Classification of Blood Glucose Signals for the Detection of Type 2 Diabetes Mellitus using a Geometric Feature Space and Machine Learning Algorithms
DOI:
https://doi.org/10.70567/mc.v42.ocsid8243Keywords:
amplitud, ángulo de zenit, factor de forma, diferenciación de señalesAbstract
This study proposes a new approach for the early detection of type 2 diabetes mellitus through the automated analysis of physiological signals. The method developed is based on the construction of a geometric feature space generated from parameters extracted from patient signals, and the subsequent application of machine learning algorithms on this space. Experimental results demonstrate high diagnostic efficiency, with F1-score values reaching 1.000 in the best configurations, supported by complementary metrics of sensitivity (ranging [0.960–1.000]), specificity (equal to or higher than 0.984) and balanced accuracy (equal to or higher than 0.983). These results confirm that the proposed technique offers a robust and reliable system for the identification of patterns associated with type 2 diabetes mellitus.
References
Abhari S., Hassanzadeh H., y Jalili S. Artificial intelligence applications in type 2 diabetes mellitus care: Focus on machine learning methods. Frontiers in Artificial Intelligence, 6:1123450, 2023. https://doi.org/10.3389/frai.2023.1123450.
American Diabetes Association. Standards of medical care in diabetes. 2023. Consultado en julio 2023.
Carrell A.M., Mallinar N., Lucas J., y Nakkiran P. The calibration generalization gap. arXiv preprint arXiv:2210.01964, 2022.
García Blesa M., Vorobioff J., y Legnani W. An innovative method to distinguish chaos from noise in the time domain. International Journal of Applied and Computational Mathematics, 11:161, 2025. https://doi.org/10.1007/s40819-025-01991-x. Published 04 August 2025.
Genuth S.M., Palmer J.P., y Nathan D.M. Classification and diagnosis of diabetes. 2018.
Géron A. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. O’Reilly Media, Inc.", 2022.
Herman W.H., Ye W., Griffin S.J., Simmons R.K., Davies M.J., Khunti K., Rutten G.E., Sandbaek A., Lauritzen T., Borch-Johnsen K., et al. Early detection and treatment of type 2 diabetes reduce cardiovascular morbidity and mortality: a simulation of the results of the anglo-danish-dutch study of intensive treatment in people with screen-detected diabetes in primary care (addition-europe). Diabetes care, 38(8):1449–1455, 2015.
James G., Witten D., Hastie T., y Tibshirani R. An Introduction to Statistical Learning with Applications in R. Springer Texts in Statistics. Springer, New York, 2nd edición, 2021.
Kodama S., Fujihara K., Horikawa C., Ishiguro H., Yachi Y., Saito K., Shimano H., y Sone H. Predictive ability of current machine learning algorithms for type 2 diabetes mellitus: A meta-analysis. Diabetologia, 65(3):526–538, 2022. https://doi.org/10.1007/s00125-021-05614-1.
Murphy K.P. Machine Learning: A Probabilistic Perspective. MIT Press, 2012.
Rodriguez de Castro C., Vigil L., Vargas B., Garcia Delgado E., Garcia Carretero R., Ruiz-Galiana J., y Varela M. Glucose time series complexity as a predictor of type 2 diabetes. Diabetes/metabolism research and reviews, 33(2):e2831, 2017.
Zihlmann M., Perekrestenko D., y Tschannen M. Convolutional recurrent neural networks for electrocardiogram classification. En 2017 Computing in Cardiology (CinC), páginas 1–4. 2017. https://doi.org/10.22489/CinC.2017.070-060.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Argentine Association for Computational Mechanics
This work is licensed under a Creative Commons Attribution 4.0 International License.
This publication is open access diamond, with no cost to authors or readers.
Only those papers that have been accepted for publication and have been presented at the AMCA congress will be published.
