Using Machine Learning to Fight Child Acute Malnutrition and Predict Weight Gain During Outpatient Treatment with a
Luis Javier Sánchez-Martínez1, Pilar Charle-Cuéllar2, Abdoul Aziz Gado3
1Unit of Physical Anthropology, Department of Biodiversity, Ecology and Evolution, Faculty of Biological Sciences, Complutense University of Madrid, 28040 Madrid, Spain.
Nutrients
|December 17, 2024
Summary
Machine learning accurately predicts low weight gain in children with acute malnutrition using socio-economic data. This helps tailor treatment protocols in humanitarian settings for better outcomes.
Area of Science:
- Public Health
- Machine Learning
- Pediatrics
Background:
- Child acute malnutrition affects 45 million children globally.
- World Health Organization recommends weekly weight monitoring for treatment.
- Simplified protocols using arm circumference are used in emergency settings.
Purpose of the Study:
- Predict weight gain in children with acute malnutrition using machine learning.
- Identify socio-economic factors influencing weight gain.
- Optimize treatment protocols in humanitarian settings.
Main Methods:
- Utilized machine learning (Random Forest, ensemble models) on 51 socio-economic variables.
- Selected key variables using Variable Selection Using Random Forest (VSURF).
- Employed Receiver Operating Characteristic (ROC) curves to determine optimal cut-off points.
Main Results:
- Socio-economic factors like water, sanitation, caregiver employment, and treatment access are critical.
- Ensemble model achieved R2 = 0.55, outperforming individual algorithms.
- Identified an optimal cut-off (<6.5 g/kg/day) with AUC 0.777, achieving 84% success in identifying low weight gain.
Conclusions:
- Context-specific cut-off points for weight gain are essential.
- Machine learning techniques offer practical utility for optimizing malnutrition treatment in humanitarian contexts.
Related Concept Videos
01:29Drug Dosing: Infants and Children
Pediatric patient dosages diverge from adults due to disparities in body surface area, total body water, and extracellular fluid per kilogram of body weight. The dosing regimen considers the variations in pharmacokinetics and pharmacology across distinct age groups, encompassing preterm newborns, infants, young children, older children, and adolescents. Calculation of pediatric patient doses is predicated on determining body surface area, which exhibits a superior correlation with the child's...
01:26Pharmacokinetics in Pediatric Patients: Drug Excretion
In pediatric medicine, understanding the renal function and drug elimination nuances is crucial for administering safe and effective treatments. Newborns, in particular, display markedly slower renal functions than adults, profoundly affecting how drugs are cleared from their bodies. This slower drug clearance requires clinicians to extend the dosing intervals for many medications to prevent drug accumulation and toxicity while ensuring therapeutic efficacy.One key area where these adjustments...