Using nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose prediction
Abstract Background Predicting of future blood glucose (BG) concentration is important for diabetes control. Many automatic BG monitoring or controlling systems use BG predictors. The accuracy of the prediction for long prediction time is a major factor affecting the performance of the control syste...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-04-01
|
| Series: | Bioelectronic Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42234-024-00141-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544406586359808 |
|---|---|
| author | Fayrouz Allam |
| author_facet | Fayrouz Allam |
| author_sort | Fayrouz Allam |
| collection | DOAJ |
| description | Abstract Background Predicting of future blood glucose (BG) concentration is important for diabetes control. Many automatic BG monitoring or controlling systems use BG predictors. The accuracy of the prediction for long prediction time is a major factor affecting the performance of the control system. The predicted BG can be used for glycemia management in the form of early hypoglycemic/hyperglycemic alarms or adjusting insulin injections. Recent developments in continuous glucose monitoring (CGM) devices open new opportunities for glycemia management of diabetic patients. Many of those systems need prediction for long prediction horizons to avoid going through hypo or hyperglycemia. Methods In this article a nonlinear autoregressive exogenous input neural network (NNARX) is proposed to predict the glucose concentration for longer prediction horizons (PHs) than that was obtained previously with an established recurrent neural network (RNN). The proposed NNARX is a modified version from our previously published RNN with different initialization and building technique but has the same architecture. The modification is based on starting with building nonlinear autoregressive exogenous input model using MATLAB and train it, then close the loop to get NNARX network. Results The results of using the proposed NNARX indicate that the proposed NNARX is better in prediction and stability than unmodified RNN as PH becomes higher than 45 minutes. Conclusions Modification in RNN building extends the ability of the prediction till 100 minutes. It performs statistically significant improvements in the FIT and RMSE values for 100 minutes prediction. It also decreases root mean squared error (RMSE) for both 45 and 60 minutes of prediction. |
| format | Article |
| id | doaj-art-022826727a5a44dab4057e1a1dc2a6a5 |
| institution | Kabale University |
| issn | 2332-8886 |
| language | English |
| publishDate | 2024-04-01 |
| publisher | BMC |
| record_format | Article |
| series | Bioelectronic Medicine |
| spelling | doaj-art-022826727a5a44dab4057e1a1dc2a6a52025-01-12T12:33:19ZengBMCBioelectronic Medicine2332-88862024-04-011011910.1186/s42234-024-00141-wUsing nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose predictionFayrouz Allam0Automatic control department, Tabin Institute For Metallurgical Studies, Iron and Steel street, TabbinAbstract Background Predicting of future blood glucose (BG) concentration is important for diabetes control. Many automatic BG monitoring or controlling systems use BG predictors. The accuracy of the prediction for long prediction time is a major factor affecting the performance of the control system. The predicted BG can be used for glycemia management in the form of early hypoglycemic/hyperglycemic alarms or adjusting insulin injections. Recent developments in continuous glucose monitoring (CGM) devices open new opportunities for glycemia management of diabetic patients. Many of those systems need prediction for long prediction horizons to avoid going through hypo or hyperglycemia. Methods In this article a nonlinear autoregressive exogenous input neural network (NNARX) is proposed to predict the glucose concentration for longer prediction horizons (PHs) than that was obtained previously with an established recurrent neural network (RNN). The proposed NNARX is a modified version from our previously published RNN with different initialization and building technique but has the same architecture. The modification is based on starting with building nonlinear autoregressive exogenous input model using MATLAB and train it, then close the loop to get NNARX network. Results The results of using the proposed NNARX indicate that the proposed NNARX is better in prediction and stability than unmodified RNN as PH becomes higher than 45 minutes. Conclusions Modification in RNN building extends the ability of the prediction till 100 minutes. It performs statistically significant improvements in the FIT and RMSE values for 100 minutes prediction. It also decreases root mean squared error (RMSE) for both 45 and 60 minutes of prediction.https://doi.org/10.1186/s42234-024-00141-wRecurrent neural networkNonlinear auto regressive modelContinuous glucose monitoringBlood glucose prediction |
| spellingShingle | Fayrouz Allam Using nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose prediction Bioelectronic Medicine Recurrent neural network Nonlinear auto regressive model Continuous glucose monitoring Blood glucose prediction |
| title | Using nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose prediction |
| title_full | Using nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose prediction |
| title_fullStr | Using nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose prediction |
| title_full_unstemmed | Using nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose prediction |
| title_short | Using nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose prediction |
| title_sort | using nonlinear auto regressive with exogenous input neural network nnarx in blood glucose prediction |
| topic | Recurrent neural network Nonlinear auto regressive model Continuous glucose monitoring Blood glucose prediction |
| url | https://doi.org/10.1186/s42234-024-00141-w |
| work_keys_str_mv | AT fayrouzallam usingnonlinearautoregressivewithexogenousinputneuralnetworknnarxinbloodglucoseprediction |