom G, Alhassan Y, Yawson A . Understanding the determinants of infant and under-five mortality rates: a multivariate decomposition analysis of Demographic and Health Surveys in Ghana, 2003, 2008 and 2014. BMJ Glob Health. 2019; 4(4):e001658. PMC: 6626520. DOI: 10.1136/bmjgh-2019-001658. View

15.

Ozodiegwu I, Mamudu H, Wang L, Wallace R, Quinn M, Liu Y . Country-Level Analysis of the Association between Maternal Obesity and Neonatal Mortality in 34 Sub-Saharan African Countries. Ann Glob Health. 2019; 85(1):139. PMC: 6896841. DOI: 10.5334/aogh.2510. View