PREDICTION OF STUNTING PREVALENCE IN EAST JAVA PROVINCE  WITH RANDOM FOREST ALGORITHM

M. Syauqi  Haris; Mochammad  Anshori; Ahsanun Naseh Khudori

doi:10.52436/1.jutif.2023.4.1.614

M. Syauqi Haris Informatika, Institut Teknologi, Sains, dan Kesehatan RS dr. Soepraoen Kesdam V/Brw, Indonesia
Mochammad Anshori Informatika, Institut Teknologi, Sains, dan Kesehatan RS dr. Soepraoen Kesdam V/Brw, Indonesia
Ahsanun Naseh Khudori Informatika, Institut Teknologi, Sains, dan Kesehatan RS dr. Soepraoen Kesdam V/Brw, Indonesia

DOI: https://doi.org/10.52436/1.jutif.2023.4.1.614

Keywords: Machine Learning, Prediction, Python, Random Forest, Stunting

Abstract

Stunting or cases of failure to thrive in toddlers is one of the most serious health problems faced by the people of Indonesia. Based on data from the Ministry of Health and the Central Statistics Agency, East Java Province has a stunting prevalence value of 26.8% which is categorized as a high prevalence value according to the standards of the World Health Organization (WHO). Random forest is one of the machine learning algorithms in the field of artificial intelligence that can learn patterns from labeled data so that it can be used as a method for predicting or forecasting data. This approach is considered very suitable to be used in predicting the value of stunting prevalence because stunting prevalence data is usually accompanied by other data in the health sector according to survey results. Previous studies on the prediction of stunting prevalence used secondary data sourced from one survey only. Therefore, this study is one of the efforts to contribute in providing solutions for the stunting problem in East Java Province by combining several data from different surveys in the same year. The results of this study show that from 20 factor candidates for predicting stunting prevalence value, only 12 factors are suspected to be causative factors based on their correlation value. However, the prediction results obtained using the random forest algorithm in this study, with data consisting of 12 features and a dataset consisting of only 38 data, have results with error values of 1.02 in MAE and 1.64 in MSE that are not better than multi-linear regression which can produce smaller error values of 0.93 in MAE and 1.34 in MSE.

Downloads

Download data is not yet available.

References

Subdirektorat Statistik dan Perumahan, “Profil Statistik Kesehatan,” Jakarta, 2019.

M. De Onis et al., “Prevalence thresholds for wasting, overweight and stunting in children under 5 years,” Public Health Nutr., vol. 22, no. 1, pp. 175–179, 2019, doi: 10.1017/S1368980018002434.

K. G. Dewey and K. Begum, “Long-term consequences of stunting in early life,” Matern. Child Nutr., vol. 7, no. SUPPL. 3, pp. 5–18, 2011, doi: 10.1111/j.1740-8709.2011.00349.x.

B. Mzumara, P. Bwembya, H. Halwiindi, R. Mugode, and J. Banda, “Factors associated with stunting among children below five years of age in Zambia: Evidence from the 2014 Zambia demographic and health survey,” BMC Nutr., vol. 4, no. 1, pp. 1–8, 2018, doi: 10.1186/s40795-018-0260-9.

O. N. Chilyabanyama et al., “Performance of Machine Learning Classifiers in Classifying Stunting among Under-Five Children in Zambia,” 2022.

C. R. Titaley, I. Ariawan, D. Hapsari, and A. Muasyaroh, “Determinants of the Stunting of Children in Indonesia : A Multilevel Analysis of the 2013 Indonesia Basic Health Survey,” Nutrients, vol. 11, p. 1160, 2013.

A. Muche, L. D. Gezie, A. G. egzabher Baraki, and E. T. Amsalu, “Predictors of stunting among children age 6–59 months in Ethiopia using Bayesian multi-level analysis,” Sci. Rep., vol. 11, no. 1, pp. 1–12, 2021, doi: 10.1038/s41598-021-82755-7.

F. H. Bitew, C. S. Sparks, and S. H. Nyarko, “Machine learning algorithms for predicting undernutrition among under-five children in Ethiopia,” Public Health Nutr., vol. 25, no. 2, pp. 269–280, 2022, doi: 10.1017/S1368980021004262.

S. M. J. Rahman et al., “Investigate the risk factors of stunting, wasting, and underweight among under-five Bangladeshi children and its prediction based on machine learning approach,” PLoS One, vol. 16, no. 6 June 2021, pp. 1–11, 2021, doi: 10.1371/journal.pone.0253172.

Kementerian Kesehatan Republik Indonesia, “Buletin Jendela Data dan Informasi Kesehatan: Situasi Balita Pendek (Stunting) di Indonesia,” Jakarta, 2018.

S. van der Berg, L. Patel, and G. Bridgman, “Food insecurity in South Africa: Evidence from NIDS-CRAM wave 5,” Dev. South. Afr., vol. 0, no. 0, pp. 1–16, 2022, doi: 10.1080/0376835X.2022.2062299.

The Ministry of Health of The Republic of Indonesia, “Report on the Implementation of the March 2019 Susenas Integration and the 2019 Indonesian Toddler Nutritional Status Survey,” 2019.

E. Retnoningsih and R. Pramudita, “Mengenal Machine Learning Dengan Teknik Supervised Dan Unsupervised Learning Menggunakan Python,” BINA Insa. ICT J., vol. 7, no. 2, p. 156, Dec. 2020, doi: 10.51211/biict.v7i2.1422.

P. D. Kusuma, Machine Learning Teori, Program, Dan Studi Kasus. Yogyakarta: Deepublish, 2020.

S. Lonang and D. Normawati, “Klasifikasi Status Stunting Pada Balita Menggunakan K-Nearest Neighbor Dengan Feature Selection Backward Elimination,” J. Media Inform. Budidarma, vol. 6, no. 1, p. 49, 2022, doi: 10.30865/mib.v6i1.3312.

A. Byna, “Comparative Analysis of Machine Learning Algorithms for classification about Stunting Genesis,” 2020, doi: 10.4108/eai.23-11-2019.2298349.

A. Y. Perdana, R. Latuconsina, and A. Dinimaharawati, “Prediksi Stunting Pada Balita Dengan Algoritma Random Forest,” ISSN 2355-9365 e-Proceeding Eng. Vol.8, No.5 Oktober 2021, vol. 8, no. 5, pp. 6650–6656, 2021.

M. Anshori, F. Mar’i, and F. A. Bachtiar, “Comparison of Machine Learning Methods for Android Malicious Software Classification based on System Call,” Proc. 2019 4th Int. Conf. Sustain. Inf. Eng. Technol. SIET 2019, pp. 343–348, 2019, doi: 10.1109/SIET48054.2019.8985998.

N. Khasanah, R. Komarudin, N. Afni, Y. I. Maulana, and A. Salim, “Skin Cancer Classification Using Random Forest Algorithm,” Sisfotenika, vol. 11, no. 2, p. 137, 2021, doi: 10.30700/jst.v11i2.1122.

L. Wan, K. Gong, G. Zhang, X. Yuan, C. Li, and X. Deng, “An efficient rolling bearing fault diagnosis method based on spark and improved random forest algorithm,” IEEE Access, vol. 9, pp. 37866–37882, 2021, doi: 10.1109/ACCESS.2021.3063929.

S. A. Hemo and M. I. Rayhan, “Classification tree and random forest model to predict under-five malnutrition in Bangladesh,” Biom Biostat Int J, vol. 10, no. 3, pp. 116–123, 2021, doi: 10.15406/bbij.2021.10.00337.