Machine learning vs. traditional logistic regression: predictive performance and risk factor identification for child...

Logistic regression (LR) has long been the standard econometric tool for modeling child nutritional outcomes in public health research. However, conventional econometric LR (CE-LR) faces limitations in predictive accuracy, reliance on restrictive assumptions, and handling high-dimensional data. Machine learning-enhanced LR (ML-LR)-which relaxes the strict statistical assumptions of traditional models to better capture complex patterns-combined with Shapley Additive Explanations (SHAP), offers a promising alternative, improving both prediction and interpretability of risk factors. This study presents the first Pakistan-specific application and comparison of ML-LR (with SHAP analysis) against CE-LR, introducing a novel hybrid framework that combines predictive power with interpretability for policy-relevant insights using nationally representative data from Pakistan's 2017-2018 Demographic and Health Survey (n = 4,098 children under five). Results indicate persistent malnutrition rates: stunting (38.13%), underweight (23.04%), and wasting (8.05%). The ML-LR model identified all 13 hypothesized risk factors as significant, while CE-LR detected only six. Crucially, ML-LR captured key predictors missed by CE-LR, such as maternal BMI, employment, and dietary diversity. The SHAP analysis further revealed nuanced relationships: child age, low maternal BMI, unemployment, and unimproved water increased malnutrition risk, while higher birth order, adequate dietary diversity (if children were given ≥ 5 food items), maternal education, and male gender had protective effects. Crucially, ML-LR + SHAP uncovered context-dependent relationships invisible to CE-LR. For example, dietary diversity operated bidirectionally-low diversity was a risk factor, while adequate diversity was protective-a distinction CE-LR failed to capture. These findings demonstrate ML-LR's superior ability to model complex, heterogeneous determinants of child malnutrition. The study advocates for integrating ML techniques with explainable AI (e.g., SHAP) in econometric analyses to enhance policy-relevant insights in public health.