Use of a Deep Learning and Random Forest Approach to Track Changes in the Predictive Nature of Socioeconomic Drivers of Under-5 Mortality Rates in Sub-Saharan Africa

Overview

Journal BMJ Open

Specialty General Medicine

Date 2022 Feb 18

PMID 35177443

Authors

Justine B Nasejje

Rendani Mbuvha

Henry Mwambi

Affiliations

Soon will be listed here.

Abstract

Objectives: We used machine learning algorithms to track how the ranks of importance and the survival outcome of four socioeconomic determinants (place of residence, mother's level of education, wealth index and sex of the child) of under-5 mortality rate (U5MR) in sub-Saharan Africa have evolved.

Settings: This work consists of multiple cross-sectional studies. We analysed data from the Demographic Health Surveys (DHS) collected from four countries; Uganda, Zimbabwe, Chad and Ghana, each randomly selected from the four subregions of sub-Saharan Africa.

Participants: Each country has multiple DHS datasets and a total of 11 datasets were selected for analysis. A total of n=85 688 children were drawn from the eleven datasets.

Primary And Secondary Outcomes: The primary outcome variable is U5MR; the secondary outcomes were to obtain the ranks of importance of the four socioeconomic factors over time and to compare the two machine learning models, the random survival forest (RSF) and the deep survival neural network (DeepSurv) in predicting U5MR.

Results: Mother's education level ranked first in five datasets. Wealth index ranked first in three, place of residence ranked first in two and sex of the child ranked last in most of the datasets. The four factors showed a favourable survival outcome over time, confirming that past interventions targeting these factors are yielding positive results. The DeepSurv model has a higher predictive performance with mean concordance indexes (between 67% and 80%), above 50% compared with the RSF model.

Conclusions: The study reveals that children under the age of 5 in sub-Saharan Africa have favourable survival outcomes associated with the four socioeconomic factors over time. It also shows that deep survival neural network models are efficient in predicting U5MR and should, therefore, be used in the big data era to draft evidence-based policies to achieve the third sustainable development goal.

Citing Articles

Predictors of pregnancy loss among urban and rural women aged 15 to 49 years in Pakistan.

Samuel K, Kandala N, Ryan B, Thind A BMC Public Health. 2025; 25(1):950.

PMID: 40065258 PMC: 11895280. DOI: 10.1186/s12889-025-22165-w.

References

Sousa A, Hill K, Dal Poz M . Sub-national assessment of inequality trends in neonatal and child mortality in Brazil. Int J Equity Health. 2010; 9:21. PMC: 2944212. DOI: 10.1186/1475-9276-9-21. View

Pencina M, DAgostino R . Overall C as a measure of discrimination in survival analysis: model specific population value and confidence interval estimation. Stat Med. 2004; 23(13):2109-23. DOI: 10.1002/sim.1802. View

Mariani L, Coradini D, Biganzoli E, Boracchi P, Marubini E, Pilotti S . Prognostic factors for metachronous contralateral breast cancer: a comparison of the linear Cox regression model and its artificial neural network extension. Breast Cancer Res Treat. 1997; 44(2):167-78. DOI: 10.1023/a:1005765403093. View

Ayele D, Zewotir T, Mwambi H . Survival analysis of under-five mortality using Cox and frailty models in Ethiopia. J Health Popul Nutr. 2017; 36(1):25. PMC: 5455089. DOI: 10.1186/s41043-017-0103-3. View

Wright M, Dankowski T, Ziegler A . Unbiased split variable selection for random survival forests using maximally selected rank statistics. Stat Med. 2017; 36(8):1272-1284. DOI: 10.1002/sim.7212. View

Wright M, Ziegler A, Konig I . Do little interactions get lost in dark random forests?. BMC Bioinformatics. 2016; 17:145. PMC: 4815164. DOI: 10.1186/s12859-016-0995-8. View

Faraggi D, Simon R . A neural network model for survival data. Stat Med. 1995; 14(1):73-82. DOI: 10.1002/sim.4780140108. View

Harrell Jr F, Lee K, Califf R, Pryor D, Rosati R . Regression modelling strategies for improved prognostic prediction. Stat Med. 1984; 3(2):143-52. DOI: 10.1002/sim.4780030207. View

Van Malderen C, Amouzou A, Barros A, Masquelier B, Van Oyen H, Speybroeck N . Socioeconomic factors contributing to under-five mortality in sub-Saharan Africa: a decomposition analysis. BMC Public Health. 2019; 19(1):760. PMC: 6570834. DOI: 10.1186/s12889-019-7111-8. View

10.

Katzman J, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y . DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Med Res Methodol. 2018; 18(1):24. PMC: 5828433. DOI: 10.1186/s12874-018-0482-1. View

11.

Gordon L, Olshen R . Tree-structured survival analysis. Cancer Treat Rep. 1985; 69(10):1065-9. View

12.

Yohannes T, Laelago T, Ayele M, Tamrat T . Mortality and morbidity trends and predictors of mortality in under-five children with severe acute malnutrition in Hadiya zone, South Ethiopia: a four-year retrospective review of hospital-based records (2012-2015). BMC Nutr. 2020; 3:18. PMC: 7050820. DOI: 10.1186/s40795-017-0135-5. View

13.

Kimani-Murage E, Fotso J, Egondi T, Abuya B, Elungata P, Ziraba A . Trends in childhood mortality in Kenya: the urban advantage has seemingly been wiped out. Health Place. 2014; 29:95-103. PMC: 4158907. DOI: 10.1016/j.healthplace.2014.06.003. View

14.

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

15.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

16.

Sargent D . Comparison of artificial neural networks with other statistical approaches: results from medical data sets. Cancer. 2001; 91(8 Suppl):1636-42. DOI: 10.1002/1097-0142(20010415)91:8+<1636::aid-cncr1176>3.0.co;2-d. View

17.

Morakinyo O, Fagbamigbe A . Neonatal, infant and under-five mortalities in Nigeria: An examination of trends and drivers (2003-2013). PLoS One. 2017; 12(8):e0182990. PMC: 5549979. DOI: 10.1371/journal.pone.0182990. View

18.

Yousefi S, Amrollahi F, Amgad M, Dong C, Lewis J, Song C . Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models. Sci Rep. 2017; 7(1):11707. PMC: 5601479. DOI: 10.1038/s41598-017-11817-6. View

19.

Strobl C, Boulesteix A, Kneib T, Augustin T, Zeileis A . Conditional variable importance for random forests. BMC Bioinformatics. 2008; 9:307. PMC: 2491635. DOI: 10.1186/1471-2105-9-307. View

20.

Nasejje J, Mwambi H, Dheda K, Lesosky M . A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data. BMC Med Res Methodol. 2017; 17(1):115. PMC: 5534080. DOI: 10.1186/s12874-017-0383-8. View