Abstract
Using a novel machine learning approach, we identify and prioritize in terms of predictive potency the top 10 distal causes of under-5 child mortality from almost 40 potential distal causes in more than a quarter of a million households in more than 25 low- and middle-income countries. Notably, all 10 distal causes are preventable and treatable through social, educational, and physical intervention. Thus, a unique contribution of our machine learning approach is to identify lesser-known preventable and treatable distal causes of under-5 child mortality that likely account for better-known proximal causes. Funding Statement: A.B. was supported by a Post-doctoral Fellowship within MIUR programme framework ”Dipartimenti di Eccellenza” (DiPSCO, University of Trento). G.E. was supported by NAP SUG 2015, Singapore Ministry of Education ACR Tier 1 (RG149/16 and RT10/19). M.H.B. was supported by the Intramural Research Program of the NIH/NICHD, USA, and an International Research Fellowship at the Institute for Fiscal Studies (IFS), London, UK, funded by the European Research Council (ERC) under the Horizon 2020 research and innovation programme (grant agreement No 695300- HKADeC-ERC-2015-AdG). Computational resources were provided by the National Super Computing Center of Singapore (Project ID: 12001609; Computational study of Child Development in Low Resource Contexts). Declaration of Interests: The Authors declare no conflict of interest. Ethics Approval Statement: Ethics approvals were handled in each site in which data were collected.
Highlights
In this study we used a machine learning framework derived from bio-informatics to delineate and rank distal causes of under-5 Child Mortality (CM) in low- and middle-income countries (LMIC)
This is the first time that a Machine Learning (ML) framework has been applied to the Multiple Indicators Cluster Survey (MICS) dataset or to identifying and prioritizing causes of under-5 CM
When the knowledge and technology for life-saving interventions are available, it is unacceptable that 15,000 children die every day from preventable causes
Summary
We used data of the Multiple Indicators Cluster Survey (MICS) (N = 275,160) from 27 LMIC and a machine-learning approach to rank 37 distal causes of CM and identify the top 10 causes in terms of predictive potency. Based on the top 10 causes, we identified households with improved conditions. We retrospectively validated the results by investigating the association between variations of CM and variations of the percentage of households with improved conditions at country-level, between the 2005–2007 and the 2013–2017 administrations of the MICS. A unique contribution of our approach is to identify lesser-known distal causes which likely account for better-known proximal causes: notably, the identified distal causes and preventable and treatable through social, educational, and physical interventions. We demonstrate how machine learning can be used to obtain operational information from big dataset to guide interventions and policy makers.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have