<![CDATA[Child nutrition vulnerability is a multidimensional issue influenced by health outcomes, socioeconomic conditions, environmental factors, maternal education, dietary patterns, and access to health services. This study developed the Child Nutrition Vulnerability Index (IKGA) to map district level vulnerability in 33 districts or cities of North Sumatra during 2021-2023 and to examine the stability of the resulting priority ranking. Birth, severe malnutrition, and low birth weight data were obtained from the North Sumatra Provincial Health Office; sanitation was derived from Riskesdas; and supporting socioeconomic and service access variables were compiled from district level research and statistical datasets. The method included indicator transformation, annual min-max normalization, weighted composite aggregation, tertile-based relative risk classification, spatial visualization, one-at-a-time and Monte Carlo sensitivity analyses, and exploratory machine learning benchmarking using Random Forest, Decision Tree, and K-Means. The 2023 average IKGA was 0.3486, with the highest score in Nias (0.5573) and the lowest in Kota Binjai (0.1934). Monte Carlo sensitivity analysis produced an average Spearman rank correlation of 0.9957, indicating stable rankings under moderate weight variation. Random Forest reproduced the IKGA categories better than Decision Tree and K-Means, with 0.727 accuracy and 0.724 macro-F1. The IKGA provides an interpretable district level prioritization tool for SI-GIZI SIGAP, but the categories should be interpreted as relative provincial priorities rather than absolute nutritional risk thresholds.]]>
Copyrights © 2026
