A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus
Type 1 diabetes mellitus (DM1) is a metabolic disease derived from falls in pancreatic insulin production resulting in chronic hyperglycemia. DM1 subjects usually have to undertake a number of assessments of blood glucose levels every day, employing capillary glucometers for the monitoring of blood...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/4/1742 |
| _version_ | 1827589184951418880 |
|---|---|
| author | Ignacio Rodríguez-Rodríguez José-Víctor Rodríguez Wai Lok Woo Bo Wei Domingo-Javier Pardo-Quiles |
| author_facet | Ignacio Rodríguez-Rodríguez José-Víctor Rodríguez Wai Lok Woo Bo Wei Domingo-Javier Pardo-Quiles |
| author_sort | Ignacio Rodríguez-Rodríguez |
| collection | DOAJ |
| description | Type 1 diabetes mellitus (DM1) is a metabolic disease derived from falls in pancreatic insulin production resulting in chronic hyperglycemia. DM1 subjects usually have to undertake a number of assessments of blood glucose levels every day, employing capillary glucometers for the monitoring of blood glucose dynamics. In recent years, advances in technology have allowed for the creation of revolutionary biosensors and continuous glucose monitoring (CGM) techniques. This has enabled the monitoring of a subject’s blood glucose level in real time. On the other hand, few attempts have been made to apply machine learning techniques to predicting glycaemia levels, but dealing with a database containing such a high level of variables is problematic. In this sense, to the best of the authors’ knowledge, the issues of proper feature selection (FS)—the stage before applying predictive algorithms—have not been subject to in-depth discussion and comparison in past research when it comes to forecasting glycaemia. Therefore, in order to assess how a proper FS stage could improve the accuracy of the glycaemia forecasted, this work has developed six FS techniques alongside four predictive algorithms, applying them to a full dataset of biomedical features related to glycaemia. These were harvested through a wide-ranging passive monitoring process involving 25 patients with DM1 in practical real-life scenarios. From the obtained results, we affirm that Random Forest (RF) as both predictive algorithm and FS strategy offers the best average performance (Root Median Square Error, RMSE = 18.54 mg/dL) throughout the 12 considered predictive horizons (up to 60 min in steps of 5 min), showing Support Vector Machines (SVM) to have the best accuracy as a forecasting algorithm when considering, in turn, the average of the six FS techniques applied (RMSE = 20.58 mg/dL). |
| first_indexed | 2024-03-09T00:51:01Z |
| format | Article |
| id | doaj.art-e9f691de81c848e293400c0e0d967615 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T00:51:01Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e9f691de81c848e293400c0e0d9676152023-12-11T17:12:32ZengMDPI AGApplied Sciences2076-34172021-02-01114174210.3390/app11041742A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes MellitusIgnacio Rodríguez-Rodríguez0José-Víctor Rodríguez1Wai Lok Woo2Bo Wei3Domingo-Javier Pardo-Quiles4Departamento de Ingeniería de Comunicaciones, Universidad de Málaga, 29071 Málaga, SpainDepartamento de Tecnologías de la Información y las Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, SpainDepartment of Computer and Information Sciences, Northumbria University, Newcastle upon Tyne NE1 8ST, UKDepartment of Computer and Information Sciences, Northumbria University, Newcastle upon Tyne NE1 8ST, UKDepartamento de Tecnologías de la Información y las Comunicaciones, Universidad Politécnica de Cartagena, 30202 Cartagena, SpainType 1 diabetes mellitus (DM1) is a metabolic disease derived from falls in pancreatic insulin production resulting in chronic hyperglycemia. DM1 subjects usually have to undertake a number of assessments of blood glucose levels every day, employing capillary glucometers for the monitoring of blood glucose dynamics. In recent years, advances in technology have allowed for the creation of revolutionary biosensors and continuous glucose monitoring (CGM) techniques. This has enabled the monitoring of a subject’s blood glucose level in real time. On the other hand, few attempts have been made to apply machine learning techniques to predicting glycaemia levels, but dealing with a database containing such a high level of variables is problematic. In this sense, to the best of the authors’ knowledge, the issues of proper feature selection (FS)—the stage before applying predictive algorithms—have not been subject to in-depth discussion and comparison in past research when it comes to forecasting glycaemia. Therefore, in order to assess how a proper FS stage could improve the accuracy of the glycaemia forecasted, this work has developed six FS techniques alongside four predictive algorithms, applying them to a full dataset of biomedical features related to glycaemia. These were harvested through a wide-ranging passive monitoring process involving 25 patients with DM1 in practical real-life scenarios. From the obtained results, we affirm that Random Forest (RF) as both predictive algorithm and FS strategy offers the best average performance (Root Median Square Error, RMSE = 18.54 mg/dL) throughout the 12 considered predictive horizons (up to 60 min in steps of 5 min), showing Support Vector Machines (SVM) to have the best accuracy as a forecasting algorithm when considering, in turn, the average of the six FS techniques applied (RMSE = 20.58 mg/dL).https://www.mdpi.com/2076-3417/11/4/1742diabetes mellitusmachine learningfeature selectiontime series forecasting |
| spellingShingle | Ignacio Rodríguez-Rodríguez José-Víctor Rodríguez Wai Lok Woo Bo Wei Domingo-Javier Pardo-Quiles A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus Applied Sciences diabetes mellitus machine learning feature selection time series forecasting |
| title | A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus |
| title_full | A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus |
| title_fullStr | A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus |
| title_full_unstemmed | A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus |
| title_short | A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus |
| title_sort | comparison of feature selection and forecasting machine learning algorithms for predicting glycaemia in type 1 diabetes mellitus |
| topic | diabetes mellitus machine learning feature selection time series forecasting |
| url | https://www.mdpi.com/2076-3417/11/4/1742 |
| work_keys_str_mv | AT ignaciorodriguezrodriguez acomparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT josevictorrodriguez acomparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT wailokwoo acomparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT bowei acomparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT domingojavierpardoquiles acomparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT ignaciorodriguezrodriguez comparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT josevictorrodriguez comparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT wailokwoo comparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT bowei comparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus AT domingojavierpardoquiles comparisonoffeatureselectionandforecastingmachinelearningalgorithmsforpredictingglycaemiaintype1diabetesmellitus |