Cargando…

Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only

In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical even...

Descripción completa

Detalles Bibliográficos
Autores principales: Prendin, Francesco, Del Favero, Simone, Vettoretti, Martina, Sparacino, Giovanni, Facchinetti, Andrea
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7956406/
https://www.ncbi.nlm.nih.gov/pubmed/33673415
http://dx.doi.org/10.3390/s21051647
_version_ 1783664427981078528
author Prendin, Francesco
Del Favero, Simone
Vettoretti, Martina
Sparacino, Giovanni
Facchinetti, Andrea
author_facet Prendin, Francesco
Del Favero, Simone
Vettoretti, Martina
Sparacino, Giovanni
Facchinetti, Andrea
author_sort Prendin, Francesco
collection PubMed
description In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical event. The only input of this kind of algorithm is often continuous glucose monitoring (CGM) sensor data, because other signals (such as injected insulin, ingested carbs, and physical activity) are frequently unavailable. Several predictive algorithms fed by CGM data only have been proposed in the literature, but they were assessed using datasets originated by different experimental protocols, making a comparison of their relative merits difficult. The aim of the present work was to perform a head-to-head comparison of thirty different linear and nonlinear predictive algorithms using the same dataset, given by 124 CGM traces collected over 10 days with the newest Dexcom G6 sensor available on the market and considering a 30-min prediction horizon. We considered the state-of-the art methods, investigating, in particular, linear black-box methods (autoregressive; autoregressive moving-average; and autoregressive integrated moving-average, ARIMA) and nonlinear machine-learning methods (support vector regression, SVR; regression random forest; feed-forward neural network, fNN; and long short-term memory neural network). For each method, the prediction accuracy and hypoglycemia detection capabilities were assessed using either population or individualized model parameters. As far as prediction accuracy is concerned, the results show that the best linear algorithm (individualized ARIMA) provides accuracy comparable to that of the best nonlinear algorithm (individualized fNN), with root mean square errors of 22.15 and 21.52 mg/dL, respectively. As far as hypoglycemia detection is concerned, the best linear algorithm (individualized ARIMA) provided precision = 64%, recall = 82%, and one false alarm/day, comparable to the best nonlinear technique (population SVR): precision = 63%, recall = 69%, and 0.5 false alarms/day. In general, the head-to-head comparison of the thirty algorithms fed by CGM data only made using a wide dataset shows that individualized linear models are more effective than population ones, while no significant advantages seem to emerge when employing nonlinear methodologies.
format Online
Article
Text
id pubmed-7956406
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-79564062021-03-16 Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only Prendin, Francesco Del Favero, Simone Vettoretti, Martina Sparacino, Giovanni Facchinetti, Andrea Sensors (Basel) Article In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical event. The only input of this kind of algorithm is often continuous glucose monitoring (CGM) sensor data, because other signals (such as injected insulin, ingested carbs, and physical activity) are frequently unavailable. Several predictive algorithms fed by CGM data only have been proposed in the literature, but they were assessed using datasets originated by different experimental protocols, making a comparison of their relative merits difficult. The aim of the present work was to perform a head-to-head comparison of thirty different linear and nonlinear predictive algorithms using the same dataset, given by 124 CGM traces collected over 10 days with the newest Dexcom G6 sensor available on the market and considering a 30-min prediction horizon. We considered the state-of-the art methods, investigating, in particular, linear black-box methods (autoregressive; autoregressive moving-average; and autoregressive integrated moving-average, ARIMA) and nonlinear machine-learning methods (support vector regression, SVR; regression random forest; feed-forward neural network, fNN; and long short-term memory neural network). For each method, the prediction accuracy and hypoglycemia detection capabilities were assessed using either population or individualized model parameters. As far as prediction accuracy is concerned, the results show that the best linear algorithm (individualized ARIMA) provides accuracy comparable to that of the best nonlinear algorithm (individualized fNN), with root mean square errors of 22.15 and 21.52 mg/dL, respectively. As far as hypoglycemia detection is concerned, the best linear algorithm (individualized ARIMA) provided precision = 64%, recall = 82%, and one false alarm/day, comparable to the best nonlinear technique (population SVR): precision = 63%, recall = 69%, and 0.5 false alarms/day. In general, the head-to-head comparison of the thirty algorithms fed by CGM data only made using a wide dataset shows that individualized linear models are more effective than population ones, while no significant advantages seem to emerge when employing nonlinear methodologies. MDPI 2021-02-27 /pmc/articles/PMC7956406/ /pubmed/33673415 http://dx.doi.org/10.3390/s21051647 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Prendin, Francesco
Del Favero, Simone
Vettoretti, Martina
Sparacino, Giovanni
Facchinetti, Andrea
Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only
title Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only
title_full Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only
title_fullStr Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only
title_full_unstemmed Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only
title_short Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only
title_sort forecasting of glucose levels and hypoglycemic events: head-to-head comparison of linear and nonlinear data-driven algorithms based on continuous glucose monitoring data only
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7956406/
https://www.ncbi.nlm.nih.gov/pubmed/33673415
http://dx.doi.org/10.3390/s21051647
work_keys_str_mv AT prendinfrancesco forecastingofglucoselevelsandhypoglycemiceventsheadtoheadcomparisonoflinearandnonlineardatadrivenalgorithmsbasedoncontinuousglucosemonitoringdataonly
AT delfaverosimone forecastingofglucoselevelsandhypoglycemiceventsheadtoheadcomparisonoflinearandnonlineardatadrivenalgorithmsbasedoncontinuousglucosemonitoringdataonly
AT vettorettimartina forecastingofglucoselevelsandhypoglycemiceventsheadtoheadcomparisonoflinearandnonlineardatadrivenalgorithmsbasedoncontinuousglucosemonitoringdataonly
AT sparacinogiovanni forecastingofglucoselevelsandhypoglycemiceventsheadtoheadcomparisonoflinearandnonlineardatadrivenalgorithmsbasedoncontinuousglucosemonitoringdataonly
AT facchinettiandrea forecastingofglucoselevelsandhypoglycemiceventsheadtoheadcomparisonoflinearandnonlineardatadrivenalgorithmsbasedoncontinuousglucosemonitoringdataonly