Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes
| Autor: | Oscar Garnica, José Ignacio Hidalgo, Juan Lanchares, Felix Tena |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Blood Glucose
Computer science TP1-1185 Machine learning computer.software_genre Biochemistry Article Analytical Chemistry blood glucose prediction Humans Preprocessor In patient Electrical and Electronic Engineering Instrumentation diabetes Artificial neural network Ensemble forecasting business.industry Blood Glucose Self-Monitoring Chemical technology Deep learning Rank (computer programming) deep learning neural networks Atomic and Molecular Physics and Optics Diabetes Mellitus Type 1 Workflow Neural Networks Computer Enhanced Data Rates for GSM Evolution Artificial intelligence business ensemble models computer Algorithms |
| Zdroj: | Sensors, Vol 21, Iss 7090, p 7090 (2021) Sensors (Basel, Switzerland) Sensors Volume 21 Issue 21 |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s21217090 |
| Popis: | This article proposes two ensemble neural network-based models for blood glucose prediction at three different prediction horizons—30, 60, and 120 min—and compares their performance with ten recently proposed neural networks. The twelve models’ performances are evaluated under the same OhioT1DM Dataset, preprocessing workflow, and tools at the three prediction horizons using the most common metrics in blood glucose prediction, and we rank the best-performing ones using three methods devised for the statistical comparison of the performance of multiple algorithms: scmamp, model confidence set, and superior predictive ability. Our analysis provides a comparison of the state-of-the-art neural networks for blood glucose prediction, estimating the model’s error, highlighting those with the highest probability of being the best predictors, and providing a guide for their use in clinical practice. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|