Expert system for early detection of stunting nutritional status in toddlers using the forward chaining method (studi kasus: penajam paser utara regency)
Keywords:
Early Detection, Expert System, Forward Chaining, Penajam Paser Utara, StuntinAbstract
Stunting is a chronic nutritional problem in toddlers that can negatively affect physical growth, cognitive development, and overall quality of life in the long term. In 2023, the prevalence of stunting in Penajam Paser Utara Regency reached 9.67%, with 648 stunted toddlers out of 6,702 recorded toddlers. Among the districts, Sepaku District contributed the highest percentage of cases at 17.19%. These conditions indicate the need for a fast and accurate decision support system to assist early detection and prevention efforts. This study aims to design an expert system for early stunting detection using the Forward Chaining algorithm. The method applies a rule-based reasoning approach by tracing facts provided by users, including gender, age, and height, and matching them with a knowledge base derived from official child growth and nutritional standards. The system processes these facts through IF-THEN rules to generate conclusions regarding the nutritional status of toddlers, categorized as either Stunting or Normal. System testing was conducted through simulations using sample toddler data to evaluate the accuracy of the rule-matching process. The results indicate that the Forward Chaining method is capable of classifying nutritional status accurately and consistently based on fact tracing and predefined rules. The developed expert system can support health workers and Posyandu cadres in conducting early screening and decision-making in stunting-prone areas. Furthermore, this research is expected to contribute to the development of intelligent health-support applications for community-based child nutrition monitoring and intervention programs.
References
[1] Dinas Kesehatan Kabupaten Penajam Paser Utara, "Jumlah Data Balita Pendek (Stunting) Menurut Kecamatan di Kabupaten Penajam Paser Utara Tahun 2023," Portal Satu Data Indonesia, Dataset CSV, 2023.
[2] Kurnianto, N. U., & Kurnianto, L. A., "Analysis of Diabetes Disease Using K-Nearest Neighbor (KNN) and Naïve Bayes Methods," Jurnal Ilmu Komputer dan Cerdas, vol. 5, no. 1, pp. 12-25, 2026.
[3] Noor, F. K. R., "Asuhan Keperawatan Pasien yang Mengalami Masalah Gizi Kronis dan Ketidakstabilan Metabolisme," Jurnal Kesehatan Madani, vol. 11, no. 2, pp. 45-56, 2024.
[4] Zaenuddin, I., & Riyan, A. B., "Peran Kecerdasan Buatan dan Dampaknya Pada Transformasi Dunia Teknologi Kesehatan," Jurnal Sains Grafika, vol. 3, no. 1, pp. 28-35, 2024.
[5] Ningrum, D. K., & Ismawardi, A. M., "Efektivitas Algoritma Kecerdasan Buatan dalam Implementasi Screening Kesehatan Digital: Systematic Literature Review," Jurnal Sistem Informasi Medis, vol. 4, no. 2, pp. 88-99, 2025.
[6] Akbar, F. M. N., "Penerapan Metode KNN (K-Nearest Neighbor) untuk Klasifikasi Kualitas Kesehatan Lingkungan," Jurnal Teknologi Lingkungan, vol. 18, no. 1, pp. 102-111, 2023.
[7] Munir, A., et al., "Perbandingan Akurasi Algoritma Naïve Bayes dan Algoritma Decision Tree dalam Pengklasifikasian Penyakit Kronis," Jurnal Informatika Klinis, vol. 7, no. 3, pp. 142-151, 2024.
[8] Prasetya, W. D., & Sujatmiko, B., "Rancang Bangun Aplikasi dengan Perbandingan Metode K-Nearest Neighbor (KNN) dan Naïve Bayes dalam Klasifikasi Resiko Medis," Jurnal Pengembangan Teknologi Informasi, vol. 12, no. 4, pp. 210-219, 2022.
[9] Firmandala, L. O. S., & Fatah, Z., "Implementasi Data Mining Klasifikasi Status Kesehatan Masyarakat di Perguruan Tinggi Menggunakan K-Nearest Neighbors," Jurnal Core Unuja, vol. 5, no. 2, pp. 75-84, 2024.
[10] Anisa, D. N., "Klasifikasi Derajat Gizi Buruk Menggunakan Algoritma Naïve Bayes Berdasarkan Parameter Antropometri," Dinamika Informatika, vol. 14, no. 1, pp. 30-39, 2022.
[11] Delvika, R., et al., "Comparison of Classification Between Naïve Bayes and K-Nearest Neighbor on Health Risk: Indonesian Journal of Machine Learning and Computer Science (MALCOM)," vol. 2, pp. 68-75, 2022.
[12] Kurniawan, M. F., & Megawaty, D. A., "Comparison of Logistic Regression, Random Forest, Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) Algorithms in Early Disease Prediction," Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 1, pp. 50-59, 2025.
[13] Irsyad, H. H., Syafwan, M. I., & Ramadhani, D., "Analisis Perbandingan Kinerja Algoritma K-Nearest Neighbors dan Support Vector Machine untuk Klasifikasi Gizi Klinis," Journal of System & Technology (Systec), vol. 1, no. 2, pp. 115-124, 2025.
[14] Fachrezi, M. R., Aryanda, H., Syahputra, A., & Riansyah, R., "Sistem Klasifikasi Status Gizi Balita Menggunakan Algoritma Cerdas Berbasis Web," Jurnal Ilmu Komputer dan Teknik Informatika (JUIKTI), vol. 2, no. 1, pp. 119-130, 2026.
[15] Susanto, E. B., Anzila, N. N., & Ismanto, B., "Comparison Of The Effectiveness Of K-Nearest Neighbor (KNN) And Naïve Bayes Algorithms In Identifying High-Risk Patients," Journal of Artificial Intelligence and Software Engineering (J-AISE), vol. 5, no. 1, pp. 22-31, 2025.
[16] Hunafa, M. R., & Hermawan, A., "Perbandingan Algoritma Naïve Bayes dan K-Nearest Neighbor Pada Imbalance Class Dataset Penyakit," KLIK: Kajian Ilmiah Informatika dan Komputer, vol. 4, no. 3, pp. 1551-1561, 2023.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Machine Intelligence for Societal Advancement
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
