Prediction of Adverse Glycemic Events from Continuous Glucose Monitoring Signal

Journal article


Gadaleta, M., Facchinetti, A., Grisan, E. and Rossi, M. (2019). Prediction of Adverse Glycemic Events from Continuous Glucose Monitoring Signal. IEEE Journal of Biomedical and Health Informatics. 23 (2).
AuthorsGadaleta, M., Facchinetti, A., Grisan, E. and Rossi, M.
Abstract

The most important objective of any diabetes therapy is to maintain the blood glucose concentration within the euglycemic range, avoiding or at least mitigating critical hypo/hyperglycemic episodes. Modern continuous glucose monitoring (CGM) devices bear the promise of providing the patients with an increased and timely awareness of glycemic conditions as these get dangerously near to hypo/hyperglycemia. The challenge is to detect, with reasonable advance, the patterns leading to risky situations, allowing the patient to make therapeutic decisions on the basis of future (predicted) glucose concentration levels. We underline that a technically sound performance comparison of the approaches proposed in recent years has yet to be done, thus it is unclear which one is preferred. The aim of this study is to fill this gap by carrying out a comparative analysis among the most common methods for glucose event prediction. Both regression and classification algorithms have been implemented and analyzed, including static and dynamic training approaches. The dataset consists of 89 CGM time series measured in diabetic subjects for 7 subsequent days. Performance metrics, specifically defined to assess and compare the event-prediction capabilities of the methods, have been introduced and analyzed. Our numerical results show that a static training approach exhibits better performance, in particular when regression methods are considered. However, classifiers show some improvement when trained for a specific event category, such as hyperglycemia, achieving performance comparable to the regressors, with the advantage of predicting the events sooner.

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Year2019
JournalIEEE Journal of Biomedical and Health Informatics
Journal citation23 (2)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN2168-2194
Digital Object Identifier (DOI)doi:10.1109/JBHI.2018.2823763
Web address (URL)https://ieeexplore.ieee.org/document/8332482
Publication dates
Print01 Mar 2019
Online06 Apr 2018
Publication process dates
Deposited27 Nov 2019
Accepted author manuscript
License
CC BY 4.0
File Access Level
Open
Permalink -

https://openresearch.lsbu.ac.uk/item/8895q

  • 1
    total views
  • 1
    total downloads
  • 1
    views this month
  • 0
    downloads this month

Related outputs

Does Quantification of Carotid Plaque Surface Irregularities Better Detect Symptomatic Plaques Compared to the Subjective Classification?
Rafailidis, V., Chryssogonidis, I., Grisan, E., Xerras, C., Cheimariotis, G-A., Tegos, T., Rafailidis, D., Sidhu, P. and Charitanti-Kouridou, A. (2019). Does Quantification of Carotid Plaque Surface Irregularities Better Detect Symptomatic Plaques Compared to the Subjective Classification? Journal of Ultrasound in Medicine. 38 (12), pp. 3163-3171.
An ultrasonographic multiparametric carotid plaque risk index associated with cerebrovascular symptomatology: A study comparing color Doppler imaging and contrast-enhanced ultrasonography
Rafailidis, V., Chryssogonidis, I., Xerras, C., Grisan, E., Cheimariotis, G-A., Tegos, T., Rafailidis, P.S., Sidhu, P.S. and Charitanti-Kouridou, A. (2019). An ultrasonographic multiparametric carotid plaque risk index associated with cerebrovascular symptomatology: A study comparing color Doppler imaging and contrast-enhanced ultrasonography. American Journal of Neuroradiology. 40 (6), pp. 1022-1028.
The motor cortex of the sheep: laminar organization, projections and diffusion tensor imaging of the intracranial pyramidal and extrapyramidal tracts
Peruffo, A., Corain, L., Bombardi, C., Centelleghe, C., Grisan, E., Graïc, J-M, Bontempi, P., Grandis, A. and Cozzi, B. (2019). The motor cortex of the sheep: laminar organization, projections and diffusion tensor imaging of the intracranial pyramidal and extrapyramidal tracts. Brain Structure and Function. 224 (5), pp. 1933-1946.
Building a reduced dictionary of relevant perfusion patterns from CEUS data for the classification of testis lesions
Favaron, T., Huang, D.Y., Christensen-Jeffries, K., Eckersley, R., Sidhu, P.S. and Grisan, E. (2019). Building a reduced dictionary of relevant perfusion patterns from CEUS data for the classification of testis lesions. 2019 IEEE 16th International Symposium on Biomedical Imaging. Venice, Italy 08 - 11 Apr 2019 Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ISBI.2019.8759528
Deep Convolutional Neural Network for Survival Estimation of Amyotrophic Lateral Sclerosis patients
Grisan, E., Zandon`a, A. and Di Camillo, B. (2019). Deep Convolutional Neural Network for Survival Estimation of Amyotrophic Lateral Sclerosis patients. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges, Belgium 24 - 26 Apr 2019 i6doc.
Sparse Image Reconstruction for Contrast Enhanced Cardiac Ultrasound using Diverging Waves
Stanziola, A., Toulemonde, M., Papadopoulou, V., Corbett, R., Duncan, N., Grisan, E. and Tang, M-X. (2019). Sparse Image Reconstruction for Contrast Enhanced Cardiac Ultrasound using Diverging Waves. IEEE International Ultrasonics Symposium 2019. Glasgow 09 2009 - 06 Oct 2019 Institute of Electrical and Electronics Engineers (IEEE).
Super resolution ultrasound image filtering with machine learning to reduce the localization error
Harput, S., Fong, L.H., Stanziola, A., Zhang, G., Toulemonde, M., Zhou, J., Christensen-Jeffries, K., Brown, J., Eckersley, R., Grisan, E., Dunsby, C. and Tang, M. (2019). Super resolution ultrasound image filtering with machine learning to reduce the localization error. IEEE International Ultrasonics Symposium 2019. Glasgow 09 2009 - 06 Oct 2019 Institute of Electrical and Electronics Engineers (IEEE).
Temporal Convolution Networks for Real-Time Abdominal Fetal Aorta Analysis with Ultrasound
Savioli, N., Visentin, S., Cosmi, E., Grisan, E., Lamata, P. and Montana, G. (2018). Temporal Convolution Networks for Real-Time Abdominal Fetal Aorta Analysis with Ultrasound. Artificial Neural Networks and Machine Learning – ICANN 2018. Rhodes, Greece 04 - 07 Oct 2018 Springer. doi:10.1007/978-3-030-01421-6_15