Applied Machine learning for Pediatric Nutrition A K-Means Clustering Application Based on WHO Z-Scores
DOI:
https://doi.org/10.31937/si.v17i1.4495Abstract
Abstract—Nutritional status in early childhood is a key indicator of public health and serves as a basis for targeted nutritional interventions. This study applies the K-Means Clustering algorithm to anthropometric data—including weight, height, and head circumference—to classify children's nutritional status into five categories: severely undernourished (−3 SD), moderately undernourished (−2 SD), normal, mildly overnourished (+1 SD), and moderately overnourished (+2 SD). The clustering process is based on Z-scores derived from WHO standards, namely Weight-for-Age (WAZ), Height-for-Age (HAZ), and Head Circumference-for-Age (HCAZ), which serve as input features for the clustering algorithm. The number of clusters (k = 5) is aligned with national nutritional classification guidelines. The clustering results are visualized to illustrate the data distribution across the three indicators, and evaluated using Euclidean distance to assess the proximity of each data point to its assigned cluster centroid. The results demonstrate that K-Means Clustering can effectively classify children's nutritional status in a manner consistent with manual classification based on WHO thresholds. This study highlights the potential of data mining approaches in supporting health information systems for the early and automated detection of child malnutrition.
Index Terms—Nutritional Status; Anthropometry; Z-Score; K-Means Clustering
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Julius Sepadan Maruli Tua Manurung, Sri Agustina Rumapea, Edward Rajagukguk, Fernando Rumapea
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike International License (CC-BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Copyright without Restrictions
The journal allows the author(s) to hold the copyright without restrictions and will retain publishing rights without restrictions.
The submitted papers are assumed to contain no proprietary material unprotected by patent or patent application; responsibility for technical content and for protection of proprietary material rests solely with the author(s) and their organizations and is not the responsibility of the ULTIMA InfoSys or its Editorial Staff. The main (first/corresponding) author is responsible for ensuring that the article has been seen and approved by all the other authors. It is the responsibility of the author to obtain all necessary copyright release permissions for the use of any copyrighted materials in the manuscript prior to the submission.
