Comparative Evaluation of Ensemble Learning Models for Prenatal Stunting Risk Assessment Based on Maternal Health Data

Nur Inaya Bahar; Eka Qadri Nuranti; Intan Sari Areni

doi:10.30871/jaic.v10i4.13208

Authors

Nur Inaya Bahar Institut Teknologi Bacharuddin Jusuf Habibie
Eka Qadri Nuranti Institut Teknologi Bacharuddin Jusuf Habibie
Intan Sari Areni Institut Teknologi Bacharuddin Jusuf Habibie

DOI:

https://doi.org/10.30871/jaic.v10i4.13208

Keywords:

Ensemble Learning, Prenatal Stunting, Light Gradient Boosting Machine, Maternal Data

Abstract

Stunting remains a significant public health challenge, where interventions are often delayed as they occur postnatally. This research aims to shift the detection focus to the prenatal phase by comparing the performance of four Ensemble Learning algorithms: Random Forest, XGBoost, CatBoost, and Light Gradient Boosting Machine (LGBM). Using a maternal dataset from DPPKB Parepare City consisting of 871 respondents, the models were developed through a Stratified 5-Fold Group Cross Validation scheme to predict stunting risk based on clinical features of pregnant women. Experimental results show that LGBM is the most optimal algorithm, where the hyperparameter tuning process increased model performance to an F1-Score of 94.34% and an accuracy of 94.50%. Ablation analysis identified maternal age, height, and the age of the last child as the most dominant predictors. The best model was integrated into a web-based decision support system using cloud-based microservices architecture, featuring geospatial mapping. This study proves that the application of LGBM on prenatal maternal data can provide accurate early detection to support targeted nutritional interventions for Family Assistance Teams (TPK) in Parepare City, although its generalizability remains limited to local administrative characteristics and warrants further prospective external validation before broader deployment.

Downloads

Download data is not yet available.

References

[1] World Health Organization, “Malnutrisi,” World Health Organization. Accessed: May 15, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/malnutrition

[2] A. Heryati, D. Marcelina, and H. Romli, “Optimization of Stunting Risk Prediction Using a Hybrid Genetic-Machine Learning Model,” J. Artif. Intell. Softw. Eng., vol. 5, no. 2, pp. 807–815, 2025, doi: 10.30811/jaise.v5i2.6988.

[3] K. S. R. I. Negara, “Buka Rakornas Stunting, Wapres Ungkap Keberhasilan Pemerintah Turunkan Prevalensi Lima Tahun Terakhir,” Kementerian Sekretariat Negara Republik Indonesia. Accessed: May 16, 2026. [Online]. Available: https://www.setneg.go.id/Baca/Index/Buka_Rakornas_Stunting_Wapres_Ungkap_Keberhasilan_Pemerintah_Turunkan_Prevalensi_Lima_Tahun_Terakhir

[4] K. R. Syukrina, Erika, and O. Hasanah, “Faktor-faktor yang Menyebabkan Stunting pada Balita: Sebuah Studi Literatur,” J. Med. Hutama, vol. 5, no. 02 Januari, pp. 3854–3867, 2024.

[5] A. N. Sartika, M. Khoirunnisa, E. Meiyetriani, E. Ermayani, I. L. Pramesthi, and A. J. Nur Ananda, “Prenatal and postnatal determinants of stunting at age 0–11 months: A cross-sectional study in Indonesia,” PLoS One, vol. 16, no. 7 July, pp. 1–14, 2021, doi: 10.1371/journal.pone.0254662.

[6] P. L. Rosida, M. Nurmalasari, and D. Krismawati, “Implementasi Decision Tree untuk Prediksi Kelahiran Bayi Prematur Decision Tree Implementation for Premature Birth Prediction,” vol. 14, pp. 178–186, 2024.

[7] U. R. Gurning, S. F. Octavia, and D. R. Andriyani, “Prediction of Stunting Risk In Families Using Naïve Bayes Classifier and Chi-Square Prediksi Risiko Stunting pada Keluarga Menggunakan Naïve Bayes Classifier dan Chi-Square,” vol. 4, no. January, pp. 172–180, 2024.

[8] D. M. Puspita, K. I. Santoso, A. Triyono, E. Supriyadi, and S. Agus, “Algoritma Random Forest , Decision Tree dan XGboost Untuk Klasifikasi Stunting Pada Balita,” vol. 23, no. 1, pp. 67–76, 2025.

[9] R. Ratnasari, A. J. Wahidin, and T. H. Andika, “Deteksi Dini Stunting Pada Anak Berdasarkan Indikator Antropometri dengan Menggunakan Algoritma Machine Learning,” J. Algoritm., vol. 21, no. 2, pp. 378–387, 2024, doi: 10.33364/algoritma/v.21-2.2122.

[10] G. S. Azahra and M. D. Kartikasari, “Child Stunting Classification using the LightGBM Method : A Case Study in the Rowosari District of Kendal , Central Java,” vol. 8, no. 1, pp. 102–113, 2025.

[11] L. Fitriani, S. Wahyuni, and . N., “Penyuluhan Upaya Pencegahan Stunting Sejak Masa Kehamilan,” J. Abdimas ITEKES Bali, vol. 2, no. 2, pp. 84–88, 2023, doi: 10.37294/jai.v2i2.454.

[12] O. Pahlevi, D. Ayu, L. K. Rahayu, H. Leidiyana, and Y. Handrianto, “Model Klasifikasi Risiko Stunting Pada Balita Menggunakan Algoritma CatBoost Classifier,” Bull. Comput. Sci. Res., vol. 6, no. 4, pp. 414–421, 2024, doi: 10.47065/bulletincsr.v4i6.373.

[13] W. Richard, P. Thangata, B. Mkandawire, and N. Amoah, “Human Nutrition & Metabolism Advancing predictive analytics in child malnutrition : Machine , ensemble and deep learning models with balanced class distribution for early detection of stunting and wasting,” Hum. Nutr. Metab., vol. 42, no. August, p. 200340, 2025, doi: 10.1016/j.hnm.2025.200340.

[14] O. Pahlevi, D. Ayu, N. Wulandari, L. K. Rahayu, H. Leidiyana, and Y. Handrianto, “BULLETIN OF COMPUTER SCIENCE RESEARCH Model Klasifikasi Risiko Stunting Pada Balita Menggunakan Algoritma CatBoost Classifier,” vol. 6, no. 4, pp. 414–421, 2024, doi: 10.47065/bulletincsr.v4i6.373.

[15] M. S. Haris, A. N. Khudori, and W. T. Kusuma, “Perbandingan Metode Supervised Machine Learning untuk Prediksi Prevalensi Stunting di Provisi Jawa Timur,” J. Teknol. Inf. dan Ilmu Komput., vol. 9, no. 7, p. 1571, 2022, doi: 10.25126/jtiik.2022976744.

[16] R. Romlah, S. Faisal, R. Rahmat, and J. Indra, “Prediksi Risiko Angka Stunting Pada Balita Menggunakan Algoritma Support Vector Machine,” J. Inform. Teknol. dan Sains, vol. 7, no. 2, pp. 837–842, 2025, doi: 10.51401/jinteks.v7i2.5749.

[17] M. A. Rayadin, M. Musaruddin, and R. A. Saputra, “Implementasi Ensemble Learning Metode XGBoost dan Random Forest untuk Prediksi Waktu Penggantian Baterai Aki,” vol. 5, no. 2, pp. 111–119, 2024.

[18] V. I. Ivanoti, M. H. P, G. Triyono, D. P. Utami, U. B. Luhur, and I. Technology, “Decision Support System For Predicting Employee Leave Using The Light Gradient Boosting Machine ( Lightgbm ) And K-Means,” vol. 4, no. 3, pp. 657–667, 2023.

[19] T. Hidayat, I. Sembiring, H. D. Purnomo, and A. Iriani, “Prediksi Prevalensi Stunting Balita dengan Pendekatan Algoritma Support Vector Machine dan Synthetic Minority Oversampling Technique (SMOTE),” J. Pekommas, vol. 10, no. 1, pp. 9–16, 2025, doi: 10.56873/jpkm.v9i1.5389.

[20] R. Meyes, M. Lu, C. W. de Puiseau, and T. Meisen, “Ablation Studies in Artificial Neural Networks,” pp. 1–19, 2019.

[21] E. Sugianti, A. Buanasita, H. Hidayanti, and B. D. Putri, “Analisis faktor ibu terhadap kejadian stunting pada balita usia 24-59 bulan di perkotaan Maternal factor analysis on stunting incidence among children aged 24-59 months in urban areas Abstrak Pendahuluan Metode,” vol. 8, no. 1, pp. 30–42, 2023.

[22] L. M. Cendani and A. Wibowo, “Perbandingan Metode Ensemble Learning pada Klasifikasi Penyakit Diabetes,” vol. 13, no. 1, pp. 33–44, 2022.