Lulu Amnah Fitriya Maharani, Purwadi Purwadi, Debby Ummul Hidayah

Clustering And Classification Of Toddler Stunting Risk Using K-Means And Naive Bayes: A Case Study At Kembaran 1 Community Health Center

Introduction

Clustering and classification of toddler stunting risk using k-means and naive bayes: a case study at kembaran 1 community health center. Predict toddler stunting risk using K-Means & Naive Bayes at Kembaran 1 Public Health Center. Achieves 93.56% accuracy for early detection & targeted interventions.

Abstract

Stunting continues to be a significant public health concern in Indonesia, with a frequency of 17.25% at Kembaran 1 Public Health Center, highlighting ongoing difficulties in early childhood nutrition and growth surveillance. This work seeks to assess and forecast stunting risk in toddlers by employing K-Means clustering and Naive Bayes classification to enhance early detection precision. The K-Means method was utilized on 1,168 toddler growth records to categorize stunting features, whereas the Davies–Bouldin Index (DBI) was employed to evaluate cluster quality. The ideal cluster was attained at k = 8, yielding a DBI value of 4.353, indicating compact and distinctly differentiated clusters. The Naive Bayes classifier subsequently predicted stunting potential with an accuracy of 93.56%, accurately categorizing 218 out of 233 test examples, yielding precision, recall, and F1-score values for the “short” class of 97.41%, 94.95%, and 96.18%, respectively. The findings indicate that the hybrid model successfully combines unsupervised and supervised learning, improving stunting prediction accuracy and cluster interpretability. The research provides a data-centric framework for localized stunting surveillance, aiding community health centers in formulating targeted early treatments and mitigating long-term developmental hazards.

Review

This paper addresses the critical public health challenge of stunting in toddlers, a significant concern particularly evident at the Kembaran 1 Public Health Center in Indonesia, where its frequency is noted at 17.25%. The authors propose a data-driven approach leveraging K-Means clustering and Naive Bayes classification to enhance the precision of early detection and risk forecasting for stunting. This hybrid model aims to provide community health centers with a robust tool for more effective surveillance and intervention strategies, thereby mitigating long-term developmental risks. The methodology is clearly outlined, beginning with K-Means clustering applied to 1,168 toddler growth records to identify inherent stunting features. The use of the Davies–Bouldin Index (DBI) for cluster quality evaluation is appropriate, with an optimal k-value of 8 yielding a DBI of 4.353, indicative of well-separated and compact clusters. This unsupervised step provides valuable data segmentation before the application of the Naive Bayes classifier. The classification model subsequently demonstrates strong predictive capabilities, achieving an impressive accuracy of 93.56%, correctly categorizing 218 out of 233 test examples. Furthermore, the model exhibits high performance for the "short" class, with precision, recall, and F1-score values of 97.41%, 94.95%, and 96.18% respectively, underscoring its reliability in identifying at-risk individuals. The findings presented in this abstract suggest a significant contribution to the field of public health informatics. The successful integration of unsupervised and supervised learning not only improves prediction accuracy but also enhances the interpretability of stunting features, offering a clearer understanding of underlying risk factors. This research establishes a pragmatic, data-centric framework for localized stunting surveillance, which holds substantial promise for empowering community health centers. By providing a precise tool for early risk assessment, the study effectively supports the formulation of targeted interventions, ultimately contributing to better nutritional outcomes and overall child development.

Full Text

Comments

You need to be logged in to post a comment.