Data mining process for identification of non-spontaneous saccadic movements in clinical electrooculography

• Published in: Neurocomputing (Amsterdam) Vol. 250; pp. 28 - 36
• Main Authors: Becerra-García, R.A., García-Bermúdez, R.V., Joya-Caparrós, G., Fernández-Higuera, A., Velázquez-Rodríguez, C., Velázquez-Mariño, M., Cuevas-Beltrán, F.R., García-Lagos, F., Rodráguez-Labrada, R.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 09.08.2017
• Subjects: Classification and regression trees; Clinical electrooculography; K-nearest neighbors; Saccade identification; Support vector machines; Support vector machines; Saccade identification; K-nearest neighbors; Clinical electrooculography; Classification and regression trees
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2016.10.077

In this paper we evaluate the use of the machine learning algorithms Support Vector Machines (SVM), K-Nearest Neighbors (KNN) and Classification and Regression Trees (CART) to identify non-spontaneous saccades in clinical electrooculography tests. We propose a modification to an adaptive threshold estimation algorithm for detecting signal impulses without the need for any manually pre-established parameters. Data mining tasks such as feature selection and model tuning were performed, obtaining very efficient models using only 3 attributes: amplitude deviation, absolute response latency and relative latency. The models were evaluated with signals recorded from subjects affected by Spinocerebellar Ataxia type 2 (SCA2). Results obtained by the algorithm show accuracies over 98%, recalls over 98% and precisions over 95% for the three models evaluated.