Predicting the burden of acute malnutrition in drought-prone regions of Kenya

In drought-prone regions, timely and granular predictions of the burden of acute malnutrition could support decision-making. We explored whether routinely collected and/or publicly available data could be used to predict the prevalence of global and severe acute malnutrition, as well as the mean weight-for-height Z-score and middle-upper-arm circumference for age Z-score, in arid- and semi-arid regions of Kenya, where drought is projected to increase in frequency and intensity. The study covered six counties of northern Kenya and the period 2015–2019, during which a major drought occurred. To validate models, we sourced and curated so-called SMART anthropometric surveys covering one or more sub-counties for a total of 79 explicit survey strata and 44,218 individual child observations. We associated these surveys’ predictors specified at the sub-county or county level, and comprising climate food security, observed malnutrition, epidemic disease incidence, health service utilisation and other social conditions. We explored both generalised linear or additive models and random forests and quantified their out-of-sample performance using cross-validation. In most counties, survey-estimated nutritional indicators were worst during the October 2016-December 2019 drought period; the drought also saw peaks in insecurity and steep vaccination declines. Candidate models had moderate performance, with random forests slightly outperforming generalised linear models. The most promising performance was observed for global acute malnutrition prevalence. The study did not identify a model that could very accurately predict malnutrition burden, but analyses relying on larger datasets with a wider range of predictors and encompassing multiple drought periods may yield sufficient performance and are warranted given the potential utility and efficiency of predictive models in lieu of assumptions or expensive and untimely ground data collection

Environmental health · Geography · Malnutrition · Severe Acute Malnutrition · Statistical analysis · Statistics · Child Nutrition and Water Access · Internal Medicine · Mathematics · Medicine

• Fast Stable Restricted Maximum Likelihood and Marginal Likelihood Estimation of Semiparametric Generalized Linear Models

  Open Access•Simon N Wood•Journal of the Royal Statistical…•2011

  Incluir item

• Global spatio-temporally harmonised datasets for producing high-resolution gridded population distribution datasets

  Open Access•Christopher T Lloyd, Heather Chamberlain et al.•Big Earth Data•2019

  Incluir item

• Mapping HIV prevalence in sub-Saharan Africa between 2000 and 2017

  Open Access•Laura Dwyer-Lindgren, Laura Dwyer‐Lindgren et al.•Nature•2019

  Incluir item

• Ranger

  Open Access•Marvin N Wright, Andreas Ziegler•Journal of Statistical Software•2017

  Incluir item

• Questioning global health in the times of Covid-19

  Open Access•Ritu Priya, Amitabha Sarkar et al.•Humanities and Social Sciences…•2023

  Incluir item

• Nutritional Challenges among African Refugee and Internally Displaced Children

  Open Access•Claire Gooding, Salwa Musa et al.•Children•2024

  Incluir item