Machine learning techniques combined with wearable electronics can deliver accurate short-term blood glucose level prediction models. These models can learn personalized glucose-insulin dynamics based on the sensor data collected by monitoring several aspects of the physiological condition and daily activity of an individual. Until now, the prevalent approach for developing data-driven prediction models was to collect as much data as possible to help physicians and patients optimally adjust therapy. The objective of this work was to investigate the minimum data variety, volume, and velocity required to create accurate person-centric short-term prediction models. We developed a series of these models using different machine learning time series forecasting techniques suitable for execution within a wearable processor. We conducted an extensive passive patient monitoring study in real-world conditions to build an appropriate data set. The study involved a subset of type 1 diabetic subjects wearing a flash glucose monitoring system. We comparatively and quantitatively evaluated the performance of the developed data-driven prediction models and the corresponding machine learning techniques. Our results indicate that very accurate short-term prediction can be achieved by only monitoring interstitial glucose data over a very short time period and using a low sampling frequency. The models developed can predict glucose levels within a 15-min horizon with an average error as low as 15.43 mg/dL using only 24 historic values collected within a period of sex hours, and by increasing the sampling frequency to include 72 values, the average error is reduced to 10.15 mg/dL. Our prediction models are suitable for execution within a wearable device, requiring the minimum hardware requirements while at simultaneously achieving very high prediction accuracy.

Utility of big data in predicting short-term blood glucose levels in type 1 diabetes mellitus through machine learning techniques / Rodriguez-Rodriguez, I.; Chatzigiannakis, I.; Rodriguez, J. -V.; Maranghi, M.; Gentili, M.; Zamora-Izquierdo, M. -A.. - In: SENSORS. - ISSN 1424-8220. - 19:20(2019). [10.3390/s19204482]

Utility of big data in predicting short-term blood glucose levels in type 1 diabetes mellitus through machine learning techniques

Chatzigiannakis I.
Co-primo
Membro del Collaboration Group
;
Maranghi M.
Secondo
Membro del Collaboration Group
;
Gentili M.
Penultimo
Membro del Collaboration Group
;
2019

Abstract

Machine learning techniques combined with wearable electronics can deliver accurate short-term blood glucose level prediction models. These models can learn personalized glucose-insulin dynamics based on the sensor data collected by monitoring several aspects of the physiological condition and daily activity of an individual. Until now, the prevalent approach for developing data-driven prediction models was to collect as much data as possible to help physicians and patients optimally adjust therapy. The objective of this work was to investigate the minimum data variety, volume, and velocity required to create accurate person-centric short-term prediction models. We developed a series of these models using different machine learning time series forecasting techniques suitable for execution within a wearable processor. We conducted an extensive passive patient monitoring study in real-world conditions to build an appropriate data set. The study involved a subset of type 1 diabetic subjects wearing a flash glucose monitoring system. We comparatively and quantitatively evaluated the performance of the developed data-driven prediction models and the corresponding machine learning techniques. Our results indicate that very accurate short-term prediction can be achieved by only monitoring interstitial glucose data over a very short time period and using a low sampling frequency. The models developed can predict glucose levels within a 15-min horizon with an average error as low as 15.43 mg/dL using only 24 historic values collected within a period of sex hours, and by increasing the sampling frequency to include 72 values, the average error is reduced to 10.15 mg/dL. Our prediction models are suitable for execution within a wearable device, requiring the minimum hardware requirements while at simultaneously achieving very high prediction accuracy.
2019
Continuous glucose monitoring; Experimental evaluation; Machine learning; Short-term prediction; Univariate time series; Wearable devices
01 Pubblicazione su rivista::01a Articolo in rivista
Utility of big data in predicting short-term blood glucose levels in type 1 diabetes mellitus through machine learning techniques / Rodriguez-Rodriguez, I.; Chatzigiannakis, I.; Rodriguez, J. -V.; Maranghi, M.; Gentili, M.; Zamora-Izquierdo, M. -A.. - In: SENSORS. - ISSN 1424-8220. - 19:20(2019). [10.3390/s19204482]
File allegati a questo prodotto
File Dimensione Formato  
Rodríguez-Rodríguez_Utility-of-Big-Data_2019.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 1.11 MB
Formato Adobe PDF
1.11 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1332755
Citazioni
  • ???jsp.display-item.citation.pmc??? 12
  • Scopus 44
  • ???jsp.display-item.citation.isi??? 32
social impact