Can We Predict the Burden of Wasting in Crisis-Affected Countries? Findings from Somalia and South Sudan

Abstract

BackgroundSample surveys are the mainstay of surveillance for wasting in settings affected by crises, but are burdensome and have limited geographical coverage due to insecurity and other access issues. As a possible complement to surveys, we explored a statistical approach to predict the prevalent burden of wasting malnutrition for small population strata in two crisis-affected countries, Somalia (2014-2018) and South Sudan (2015-2018).MethodsFor each country, we sourced datasets generated by humanitarian actors or other entities on insecurity, displacement, food insecurity, access to services, epidemic occurrence and other factors on the causal pathway to malnutrition. We merged these with datasets of sample household anthropometric surveys done at administrative level 3 (district, county) as part of nutritional surveillance, and, for each of several outcomes including binary and continuous indices based on either weight-for-height or middle-upper-arm circumference, fitted and evaluated the predictive performance of generalised linear models and, as an alternative, machine learning random forests.ResultsWe developed models based on 85 ground surveys in Somalia and 175 in South Sudan. Livelihood type, measles incidence, vegetation index and water price were important predictors in Somalia, and livelihood, rainfall and terms of trade (purchasing power) in South Sudan. However, both generalised linear models and random forests had low performance for both binary and continuous anthropometric outcomes.ConclusionsPredictive models had disappointing performance and are not usable for action. The range of data used and their quality probably limited our analysis. The predictive approach remains theoretically attractive, and deserves further evaluation with larger datasets across multiple settings.

Mortality among populations affected by armed conflict in northeast Nigeria, 2016 to 2019

“…As part of identifying potential model predictors, we sourced four different databases of insecurity collected by dedicated projects: these databases tallied 10,944 (Armed Conflict Location and Event Data Project), 10,540 (Nigeria Security Tracker), 4,859 (Global Terrorism Database), and 13,300 (Nigeria Watch) people killed during our same analysis period (note that these totals reflect not just sensitivity of detection, but also database-specific inclusion criteria). Unexpectedly, none of these sources of data, despite well-documented and systematic procedures for data collection and curation, were correlated with CDR or U5DR in our models, in contrast with previous analyses in Somalia ( 22 , 23 ) and South Sudan ( 23 ), where insecurity events were a key overall mortality predictor, and with global analyses of the association of armed conflict intensity with child mortality ( 26 ). As shown in Fig.…”

“…We have used successive iterations of the small-area estimation method in different settings. During a famine in Somalia (2010 to 2012), the method found that CDR increased about fivefold to eightfold, with some 260,000 excess deaths ( 22 ), while in South Sudan we estimated 380,000 excess deaths, about 1.7 times the counterfactual ( 23 ). Repeat Somalia studies suggested about 45,000 excess deaths during the 2016 to 2018 drought ( 24 ) and a similar amount during the first year of the ongoing drought ( 25 ).…”

Law and Famine: Learning from the Hunger Courts in South Sudan

“…Famine continues to be an important topic as it is likely to become more prevalent. Despite claims that famines could end ( de Waal, 2018), over the last decade five high-profiles famines have resulted in hundreds of thousands of deaths (Checchi and Robinson, 2013;Checchi et al, 2018). The World Food Programme (WFP) -the world's largest humanitarian organization -describes how, in 2023, 900,000 people are 'fighting to survive in famine-like conditions', a 10-fold increase compared to 2018 (WFP, 2023).…”

A Touch of Genius: The Life, Work and Influence of Sir Edward Evans-Pritchard

“…The current civil war started in December 2013, and by 2015 it spread to Western Equatoria. 24 The war cost an estimated four hundred thousand lives (Checchi et al 2018), and over four million people fled their homes. 25 For many South Sudanese, forced displacement is a familiar condition.…”