Nutritional Status Classification of Children Using a Decision Tree Method (Case Study at RS AN-NISA) Based on a Web Application

Michael Julius Hutabarat; Dwi Sartika Simatupang; Masmur Tarigan; Y Yulhendri

doi:10.32664/smatika.v16i01.2238

Authors

Michael Julius Hutabarat Universitas Esa Unggul
Dwi Sartika Simatupang Universitas Esa Unggul
Masmur Tarigan Universitas Esa Unggul
Yulhendri Universitas Esa Unggul

DOI:

https://doi.org/10.32664/smatika.v16i01.2238

Keywords:

Classification, Decision Tree, Flask, Machine Learning, Nutritional Status

Abstract

This study develops a web-based classification model for the nutritional status of children aged 0–5 years using the Decision Tree (C4.5) algorithm applied to anthropometric data obtained from RS AN-NISA Tangerang during the period of January–December 2024. The attributes utilized include age (in months), gender, weight, and height, with nutritional status categorized into three classes: undernutrition, normal nutrition, and overnutrition. The dataset underwent a preprocessing phase consisting of data cleaning, removal of extreme values, attribute selection, categorical encoding, normalization, and dataset splitting with an 80% training and 20% testing ratio. The model was constructed using entropy-based splitting criteria with hyperparameter tuning to minimize the risk of overfitting, and its performance was evaluated using accuracy, precision, recall, and F1-score metrics, with Logistic Regression employed as a baseline model for comparison. The results demonstrate that the Decision Tree achieved an accuracy of 96.12% and a macro recall of 89.49%, outperforming the baseline model. The trained model was subsequently serialized and integrated into a Flask-based web application to enable real-time data input and nutritional status prediction. Black-box testing and User Acceptance Testing (UAT) yielded a user satisfaction rate of 88%, indicating that the system is feasible as a practical tool for early detection of child nutritional status in healthcare services.

References

[1] A. Suryawan, “Malnutrition in early life and its neurodevelopmental and cognitive consequences: a scoping review,” Nutr. Res. Rev., vol. 35, no. 1, pp. 136–149, 2022, doi: 10.1017/S0954422421000159.

[2] A. D. Laksono, “Determination of appropriate policy targets to reduce the prevalence of stunting in children under five years of age in urban-poor communities in Indonesia: a secondary data analysis of the 2022 Indonesian national nutritional status survey,” BMJ Open, vol. 14, no. 9, pp. 1–8, 2024, doi: 10.1136/bmjopen-2024-089531.

[3] K. K. R. Indonesia, “Peraturan Menteri Kesehatan Republik Indonesia Nomor 2 Tahun 2020 Tentang Standar Antropometri Anak,” 2020. [Online]. Available: https://peraturan.bpk.go.id/Details/152505/permenkes-no-2-tahun-2020%0A

[4] M. de Onis, “WHO Child Growth Standards,” Dev. Med. Child Neurol., vol. 51, no. 12, pp. 1002–1002, 2009, doi: 10.1111/j.1469-8749.2009.03503.x.

[5] D. H. Ramadhani, J. Jumadi, and G. Sandi, “Implementasi Algoritma K-Nearest Neighbors (KNN) Untuk Prediksi Gizi Buruk,” SMATIKA J., vol. 14, no. 2, pp. 326–336, 2024, doi: 10.32664/smatika.v14i02.1360.

[6] D. T. Larose and C. D. Larose, Discovering Knowledge in Data. Wiley, 2014. doi: 10.1002/9781118874059.

[7] I. I. Sinam and A. Lawan, “An improved C4.5 model classification algorithm based on Taylor’s series,” Jordanian J. Comput. Inf. Technol., vol. 5, no. 1, pp. 34–42, 2019, doi: 10.5455/jjcit.71-1546551963.

[8] M. Mahpuz, A. M. Nur, and L. M. Samsu, “Penerapan Algoritma C4.5 Dalam Mengklasifikasi Status Gizi Balita Pada Posyandu Desa Dames Damai Kabupaten Lombok Timur,” Infotek J. Inform. dan Teknol., vol. 5, no. 1, pp. 72–81, 2022, doi: 10.29408/jit.v5i1.4414.

[9] K. Pinaryanto, R. A. Nugroho, and Y. Basilius, “Classification of Toddler Nutrition Using C4.5 Decision Tree Method,” Int. J. Appl. Sci. Smart Technol., vol. 3, no. 1, pp. 131–142, 2021, doi: 10.24071/ijasst.v3i1.3366.

[10] A. Arista, “Comparison Decision Tree and Logistic Regression Machine Learning Classification Algorithms to determine Covid-19,” Sinkron, vol. 7, no. 1, pp. 59–65, 2022, doi: 10.33395/sinkron.v7i1.11243.

[11] A. Maulana, “Classification of Stunting in Toddlers using Naive Bayes Method and Decision Tree,” Indones. J. Mod. Sci. Technol., vol. 1, no. 1, pp. 28–33, 2025, doi: 10.64021/ijmst.1.1.28-33.2025.

[12] M. Sivakumar and T. Parthasarathy, S. Padmapriya, “Trade-off between training and testing ratio in machine learning for medical image processing,” PeerJ Comput. Sci., vol. 10, pp. 1–17, 2024, doi: 10.7717/peerj-cs.2245.

[13] L. Isyriyah, I. Baihaqi, and F. E. Purwiantono, “Prediksi Loyalitas Pelanggan Pada Fast Moving Consumer Goods Menggunakan Klasifikasi Metode C4.5,” SMATIKA J., vol. 13, no. 2, pp. 369–380, 2024, doi: 10.32664/smatika.v13i02.1115.

[14] A. Nazir, A. Akhyar, Y. Yusra, and E. Budianita, “Toddler Nutritional Status Classification Using C4.5 and Particle Swarm Optimization,” Sci. J. Informatics, vol. 9, no. 1, pp. 32–41, 2022, doi: 10.15294/sji.v9i1.33158.

[15] B. S. Kim, S. H. Lee, Y. R. Lee, Y. H. Park, and J. Jeong, “Design and Implementation of Cloud Docker Application Architecture Based on Machine Learning in Container Management for Smart Manufacturing,” Appl. Sci., vol. 12, no. 13, pp. 1–16, 2022, doi: 10.3390/app12136737.

[16] D. A. Pamungkas, I. L. Kharisma, D. S. Simatupang, and Kamdan, “Implementasi Deep Neural Network pada Perancangan Aplikasi Deteksi Token Scam Blockchain Ethereum,” Sist. J. Sist. Inf., vol. 12, no. 3, pp. 927–937, 2023, [Online]. Available: http://sistemasi.ftik.unisi.ac.id

[17] R. Gustriansyah, N. Suhandi, S. Puspasari, A. Sanmorino, and D. Sartika, “Toddlers’ Nutritional Status Prediction Using the Multinomial Logistics Regression Method,” J. Comput. Networks, Archit. High Perform. Comput., vol. 6, no. 1, pp. 25–33, 2023, doi: 10.47709/cnahpc.v6i1.3372.

[18] I. G. N. Adytya and B. Sudrajat, “Penilaian Prestasi Pekerja Pada Bidang Penanganan Prasarana Dan Sarana Umum Menggunakan Algoritma Decision Tree C4.5,” SMATIKA STIKI Inform. J., vol. 15, no. 1, pp. 24–36, 2025. doi: 10.32664/smatika.v15i01.1414

[19] T. R. Matondang, Y. R. Nasution, Armansyah, and M. Furqan, “Penerapan Algoritma C4.5 Pada Klasifikasi Status Gizi Balita,” J. Fasilkom, vol. 14, no. 1, pp. 216–225, 2024, doi: 10.37859/jf.v14i1.6941.

[20] V. C. Mawardi and N. J. Perdana, “The comparison of accuracy between naïve bayes classifier and C4.5 algorithm in classifying toddler nutrition status based on anthropometry index,” in Journal of Physics: Conference Series, 2019. doi: 10.1088/1742-6596/1764/1/012047.