Automatic blood glucose classification for gestational diabetes with feature selection: decision trees vs neural networks
| Autor: | María Hernando, Gema García-Sáez, M. Morillo, Estefanía Caballero-Ruiz, Belén Pons, Enrique J. Gómez, M. Balsells, Mercedes Rigla |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Decision support system
Computer science Medicina Decision tree 030209 endocrinology & metabolism Feature selection Best-first search 02 engineering and technology Machine learning computer.software_genre 03 medical and health sciences 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering medicine Blood Glucose Measurement Telecomunicaciones Artificial neural network business.industry Glucose meter Pattern recognition medicine.disease Gestational diabetes ComputingMethodologies_PATTERNRECOGNITION 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Zdroj: | IFMBE Proceedings | XIII Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON 2013) | 25/09/2013-28/09/2013 | Sevilla, Spain Archivo Digital UPM Universidad Politécnica de Madrid IFMBE Proceedings ISBN: 9783319008455 |
| Popis: | Automatic blood glucose classification may help specialists to provide a better interpretation of blood glucose data, downloaded directly from patients glucose meter and will contribute in the development of decision support systems for gestational diabetes. This paper presents an automatic blood glucose classifier for gestational diabetes that compares 6 different feature selection methods for two machine learning algorithms: neural networks and decision trees. Three searching algorithms, Greedy, Best First and Genetic, were combined with two different evaluators, CSF and Wrapper, for the feature selection. The study has been made with 6080 blood glucose measurements from 25 patients. Decision trees with a feature set selected with the Wrapper evaluator and the Best first search algorithm obtained the best accuracy: 95.92%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|