Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modeling
Abstract Background Type 1 diabetes (T1D) is a chronic endocrine disorder characterized by high blood glucose levels, impacting millions of people globally. Its management requires intensive insulin therapy, frequent blood glucose monitoring, and lifestyle adjustments. The accurate prediction of the...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-025-02867-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571599146975232 |
|---|---|
| author | Daphne N. Katsarou Eleni I. Georga Maria A. Christou Panagiota A. Christou Stelios Tigas Costas Papaloukas Dimitrios I. Fotiadis |
| author_facet | Daphne N. Katsarou Eleni I. Georga Maria A. Christou Panagiota A. Christou Stelios Tigas Costas Papaloukas Dimitrios I. Fotiadis |
| author_sort | Daphne N. Katsarou |
| collection | DOAJ |
| description | Abstract Background Type 1 diabetes (T1D) is a chronic endocrine disorder characterized by high blood glucose levels, impacting millions of people globally. Its management requires intensive insulin therapy, frequent blood glucose monitoring, and lifestyle adjustments. The accurate prediction of the short-term course of glucose levels in the subcutaneous space in T1D people, as measured by a continuous glucose monitoring (CGM) system, is essential for improving glucose control by avoiding harmful hypoglycaemic and hyperglycaemic glucose swings, facilitating precise insulin management and individualized care and, in turn, minimizing long-term vascular complications. Methods In this study, we propose an ensemble univariate short-term predictive model of the subcutaneous glucose concentration in T1D targeting at improving its error in the hypoglycaemic region. As such, the underlying basis functions are selected to minimize the percentage of erroneous predictions (EP) in the hypoglycaemic region, with EP being evaluated with continuous glucose error grid analysis (CG-EGA). The dataset comprises 29 individuals with T1D, who were monitored for 2 to 4 weeks during the GlucoseML prospective observational clinical study. Results Among six different basis models (i.e., linear regression (LR), automatic relevance determination (ARD), support vector regression (SVR), Gaussian process regression (GPR), eXtreme gradient boosting (XGBoost), and long short-term memory (LSTM)), XGBoost and SVR showed a dominant performance in the hypoglycaemic region and were selected as the constituent basis models of the ensemble model. The results indicate that the ensemble model significantly reduces the percentage of EP in the hypoglycaemic region for a 30 min prediction horizon to 19% as compared with its individual basis models (i.e., XGBoost and SVR), whilst its errors over the entire glucose range (hypoglycaemia, euglycaemia, and hyperglycaemia) are similar to those of the basis models. Conclusions The consideration of the performance of the basis functions in the hypoglycaemic region during the construction of the ensemble model contributes to enhancing their joint performance in that specific area. This could lead to more precise insulin management and a reduced risk of short-term hypoglycaemic fluctuations. |
| format | Article |
| id | doaj-art-8db3773139644e3facd28f0f1f6c3ef2 |
| institution | Kabale University |
| issn | 1472-6947 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj-art-8db3773139644e3facd28f0f1f6c3ef22025-02-02T12:27:46ZengBMCBMC Medical Informatics and Decision Making1472-69472025-01-0125111710.1186/s12911-025-02867-2Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modelingDaphne N. Katsarou0Eleni I. Georga1Maria A. Christou2Panagiota A. Christou3Stelios Tigas4Costas Papaloukas5Dimitrios I. Fotiadis6Department of Biological Applications and Technology, University of IoanninaUnit of Medical Technology Intelligent Information Systems, Department of Materials Science and Engineering, University of IoanninaDepartment of Endocrinology, University Hospital of IoanninaDepartment of Endocrinology, University Hospital of IoanninaDepartment of Endocrinology, University Hospital of IoanninaDepartment of Biological Applications and Technology, University of IoanninaUnit of Medical Technology Intelligent Information Systems, Department of Materials Science and Engineering, University of IoanninaAbstract Background Type 1 diabetes (T1D) is a chronic endocrine disorder characterized by high blood glucose levels, impacting millions of people globally. Its management requires intensive insulin therapy, frequent blood glucose monitoring, and lifestyle adjustments. The accurate prediction of the short-term course of glucose levels in the subcutaneous space in T1D people, as measured by a continuous glucose monitoring (CGM) system, is essential for improving glucose control by avoiding harmful hypoglycaemic and hyperglycaemic glucose swings, facilitating precise insulin management and individualized care and, in turn, minimizing long-term vascular complications. Methods In this study, we propose an ensemble univariate short-term predictive model of the subcutaneous glucose concentration in T1D targeting at improving its error in the hypoglycaemic region. As such, the underlying basis functions are selected to minimize the percentage of erroneous predictions (EP) in the hypoglycaemic region, with EP being evaluated with continuous glucose error grid analysis (CG-EGA). The dataset comprises 29 individuals with T1D, who were monitored for 2 to 4 weeks during the GlucoseML prospective observational clinical study. Results Among six different basis models (i.e., linear regression (LR), automatic relevance determination (ARD), support vector regression (SVR), Gaussian process regression (GPR), eXtreme gradient boosting (XGBoost), and long short-term memory (LSTM)), XGBoost and SVR showed a dominant performance in the hypoglycaemic region and were selected as the constituent basis models of the ensemble model. The results indicate that the ensemble model significantly reduces the percentage of EP in the hypoglycaemic region for a 30 min prediction horizon to 19% as compared with its individual basis models (i.e., XGBoost and SVR), whilst its errors over the entire glucose range (hypoglycaemia, euglycaemia, and hyperglycaemia) are similar to those of the basis models. Conclusions The consideration of the performance of the basis functions in the hypoglycaemic region during the construction of the ensemble model contributes to enhancing their joint performance in that specific area. This could lead to more precise insulin management and a reduced risk of short-term hypoglycaemic fluctuations.https://doi.org/10.1186/s12911-025-02867-2Type 1 diabetesContinuous glucose monitoringGlucose predictionMachine learning |
| spellingShingle | Daphne N. Katsarou Eleni I. Georga Maria A. Christou Panagiota A. Christou Stelios Tigas Costas Papaloukas Dimitrios I. Fotiadis Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modeling BMC Medical Informatics and Decision Making Type 1 diabetes Continuous glucose monitoring Glucose prediction Machine learning |
| title | Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modeling |
| title_full | Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modeling |
| title_fullStr | Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modeling |
| title_full_unstemmed | Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modeling |
| title_short | Optimizing hypoglycaemia prediction in type 1 diabetes with Ensemble Machine Learning modeling |
| title_sort | optimizing hypoglycaemia prediction in type 1 diabetes with ensemble machine learning modeling |
| topic | Type 1 diabetes Continuous glucose monitoring Glucose prediction Machine learning |
| url | https://doi.org/10.1186/s12911-025-02867-2 |
| work_keys_str_mv | AT daphnenkatsarou optimizinghypoglycaemiapredictionintype1diabeteswithensemblemachinelearningmodeling AT eleniigeorga optimizinghypoglycaemiapredictionintype1diabeteswithensemblemachinelearningmodeling AT mariaachristou optimizinghypoglycaemiapredictionintype1diabeteswithensemblemachinelearningmodeling AT panagiotaachristou optimizinghypoglycaemiapredictionintype1diabeteswithensemblemachinelearningmodeling AT steliostigas optimizinghypoglycaemiapredictionintype1diabeteswithensemblemachinelearningmodeling AT costaspapaloukas optimizinghypoglycaemiapredictionintype1diabeteswithensemblemachinelearningmodeling AT dimitriosifotiadis optimizinghypoglycaemiapredictionintype1diabeteswithensemblemachinelearningmodeling |