Comparative analysis of CatBoost and LightGBM algorithms for predicting dental caries risk based on lifestyle factors
DOI:
https://doi.org/10.21107/kursor.v13i3.504Keywords:
CatBoost, Dental and oral health, Dental caries, LightGBM, machine learningAbstract
Dental caries is a common oral infection but significantly impacts life. This study aims
to compare the performance of the CatBoost and LightGBM algorithms in predicting
dental caries risk based on health and lifestyle data from over 55,000 South Korean
NHIS participants. Imbalanced data was addressed using the SMOTE technique, while
hyperparameter tuning was performed using Optuna to maximize the F1-score. The
models were evaluated using the confusion matrix, accuracy, logloss, ROC Curve,
AUC, Precision, Recall, and F1-Score metrics. The results showed that CatBoost was
slightly superior with an accuracy of 90.4%, an F1-score of 89.7%, and an AUC of 0.95,
compared to LightGBM with an accuracy of 90.1%, an F1-score of 89.2%, and an AUC
of 0.94. In addition, CatBoost also produced fewer false negatives, making it more
sensitive in detecting caries cases. Therefore, CatBoost is recommended as the primary
model in a caries risk prediction system to support early detection and disease
prevention more effectively.
Downloads
References
[1] R. Amalia, Karies gigi: Perspektif terkini aspek biologis, klinis, dan komunitas. Ugm Press, 2021.
[2] A. Warreth, "Dental caries and its management," International journal of dentistry, vol. 2023, no. 1, p. 9365845, 2023. https://doi.org/10.1155/2023/9365845.
[3] I.-A. Kang, S. Ngnamsie Njimbouom, K.-O. Lee, and J.-D. Kim, "DCP: prediction of dental caries using machine learning in personalized medicine," Applied Sciences, vol. 12, no. 6, p. 3043, 2022. https://doi.org/10.3390/app12063043 .
[4] R. S. S. Suhadi and A. Mauludin, "Scoping Review: Rokok Sebagai Faktor Risiko terhadap Kejadian Karies Gigi," in Bandung Conference Series: Medical Science, 2023, vol. 3, no. 1, pp. 77-83. https://doi.org/10.29313/bcsms.v3i1.5626. [5] V. I. Sunarko, E. Y. Puspaningrum, R. R. Widiastuty, S. Hadi, M. K. Awang, and I. G. S. M. Diyasa, "Convolutional layer exertion on few-shot learning for brain tumor classification," Jurnal Ilmiah Kursor, vol. 13, no. 2, pp. 98-110, 2025. https://doi.org/10.21107/kursor.v13i2.430 .
[6] Y. Wu, M. Jia, Y. Fang, D. Duangthip, C. H. Chu, and S. S. Gao, "Use machine learning to predict treatment outcome of early childhood caries," BMC Oral Health, vol. 25, no. 1, p. 389, 2025. https://doi.org/10.1186/s12903-025-05768-y.
[7] W. Fernando, D. Jollyta, D. Priyanto, and D. Oktarina, "The Influence Of Data Categorization And Attribute Instances Reduction Using The Gini Index On The Accuracy Of The Classification Algorithm ModeL," Jurnal Ilmiah Kursor, vol. 12, no. 3, pp. 111-122, 2024. https://doi.org/10.21107/kursor.v12i3.372.
[8] A. Kalalo, R. Rosmini, and A. Anto, "Klasifikasi Penyakit Karies Gigi Menggunakan Algoritma Modified K-Nearest Neighbor," Journal of Big Data Analytic and Artificial Intelligence, vol. 7, no. 2, pp. 48-54, 2024. https://doi.org/10.71302/jbidai.v7i2.60.
[9] Y. Tanuwijaya and T. H. Rochadiani, "Komparatif Studi Model Deep Learning Untuk Deteksi Karies Gigi," The Indonesian Journal of Computer Science, vol. 14, no. 2, 2025. https://doi.org/10.33022/ijcs.v14i2.4857.
[10] M. Imani and H. R. Arabnia, "Hyperparameter optimization and combined data sampling techniques in machine learning for customer churn prediction: a comparative analysis," Technologies, vol. 11, no. 6, p. 167, 2023. https://doi.org/10.3390/technologies11060167.
[11] F. N. R. Putri, R. R. Isnanto, and A. Sugiharto, "Skin Rash Classification System using Modified Densenet201 Through Random Search for Hyperparameter Tuning," Jurnal Ilmiah Kursor, vol. 12, no. 4, pp. 179-190, 2024. https://doi.org/10.21107/kursor.v12i4.418.
[12] K. Ileri, "Comparative analysis of CatBoost, LightGBM, XGBoost, RF, and DT methods optimised with PSO to estimate the number of k-barriers for intrusion detection in wireless sensor networks," International Journal of Machine Learning and Cybernetics, vol. 16, no. 9, pp. 6937-6956, 2025. https://doi.org/10.1007/s13042-025-02654-5.
[13] A. Odeh, Q. A. Al-Haija, A. Aref, and A. A. Taleb, "Comparative study of CatBoost, XGBoost, and LightGBM for enhanced URL phishing detection: a performance assessment," Journal of Internet Services and Information Security, vol. 13, no. 4, pp. 1-11, 2023. https://doi.org/10.58346/JISIS.2023.I4.001.
[14] M. Gonca, B. B. Gul, and M. F. Sert, "How successful is the CatBoost classifier in diagnosing different dental anomalies in patients via sella turcica and vertebral morphologic alteration?," BMC Medical Informatics and Decision Making, vol. 24, no. 1, p. 237, 2024. https://doi.org/10.1186/s12911-024-02643-8.
[15] J. Hancock and T. Khoshgoftaar, "CatBoost for big data: an interdisciplinary review. J Big Data 7 (1): 94," ed, 2020. https://doi.org/10.1186/s40537-020-00369-8.
[16] Y. Cai, Y. Yuan, and A. Zhou, "Predictive slope stability early warning model based on CatBoost," Scientific reports, vol. 14, no. 1, p. 25727,2024. https://doi.org/10.1038/s41598-024-77058-6.
[17] R. G. Farahani, A. Zarrabi, and P. Ghazanfari, "A Report on CatBoost: unbiased boosting with categorical features," Accessed: Aug, vol. 11, 2025.
[18] Y. Wang and T. Wang, "Application of improved LightGBM model in blood glucose prediction," Applied Sciences, vol. 10, no. 9, p. 3227, 2020. https://doi.org/10.3390/app10093227.
[19] Y. Wu, M. Luo, S. Ding, and Q. Han, "Using a light gradient-boosting machine–shapley additive explanations model to evaluate the correlation between urban blue–green space landscape Spatial patterns and carbon sequestration," Land, vol. 13, no. 11, p. 1965, 2024. https://doi.org/10.3390/land13111965.
[20] S. S. Sabila and H. P. A. Tjahyaningtyas, "The multiple brain tumor with modified DenseNet121 architecture using brain MRI images: Classification multiclass brain tumor using brain MRI images with modified DenseNet121," Jurnal Ilmiah Kursor, vol. 12, no. 3, pp. 147-158, 2024. https://doi.org/10.21107/kursor.v12i3.379.
[21] G. Ke et al., "Lightgbm: A highly efficient gradient boosting decision tree," Advances in neural information processing systems, vol. 30, 2017.
[22] W. Swastika, K. R. Prilianti, P. L. T. Irawan, and H. Setiawan, "Comparative analysis of random forest and deep learning approaches for automated acute lymphoblastic leukemia detection using morphologicaland textural features," Jurnal Ilmiah Kursor, vol. 13, no. 1, pp. 24-31, 2025. https://doi.org/10.21107/kursor.v13i1.427.
[23] Y.-H. Park, S.-H. Kim, and Y.-Y. Choi, "Prediction models of early childhood caries based on machine learning algorithms," International Journal of Environmental Research and Public Health, vol. 18, no. 16, p. 8613, 2021. https://doi.org/10.3390/ijerph18168613.
[24] A. Y. Yıldız and A. Kalayci, "Gradient boosting decision trees on medical diagnosis over tabular data," in 2025 IEEE International Conference on AI and Data Analytics (ICAD), 2025: IEEE, pp. 1-8. https://doi.org/10.1109/ICAD65464.2025.11114069.
[25] J. T. Hancock and T. M. Khoshgoftaar, "Gradient boosted decision tree algorithms for medicare fraud detection," SN Computer Science, vol. 2, no. 4, p. 268, 2021. https://doi.org/10.1007/s42979-021-00655-z.
[26] J. T. Hancock and T. M. Khoshgoftaar, "CatBoost for big data: an interdisciplinary review: JT Hancock, TM Khoshgoftaar," Journal of big data, vol. 7, no. 1, p. 94, 2020. https://doi.org/10.1186/s40537-020-00369-8.
[27] 공공데이터포털, Accessed: Jun. 10, 2025. [Online]. Available: https://www.data.go.kr/index.do.
Downloads
Published
Issue
Section
Citation Check
License
Copyright (c) 2026 Chayadi Oktomy Noto Susanto, Muhajirah Ulfah, Bimo Aditya Pangestu, Slamet Riyadi
This work is licensed under a Creative Commons Attribution 4.0 International License.
+62-858-5000-1918
