Experimentos con redes neuronales recurrentes LSTM para la predicción del nivel de glucosa de pacientes con diabetes

Experiments with LSTM recurrent neural networks for glucose level prediction in patients with diabetes

Contenido principal del artículo

Resumen

La diabetes es una enfermedad en la cual el cuerpo no procesa de manera adecuada la glucosa; el tratamiento para esta enfermedad se basa en el autocuidado del paciente, sus tendencias dietarias, el ejercicio y la administración de insulina. Predecir los niveles de glucosa futuros puede ser de gran ayuda para que el paciente y el personal médico que lo atiende determinen estrategias que mantengan sus niveles de glucosa en un rango que no sea peligroso. Las técnicas de aprendizaje profundo, entre otras cosas, permiten predecir valores en una serie temporal. En la actualidad, la técnica más usada es la predicción mediante redes neuronales recurrentes tipo LSTM. Este artículo se propone realizar experimentos variando los parámetros de redes neuronales tipo LSTM para determinar si dichos parámetros tienen alguna influencia en la precisión de la predicción del modelo.

Palabras clave:

Detalles del artículo

Referencias (VER)

Alfian, A., Syafrudin, M., Anshari, M., Benes, F., Dwi, F. T., Fahrurrozi, I., Hidayatullah A. F. & Rhee, J. (2020). Blood glucose prediction model for type 1 diabetes based on artificial neural network with time-domain features. Biocybernetics and Biomedical Engineering, 40(4), 1586-1599. https://doi.org/10.1016/j.bbe.2020.10.004

Amir, T. (2022). Setup Neural Networks Hyperparameters for Best Results. LinkedIn. https://www.linkedin.com/pulse/setup-neural-networks-hyperparameters-best-results-takbiri

Anderson, S. M., Raghinaru, D., Pinsker, J. E., Boscari, F., Renard, E., Buckingham, B. A., Nimri, R., Doyle, F. J., Brown, S. A., Keith-Hynes, P., Breton, M. D., Chernavvsky, D., Bevier, D. W., Bradley, P.

Athiyarath, S., Paul, M. & Krishnaswamy, S. (2020). A comparative study and analysis of time series forecasting techniques. SN Computer Science, 1(175). https://doi.org/10.1007/s42979-020-00180-5

Bruttomesso, D., Favero, S., Calore, R., Cobelli, C., Avogaro, A. & Farret, A. (2016). Multinational Home Use of Closed-Loop Control Is Safe and Effective. Diabetes Care, 39(7), 1143-1150. https://doi.org/10.2337/dc15-2468

Bando, H., Ebe, K., Kato, Y., Bando, M. & Yonei, Y. (2018). Investigation of blood glucose profile by continuous glucose monitoring (CGM). Endocrinology Research and Metabolism, 2(1:10), 1-4. https://www.imedpub.com/articles/investigation-of-blood-glucose-profile-by-continuous-glucose-monitoring-cgm.pdf

Blázquez-García, A., Conde, A., Mori, U. & Lozano, J. A. (2021). A review on outlier/anomaly detection in time series data. ACM Computing Surveys, 54(3), 1-33. https://doi.org/10.1145/3444690

Chou, J. S. & Tran, D. S. (2018). Forecasting energy consumption time series using machine learning techniques based on usage patterns of residential householders. Energy, 165(part b), 709-726. https://doi.org/10.1016/j.energy.2018.09.144

Colah’s Blog. (2015). Understanding LSTM Networks. https://colah.github.io/posts/2015-08-Understanding-LSTMs/

Comito, C. & Pizzuti, C. (2022). Artificial intelligence for forecasting and diagnosing COVID-19 pandemic: A focused review. Artificial Intelligence in Medicine, 128, 102286. https://doi.org/10.1016/j.artmed.2022.102286

Contreras, I. & Vehi, J. (2018). Artificial intelligence for diabetes management and decision support: literature review. Journal of Medical Internet Research, 20(5), e10775. https://doi.org/10.2196/10775

Dunning, T. (2012). Diabetes education: Art, science and evidence. John Wiley y Sons, Incorporated.

Fagherazzi, G. & Ravaud, P. (2019). Digital diabetes: perspectives for diabetes prevention, management and research. Diabetes & Metabolism, 45(4), 322-329. https://doi.org/10.1016/j.diabet.2018.08.012

Fiorini, S., Martini, C., Malpassi, D., Cordera, R., Maggi, D., Verri, A. & Barla, A. (2017). Data-driven strategies for robust forecast of continuous glucose monitoring time-series. 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju, Korea (South), pp. 1680-1683https://doi.org/10.1109/EMBC.2017.8037164

Fonseca, V. (2010). Diabetes: improving patient care. Oxford University Press, Incorporated.

García-Jaramillo, M., Luque, C. & León-Vargas, F. (2023). Machine learning and deep learning techniques applied to diabetes research: a bibliometric analysis. Journal of Diabetes Science and Technology, 18(2), 287-301. https://doi.org/10.1177/19322968231215350

Holt, R. I., Cockram, C., Flyvbjerg, A. & Goldstein, B. J. (2017). Textbook of diabetes. John Wiley y Sons, Incorporated.

Holt, T. & Kumar, S. (2015). Abc of diabetes. John Wiley y Sons, Incorporated.

Islam, S., Hossain, E., Rahman, A., Hossain, M. S. & Andersson, K. (2020). A review on recent advancements in FOREX currency prediction. Algorithms, 13(8), 186. https://doi.org/10.3390/A13080186

Jaeb Center for Health Research. (2015). Pilot study 3 of outpatient control-to-range: safety and efficacy with day-and-night in-home use (CTR3). ID: NCT02137512. https://www.clinicaltrials.gov/study/NCT02137512

Joshi, A., Jain, P. & Mohanty, S. P. (2021). Everything you wanted to know about continuous glucose monitoring. IEEE Consumer Electronics Magazine, 10(6), 61-66. https://ieeexplore.ieee.org/document/9415429

Kang, Q., Chen, E., Li, C., Luo, H. & Liu, Y. (2023). Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling. Underground Space, 13, 335-350. https://doi.org/10.1016/j.undsp.2023.05.006

Lara-Benítez, P., Carranza-García, M. & Riquelme, J. C. (2021). An experimental review on deep learning architectures for time series forecasting. International Journal of Neural Systems, 31(3), 2130001. https://doi.org/10.1142/S0129065721300011

Levy, D. (2016). Type 1 diabetes. (2nd ed.). Oxford University Press, Incorporated.

Martinsson, J., Schliep, A., Eliasson, B. & Mogren, O. (2020). Blood glucose prediction with variance estimation using recurrent neural networks. Journal of Healthcare Informatics Research, 4, 1-18. https://doi.org/10.1007/s41666-019-00059-y

Mosquera-Ruiz, A. y García-Jaramillo, M. (2022, septiembre 13-16). Diseño de un prototipo para la generación de alarmas a partir del análisis de tendencias del perfil glucémico de un grupo de pacientes con diabetes. Nuevas realidades para la educación en ingeniería: Currículo, tecnología, medio ambiente y desarrollo, Cartagena, Colombia, ACOFI EIEI. https://acofipapers.org/index.php/eiei/article/view/2246/1880

Mosquera-Ruiz, A. (2023). Diseño de un sistema para la visualización del nivel de glucosa de un grupo de pacientes con diabetes. [Trabajo de grado]. Universidad EAN. http://hdl.handle.net/10882/12769

Oh, S., Byon, Y. J., Jang, K. & Yeo, H. (2015). Short-term travel-time prediction on highway: a review of the data-driven approach. Transport Reviews, 35(1), 4-32. https://doi.org/10.1080/01441647.2014.992496

Sharma, E. (2018). Energy forecasting based on predictive data mining techniques in smart energy grids. Energy Informatics, 1(suppl. 1):4, 367-428. https://doi.org/10.1186/s42162-018-0048-9

Sharma, S. (2017). Activation Functions in Neural Networks. Towards Data Science. https://towardsdatascience.com/activation-functions-neural-networks-1cbd9f8d91d6

Shaw, K. M. & Cummings, M. H. (2012). Diabetes: chronic complications. (2nd, ed.). John Wiley y Sons, Incorporated.

Zainuddin, Z., Ong, P. & Cemal, A. (2009). A neural network approach in predicting the blood glucose level for diabetic patients. International Journal of Computational Intelligence, 5(1). https://www.researchgate.net/publication/242595444_A_Neural_Network_Approach_in_Predicting_the_Blood_Glucose_Level_for_Diabetic_Patients

Zhu, T., Li, K., Chen, J., Herrero, P. & Georgiu, P. (2020). Dilated recurrent neural networks for glucose forecasting in type 1 diabetes. Journal of Healthcare Informatics Research, 4, 308-324. https://doi.org/10.1007/s41666-020-00068-2

Descargas

Los datos de descargas todavía no están disponibles.

Citado por