Blood Glucose Level Forecasting on Type-1-Diabetes Subjects during Physical Activity: A Comparative Analysis of Different Learning Techniques
Background: Type 1 Diabetes Mellitus (T1DM) is a widespread chronic disease in industrialized countries. Preventing blood glucose levels from exceeding the euglycaemic range would reduce the incidence of diabetes-related complications and improve the quality of life of subjects with T1DM. As a conse...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/8/6/72 |
| _version_ | 1797532629937946624 |
|---|---|
| author | Benedetta De Paoli Federico D’Antoni Mario Merone Silvia Pieralice Vincenzo Piemonte Paolo Pozzilli |
| author_facet | Benedetta De Paoli Federico D’Antoni Mario Merone Silvia Pieralice Vincenzo Piemonte Paolo Pozzilli |
| author_sort | Benedetta De Paoli |
| collection | DOAJ |
| description | Background: Type 1 Diabetes Mellitus (T1DM) is a widespread chronic disease in industrialized countries. Preventing blood glucose levels from exceeding the euglycaemic range would reduce the incidence of diabetes-related complications and improve the quality of life of subjects with T1DM. As a consequence, in the last decade, many Machine Learning algorithms aiming to forecast future blood glucose levels have been proposed. Despite the excellent performance they obtained, the prediction of abrupt changes in blood glucose values produced during physical activity (PA) is still one of the main challenges. Methods: A Jump Neural Network was developed in order to overcome the issue of predicting blood glucose values during PA. Three learning configurations were developed and tested: offline training, online training, and online training with reinforcement. All configurations were tested on six subjects suffering from T1DM that held regular PA (three aerobic and three anaerobic) and exploited Continuous Glucose Monitoring (CGM). Results: The forecasting performance was evaluated in terms of the Root-Mean-Squared-Error (RMSE), according to a paradigm of Precision Medicine. Conclusions: The online learning configurations performed better than the offline configuration in total days but not on the only CGM associated with the PA; thus, the results do not justify the increased computational burden because the improvement was not significant. |
| first_indexed | 2024-03-10T11:01:59Z |
| format | Article |
| id | doaj.art-f290eb5007e74df4a09b5e6a0dc72857 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-10T11:01:59Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-f290eb5007e74df4a09b5e6a0dc728572023-11-21T21:28:06ZengMDPI AGBioengineering2306-53542021-05-01867210.3390/bioengineering8060072Blood Glucose Level Forecasting on Type-1-Diabetes Subjects during Physical Activity: A Comparative Analysis of Different Learning TechniquesBenedetta De Paoli0Federico D’Antoni1Mario Merone2Silvia Pieralice3Vincenzo Piemonte4Paolo Pozzilli5Unit of Computer Systems and Bioinformatics, Department of Engineering, Università Campus Bio-Medico di Roma, 00128 Rome, ItalyUnit of Computer Systems and Bioinformatics, Department of Engineering, Università Campus Bio-Medico di Roma, 00128 Rome, ItalyUnit of Computer Systems and Bioinformatics, Department of Engineering, Università Campus Bio-Medico di Roma, 00128 Rome, ItalyUnit of Diabetology and Endocrinology, Department of Medicine, Università Campus Bio-Medico di Roma, 00128 Rome, ItalyUnit of Chemical Engineering, Department of Engineering, Università Campus Bio-Medico di Roma, 00128 Rome, ItalyUnit of Diabetology and Endocrinology, Department of Medicine, Università Campus Bio-Medico di Roma, 00128 Rome, ItalyBackground: Type 1 Diabetes Mellitus (T1DM) is a widespread chronic disease in industrialized countries. Preventing blood glucose levels from exceeding the euglycaemic range would reduce the incidence of diabetes-related complications and improve the quality of life of subjects with T1DM. As a consequence, in the last decade, many Machine Learning algorithms aiming to forecast future blood glucose levels have been proposed. Despite the excellent performance they obtained, the prediction of abrupt changes in blood glucose values produced during physical activity (PA) is still one of the main challenges. Methods: A Jump Neural Network was developed in order to overcome the issue of predicting blood glucose values during PA. Three learning configurations were developed and tested: offline training, online training, and online training with reinforcement. All configurations were tested on six subjects suffering from T1DM that held regular PA (three aerobic and three anaerobic) and exploited Continuous Glucose Monitoring (CGM). Results: The forecasting performance was evaluated in terms of the Root-Mean-Squared-Error (RMSE), according to a paradigm of Precision Medicine. Conclusions: The online learning configurations performed better than the offline configuration in total days but not on the only CGM associated with the PA; thus, the results do not justify the increased computational burden because the improvement was not significant.https://www.mdpi.com/2306-5354/8/6/72diabetestime series forecastingonline learningphysical activityprecision medicineneural network |
| spellingShingle | Benedetta De Paoli Federico D’Antoni Mario Merone Silvia Pieralice Vincenzo Piemonte Paolo Pozzilli Blood Glucose Level Forecasting on Type-1-Diabetes Subjects during Physical Activity: A Comparative Analysis of Different Learning Techniques Bioengineering diabetes time series forecasting online learning physical activity precision medicine neural network |
| title | Blood Glucose Level Forecasting on Type-1-Diabetes Subjects during Physical Activity: A Comparative Analysis of Different Learning Techniques |
| title_full | Blood Glucose Level Forecasting on Type-1-Diabetes Subjects during Physical Activity: A Comparative Analysis of Different Learning Techniques |
| title_fullStr | Blood Glucose Level Forecasting on Type-1-Diabetes Subjects during Physical Activity: A Comparative Analysis of Different Learning Techniques |
| title_full_unstemmed | Blood Glucose Level Forecasting on Type-1-Diabetes Subjects during Physical Activity: A Comparative Analysis of Different Learning Techniques |
| title_short | Blood Glucose Level Forecasting on Type-1-Diabetes Subjects during Physical Activity: A Comparative Analysis of Different Learning Techniques |
| title_sort | blood glucose level forecasting on type 1 diabetes subjects during physical activity a comparative analysis of different learning techniques |
| topic | diabetes time series forecasting online learning physical activity precision medicine neural network |
| url | https://www.mdpi.com/2306-5354/8/6/72 |
| work_keys_str_mv | AT benedettadepaoli bloodglucoselevelforecastingontype1diabetessubjectsduringphysicalactivityacomparativeanalysisofdifferentlearningtechniques AT federicodantoni bloodglucoselevelforecastingontype1diabetessubjectsduringphysicalactivityacomparativeanalysisofdifferentlearningtechniques AT mariomerone bloodglucoselevelforecastingontype1diabetessubjectsduringphysicalactivityacomparativeanalysisofdifferentlearningtechniques AT silviapieralice bloodglucoselevelforecastingontype1diabetessubjectsduringphysicalactivityacomparativeanalysisofdifferentlearningtechniques AT vincenzopiemonte bloodglucoselevelforecastingontype1diabetessubjectsduringphysicalactivityacomparativeanalysisofdifferentlearningtechniques AT paolopozzilli bloodglucoselevelforecastingontype1diabetessubjectsduringphysicalactivityacomparativeanalysisofdifferentlearningtechniques |