Parametric Versus Non-Parametric Models for Predicting Infant Mortality within Communities in Uganda using the 2016 Uganda Demographic and Health Survey Data

Benard Odur; Elizabeth Nansubuga; Jonathan Odwee; Leonard Atuhaire

doi:10.37284/eajhs.6.1.1454

Benard Odur Makerere University
Elizabeth Nansubuga, PhD Makerere University
Jonathan Odwee, PhD Transit College
Leonard Atuhaire, PhD Makerere University

DOI: https://doi.org/10.37284/eajhs.6.1.1454

Keywords: Infant, Prediction, Machine Learning, UDHS, CatBoost

Share Article:

Abstract

Machine learning techniques have been infrequently used to identify community-based infant mortality risks. Achieving SDG 3 Targets 3.2 and 3.3 could be expedited by early detection of at-risk infants within communities. This study aimed to devise a community-centric algorithm for predicting infant mortality. We analysed UDHS 2016 data containing birth records for 22,635 children born within the five years preceding the survey, excluding those born within a year of the interview date. Twelve machine learning models were evaluated for their predictive capabilities using the area under the receiver operating characteristic curve (AUC ROC) in Python. Data subsets were divided into training and testing sets in a 2:1 ratio. Among the evaluated models, CatBoost showed superior performance with an AUC ROC of 74.9%. The five most influential variables for the CatBoost model were postnatal care utilisation, paternal age, household size, preceding birth interval, and maternal age. While the algorithm’s best performance was achieved using 28 variables, it still exhibited robust predictive power when limited to the top 8 or 10 variables. Hence, CatBoost stands out as an effective tool for identifying community-based infant mortality risks

Downloads

Download data is not yet available.

References

Aheto, J. M. K. (2019). Predictive Model and Determinants of Under-five Child Mortality: Evidence From the 2014 Ghana Demographic and Health Survey. BMC Public Health, 19(1), 1-10.

Alaa, A. M., Bolton, T., Di Angelantonio, E., Rudd, J. H., & Van der Schaar, M. (2019). Cardiovascular Disease Risk Prediction Using Automated Machine Learning: A Prospective Study of 423,604 UK Biobank Participants. PloS one, 14(5), e0213653.

Batista, A. F. M., Diniz, C. S. G., Bonilha, E. A., Kawachi, I., & Chiavegatto Filho, A. D. P. (2021). Neonatal Mortality Prediction with Routinely Collected Data: a Machine Learning Approach. BMC Pediatrics, 21(1), 322. doi:10.1186/s12887-021-02788-9

Crilly, C. J., Haneuse, S., & Litt, J. S. (2021). Predicting the Outcomes of Preterm Neonates Beyond the Neonatal Intensive Care Unit: What Are We Missing? Pediatric research, 89(3), 426-445.

Darabi, H., Choubin, B., Rahmati, O., Haghighi, A. T., Pradhan, B., & Kløve, B. (2019). Urban Flood Risk Mapping Using the GARP and QUEST Models: A Comparative Study of Machine Learning Techniques. Journal of hydrology, 569, 142-154.

Emukule, G. O., McMorrow, M., Ulloa, C., Khagayi, S., Njuguna, H. N., Burton, D., & Breiman, R. F. (2014). Predicting Mortality Among Hospitalised Children with Respiratory Illness in Western Kenya, 2009–2012. PloS one, 9(3), e92968.

Gebremariam, A. D., Tiruneh, S. A., Engidaw, M. T., Tesfa, D., Azanaw, M. M., Yitbarek, G. Y., & Asmare, G. (2021). Development and Validation of a Clinical Prognostic Risk Score to Predict Early Neonatal Mortality, Ethiopia: a Receiver Operating Characteristic Curve Analysis. Clinical Epidemiology, 637-647.

Grunberg, V. A., Geller, P. A., Bonacquisti, A., & Patterson, C. A. (2019). NICU Infant Health Severity and Family Outcomes: a Systematic Review of Assessments and Findings in Psychosocial Research. Journal of Perinatology, 39(2), 156-172.

Hatami, B., Asadi, F., Bayani, A., Zali, M. R., & Kavousi, K. (2022). Machine Learning-based System for Prediction of Ascites Grades in Patients with Liver Cirrhosis using Laboratory and Clinical Data: Design and Implementation Study. Clinical Chemistry and Laboratory Medicine (CCLM), 60(12), 1946-1954.

Hegre, H., & Sambanis, N. (2006). Sensitivity Analysis of Empirical Results on Civil war Onset. Journal of conflict resolution, 50(4), 508-535.

Joseph, A. I., & Oladokun, O. O. (2022). Assessment of Impact of Improved Sanitation and Safe-Drinking Water on Child Health in West Africa. RUJMASS.

Kovacs, D., Msanga, D. R., Mshana, S. E., Bilal, M., Oravcova, K., & Matthews, L. (2021). Developing Practical Clinical Tools for Predicting Neonatal Mortality at a Neonatal Intensive Care Unit in Tanzania. BMC Pediatrics, 21(1), 537. doi:10.1186/s12887-021-03012-4

Mangold, C., Zoretic, S., Thallapureddy, K., Moreira, A., Chorath, K., & Moreira, A. (2021). Machine Learning Models for Predicting Neonatal Mortality: a Systematic Review. Neonatology, 118(4), 394-405.

Mboya, I. B., Mahande, M. J., Mohammed, M., Obure, J., & Mwambi, H. G. (2020). Prediction of Perinatal Death using Machine Learning Models: A Birth Registry-based Cohort Study in Northern Tanzania. BMJ open, 10(10), e040132.

Medlock, S., Ravelli, A. C., Tamminga, P., Mol, B. W., & Abu-Hanna, A. (2011). Prediction of Mortality in Very Premature Infants: a Systematic Review of Prediction Models. PLoS One, 6(9), e23441. doi:10.1371/journal.pone.0023441

Muchlinski, D., Siroky, D., He, J., & Kocher, M. (2016). Comparing Random Forest with Logistic Regression for Predicting Class-imbalanced Civil War Onset Data. Political Analysis, 24(1), 87-103.

Oestergaard, M. Z., Inoue, M., Yoshida, S., Mahanani, W. R., Gore, F. M., Cousens, S., & Group, T. C. H. E. R. (2011). Neonatal Mortality Levels for 193 Countries in 2009 with Trends since 1990: a Systematic Analysis of Progress, Projections, and Priorities. PLoS medicine, 8(8), e1001080.

Ramakrishnan, R., Rao, S., & He, J.R. (2021). Perinatal Health Predictors using Artificial Intelligence: A review. Women’s Health, 17, 17455065211046132.

Rois, R. (2022). An Illustration of ML Models to Determine the Prevalence and Predicting Factors of the First-Day Neonatal Mortality in Bangladesh. World Scientific News, 164, 1-16.

Safaei-Farouji, M., Thanh, H. V., Dai, Z., Mehbodniya, A., Rahimi, M., Ashraf, U., & Radwan, A. E. (2022). Exploring the Power of Machine Learning to Predict Carbon Dioxide Trapping Efficiency in Saline Aquifers for Carbon Geological Storage Project. Journal of Cleaner Production, 372, 133778.

Saravanou, A., Noelke, C., Huntington, N., Acevedo-Garcia, D., & Gunopulos, D. (2021). Predictive Modeling of Infant Mortality. Data Mining and Knowledge Discovery, 35(4), 1785-1807. doi:10.1007/s10618-020-00728-2

Sheikhtaheri, A., Zarkesh, M. R., Moradi, R., & Kermani, F. (2021a). Prediction of Neonatal Deaths in NICUs: Development and Validation of Machine Learning Models. BMC Medical Informatics and Decision Making, 21(1), 131. doi:10.1186/s12911-021-01497-8

Sheikhtaheri, A., Zarkesh, M. R., Moradi, R., & Kermani, F. (2021b). Prediction of Neonatal Deaths in NICUs: Development and Validation of Machine Learning Models. BMC medical informatics and decision making, 21(1), 1-14.

Sun, Y., Kaur, R., Gupta, S., Paul, R., Das, R., Cho, S. J., & Singh, H. (2021). Development and Validation of High Definition Phenotype-based Mortality Prediction in Critical Care Units. JAMIA Open, 4(1). doi:10.1093/jamiaopen/ooab004

Tiwari, S., Kane, L., Koundal, D., Jain, A., Alhudhaif, A., Polat, K., & Althubiti, S. A. (2022). SPOSDS: A smart Polycystic Ovary Syndrome Diagnostic System using Machine Learning. Expert Systems with Applications, 203, 117592.

Watson, S., Arulampalam, W., Petrou, S., Marlow, N., Morgan, A., Draper, E. S., & Group, N. (2014). The Effects of Designation and Volume of Neonatal Care on Mortality and Morbidity Outcomes of Very Preterm Infants in England: Retrospective Population-based Cohort Study. BMJ open, 4(7), e004856.