ACSPRI Conferences, ACSPRI Social Science Methodology Conference 2018

Font Size:  Small  Medium  Large

Under-five mortality and the continuum of care for Reproductive, Maternal, Newborn and Child Health: A Machine Learning analysis.

Adeyinka Emmanuel Adegbosin, Jing Sun

Building: Holme Building
Room: Sutherland Room
Date: 2018-12-13 03:30 PM – 05:00 PM
Last modified: 2018-12-12


Continuum of care for RMNCH refers to integrated care for the health of mothers, neonates and children. The benefit of utilizing Machine Learning (ML) to predict under-five mortality outcome have not been evaluated in any previous study. Therefore, the aim of this study is to use ML to evaluate the association between continuum of RMNCH care and all-cause under five mortality.
In this study, we utilised data from the Multiple Indicator Cluster Survey (MICS), and the Demographic and Health Survey (DHS). Analysis was conducted on data from five Low and Middle-Income Countries (LMICs), across five UNICEF sub-regions. ML approach was used to explore the association between under-five mortality and integrated RMNCH care, which comprises of: Preconception care, Antenatal care, Skilled Birth services, Postnatal care, childhood and neonatal health and nutritional services.
We will report the Receiver-Operating Characteristics (ROC) for prediction of all-cause under-five mortality. The Area-Under-the-Curve findings on continuum of care and under-five mortality prediction will be enumerated.
Based on our findings, we will draw inference on how the continuum of care for RMNCH predicts under-five mortality. Our findings will potentially provide a decision-tool that can guide maternal and child health service delivery and help identify interventions that needs to be prioritized.