ISBN
Formato digital
979-13-87837-54-9
Fecha de publicación
06-10-2025
Licencia
D. R. © Copyright 2025. Alma Y. Alanis, Jorge Galvez, Omar Avalos, Eduardo Méndez-Palos, Jorge D. Rios, Adriana Peña Perez-Negron & Gabriel Martínez Soltero
Todos los contenidos de esta obra se comparten bajo la licencia Creative Commons Atri-bución/Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0). Esto implica que no está autorizado el uso comercial de la obra original ni de las eventuales obras derivadas, las cuales deberán distribuirse bajo la misma licencia que rige la obra original. No obstante, se permite a terceros compartir el contenido siempre y cuando se reconozca debidamente la autoría y la publicación original en esta editorial.
Francisco González Barriga
Universidad de Guadalajara
0009-0005-0340-4419
Dulce María Ibarra Montes
Universidad de Guadalajara
0009-0002-2939-3066
Alma Yolanda Alanis García
Universidad de Guadalajara
0000-0001-9600-779X
Gabriel Martínez Soltero
Universidad de Guadalajara
0000-0003-3538-8132
Acerca de
In this paper, we propose a method for detecting failures in Continuous Glucose Monitors (CGMs) using Transformer-based neural networks. CGMs are critical for diabetes management, providing continuous glucose level readings. However, failures such as spikes, and loss of sensitivity can compromise the accuracy of these devices, posing risks to users’ health. The Transformer architecture, known for its ability to process sequential data efficiently, to classify CGM signal segments and identify faults. The proposed approach is compared against classical methods such as Long Short-Term Memory, Multi-Layer Perceptron, and Support Vector Machines. The Transformer model achieved the highest F1-score, outperforming the other approaches. Our results demonstrate the potential of Transformers in improving fault detection in CGMs, ensuring more reliable diabetes management.
Referencias
Clarke, W., Kovatchev, B.: Statistical tools to analyze continuous glucose monitor data. Diabetes technology & therapeutics 11(S1), S–45 (2009)
Cortes, C., Vladimir, V.: Support-vector networks. Machine Learning (1995)
Egan, A.M., Dinneen, S.F.: What is diabetes? Medicine 47(1), 1–4 (2019)
He, K., Gan, C., Li, Z., Rekik, I., Yin, Z., Ji, W., Gao, Y., Wang, Q., Zhang, J.,
Shen, D.: Transformers in medical image analysis. Intelligent Medicine 3(1), 59–78 (2023)
Hochreiter, S.: Long short-term memory. Neural Computation MIT-Press (1997)
Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: A survey. ACM computing surveys (CSUR) 54(10s), 1–41 (2022)
Lin, T., Wang, Y., Liu, X., Qiu, X.: A survey of transformers. AI open 3, 111–132 (2022)
Liu, Y., Zhang, Y., Wang, Y., Hou, F., Yuan, J., Tian, J., Zhang, Y., Shi, Z., Fan, J., He, Z.: A survey of visual transformers. IEEE Transactions on Neural Networks and Learning Systems (2023)
Lu, Y., Liu, D., Liang, Z., Liu, R., Chen, P., Liu, Y., Li, J., Feng, Z., Li, L.M.,
Sheng, B., et al.: A pretrained transformer model for decoding individual glucose dynamics from continuous glucose monitoring data. National Science Review p. nwaf039 (2025)
Mahmoudi, Z., Boiroux, D., Hagdrup, M., Nørgaard, K., Poulsen, N.K., Madsen, H., Jørgensen, J.B.: Application of the continuous-discrete extended kalman filter for fault detection in continuous glucose monitors for type 1 diabetes. In: 2016 European Control Conference (ECC). pp. 714–719. IEEE (2016)
Mahmoudi, Z., Nørgaard, K., Poulsen, N.K., Madsen, H., Jørgensen, J.B.: Fault and meal detection by redundant continuous glucose monitors and the unscented kalman filter. Biomedical Signal Processing and Control 38, 86–99 (2017)
Mahmoudi, Z., Wendt, S.L., Boiroux, D., Hagdrup, M., Nørgaard, K., Poulsen, N.K., Madsen, H., Jørgensen, J.B.: Comparison of three nonlinear filters for fault detection in continuous glucose monitors. In: 2016 38th Annual International Con- ference of the IEEE Engineering in Medicine and Biology Society (EMBC). pp. 3507–3510. IEEE (2016)
Molina, R., Rodríguez, C., et al.: Definición, clasificación y diagnóstico de la di- abetes mellitus. Revista venezolana de endocrinología y metabolismo 10, 7–12 (2012)
Reyes Sanamé, F.A., Pérez Álvarez, M.L., Alfonso Figueredo, E., Ramírez Es- tupiñan, M., Jiménez Rizo, Y.: Tratamiento actual de la diabetes mellitus tipo 2. Correo científico médico 20(1), 98–121 (2016)
Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review 65(6), 386 (1958)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back- propagating errors. nature 323(6088), 533–536 (1986)
Salgado, V.R., Hernández, J.L., López, G.M.: Descontrol glucémico asociado a la falta de bienestar emocional en personas con diabetes mellitus (2025)
Thomas, J.B., Chaudhari, S.G., Shihabudheen, K., Verma, N.K.: Cnn-based trans- former model for fault detection in power system networks. IEEE Transactions on Instrumentation and Measurement 72, 1–10 (2023)
Tunstall, L., Von Werra, L., Wolf, T.: Natural language processing with transform- ers. » O’Reilly Media, Inc.» (2022)
Vaswani, A.: Attention is all you need. Advances in Neural Information Processing Systems (2017)
Wen, Q., Zhou, T., Zhang, C., Chen, W., Ma, Z., Yan, J., Sun, L.: Transformers in time series: A survey. arXiv preprint arXiv:2202.07125 (2022)
Yu, X., Sun, X., Zhao, Y., Liu, J., Li, H.: Fault detection of continuous glucose mea- surements based on modified k-medoids clustering algorithm. Neural Computing and Applications pp. 1–10 (2020)
Zhao, C., Fu, Y.: Statistical analysis based online sensor failure detection for con- tinuous glucose monitoring in type i diabetes. Chemometrics and Intelligent Lab- oratory Systems 144, 128–137 (2015)
Zhao, Q., Zhu, J., Shen, X., Lin, C., Zhang, Y., Liang, Y., Cao, B., Li, J., Liu, X., Rao, W., et al.: Chinese diabetes datasets for data-driven machine learning. Scientific Data 10(1), 35 (2023)
Zhu, T., Kuang, L., Piao, C., Zeng, J., Li, K., Georgiou, P.: Population-specific glucose prediction in diabetes care with transformer-based deep learning on the edge. IEEE Transactions on Biomedical Circuits and Systems (2024)