Critical Evaluation of Machine Learning Models for Glucose Prediction: A Case Study Of Overfitting and Small Data
DOI:
https://doi.org/10.64803/cessmuds.v1.158Keywords:
Decision Support System, SAW, WP, Integrity ZoneAbstract
Glucose level prediction is an important area of research, but the application of machine learning models often faces challenges such as overfitting and limited data. This study aims to evaluate the performance of seven regression models—Linear Regression, Lasso, SVR, Decision Tree, Random Forest, Gradient Boosting, and K-Nearest Neighbors in predicting glucose levels on a small dataset that has undergone preprocessing and dimensionality reduction using Principal Component Analysis (PCA). The evaluation was conducted using the R-squared, Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) metrics. The results showed that most models suffered from severe overfitting, where good performance on the training data was not followed by performance on the test data, as reflected by negative R-squared values. Although Random Forest produced relatively lower errors (MSE = 0.009; RMSE = 0.095), the overall performance remained inadequate due to data limitations. These findings confirm that small sample sizes and overfitting simultaneously hamper the generalizability of models and emphasize the need for more robust approaches in biomedical applications with limited data.
References
Alanazi, A. (2022). Using machine learning for healthcare challenges and opportunities. In Informatics in Medicine Unlocked (Vol. 30). Elsevier Ltd. https://doi.org/10.1016/j.imu.2022.100924
Altman, N. S. (1992). An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression. In Source: The American Statistician (Vol. 46, Number 3).
Amalia Dewayanti, A., & Utami, H. (n.d.). ESTIMASI ROBUST PADA MODEL REGRESI UNTUK MENANGANI OUTLIER DAN HETEROSKEDASTISITAS (ROBUST ESTIMATION IN REGRESSION MODEL FOR HANDLING OUTLIER ANDHETEROSCEDASTICITY). 03(01), 2021.
Ayu, G., & Srinadi, M. (2014). Pengaruh Outlier Terhadap Estimator Parameter Regresi dan Metode Regresi Robust. https://www.researchgate.net/publication/285592493
Bagaskara, K., Perdana, H., Aprizkiyandari, S., & September, D. (2024). PENERAPAN SUPPORT VECTOR REGRESSION KERNEL LINIER DALAM MERAMALKAN HARGA CPO INDONESIA Informasi Artikel ABSTRAK Sejarah Artikel. Equator: Journal of Mathematical and Statistical Sciences (EJMSS), 3(2).
Belyadi, H., & Haghighat, A. (2021). Supervised learning. In Machine Learning Guide for Oil and Gas Using Python (pp. 169–295). Elsevier. https://doi.org/10.1016/B978-0-12-821929-4.00004-4
Breiman, L. (2001a). RANDOM FORESTS. Random Forest, 7(6), 1–33. https://doi.org/10.14569/ijacsa.2016.070603
Breiman, L. (2001b). Random Forests. In Machine Learning (Vol. 45). https://doi.org/https://doi.org/10.1023/A:1010933404324
Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 7, 1–24. https://doi.org/10.7717/PEERJ-CS.623
Cover, T. M., & Hart, P. E. (1952). Nearest Neighbor Pattern Classification. IEEE TRANSACTIONS ON INFORMATION THEORY, 24(1), 335–342.
Emerson, H., McConville, R., & Guy, M. (2023). The Safety Challenges of Deep Learning in Real-World Type 1 Diabetes Management. http://arxiv.org/abs/2310.14743
Friedman, J. H. (2001). I1999 REITZ LECTURE GREEDY FUNCTION APPROXIMATION: A GRADIENT BOOSTING MACHINE. The Annals of Statistics, 29(5), 1189–1232.
Genuer, R., Poggi, J. M., Tuleau-Malot, C., & Villa-Vialaneix, N. (2017). Random Forests for Big Data. Big Data Research, 9, 28–46. https://doi.org/10.1016/j.bdr.2017.07.003
Hameed, H., & Kleinberg, S. (2020). Comparing Machine Learning Techniques for Blood Glucose Forecasting Using Free-living and Patient Generated Data. In Proceedings of Machine Learning Research (Vol. 85). https://github.com/health-
Jollife, I. T., & Cadima, J. (2016). Principal component analysis: A review and recent developments. In Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences (Vol. 374, Number 2065). Royal Society of London. https://doi.org/10.1098/rsta.2015.0202
Kinasih, A. N. S., Handayani, A. N., Ardiansah, J. T., & Damanhuri, N. S. (2024). Comparative analysis of decision tree and random forest classifiers for structured data classification in machine learning. Science in Information Technology Letters, 5(2), 13–24. https://doi.org/10.31763/sitech.v5i2.1746
Laha, S., Rajput, A., Laha, S. S., & Jadhav, R. (2022). A Concise and Systematic Review on Non-Invasive Glucose Monitoring for Potential Diabetes Management. In Biosensors (Vol. 12, Number 11). MDPI. https://doi.org/10.3390/bios12110965
Liu, K., Li, L., Ma, Y., Jiang, J., Liu, Z., Ye, Z., Liu, S., Pu, C., Chen, C., & Yi, W. (2023). Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis. JMIR Medical Informatics, 11(1). https://doi.org/10.2196/47833
Liu, Q., & Liu, M. (2017). Energy-efficient clustering algorithm based on game theory for wireless sensor networks. International Journal of Distributed Sensor Networks, 13(11). https://doi.org/10.1177/1550147717743701
McGill, R., Tukey, J. W., & Larsen, W. A. (1978). Variations of box plots. American Statistician, 32(1), 12–16. https://doi.org/10.1080/00031305.1978.10479236
Quinlan, J. R. (1986). Induction of Decision Trees. In Machine Learning (Vol. 1).
Shi, Y., Yang, K., Yang, Z., & Zhou, Y. (2022). Primer on artificial intelligence. In Mobile Edge Artificial Intelligence (pp. 7–36). Elsevier. https://doi.org/10.1016/b978-0-12-823817-2.00011-5
Soleh, A. M., & Aunuddin. (2013). Lasso: An Alternative Solution for Selection and Shrinkage Linear Regression Models. FSK : Indonesian Journal of Statistics, 18(1), 21–27.
Sung, J. J. Y. (2024). Artificial intelligence and the future of medicine. In Artificial Intelligence in Medicine: From Ethical, Social, and Legal Perspectives (pp. 1–12). Elsevier. https://doi.org/10.1016/B978-0-323-95068-8.00001-7
Trevor Hastie, Robert Tibshirani, J. F. (2009). The Elements of Statistical learning. In Spring Series in Statistic.
van Doorn, W. P. T. M., Foreman, Y. D., Schaper, N. C., Savelberg, H. H. C. M., Koster, A., van der Kallen, C. J. H., Wesselius, A., Schram, M. T., Henry, R. M. A., Dagnelie, P. C., de Galan, B. E., Bekers, O., Stehouwer, C. D. A., Meex, S. J. R., & Brouwers, M. C. G. J. (2021). Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: The Maastricht Study. PLoS ONE, 16(6 June). https://doi.org/10.1371/journal.pone.0253125
Woldaregay, A. Z., Årsand, E., Walderhaug, S., Albers, D., Mamykina, L., Botsis, T., & Hartvigsen, G. (2019). Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes. In Artificial Intelligence in Medicine (Vol. 98, pp. 109–134). Elsevier B.V. https://doi.org/10.1016/j.artmed.2019.07.007
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Arnita Arnita, Hermaan Syahputra, Faridawaty Marpaung, Marlina Setia Sinaga, Agus Junaidi, Fanny Ramadhani (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
