L R Trambaiolli1, N Spolaôr2, A C Lorena3, R Anghinah4, J R Sato5. 1. Center of Mathematics, Computing and Cognition, Universidade Federal do ABC, Santo André, Brazil. Electronic address: lucasrtb@gmail.com. 2. Laboratório de Bioinformática, Centro de Engenharia e Ciências Exatas, Universidade Estadual do Oeste do Paraná, Foz do Iguaçu, Brazil. 3. Instituto de Ciência e Tecnologia, Universidade Federal de São Paulo, São José dos Campos, Brazil. 4. Reference Center for Cognitive Disorders, Hospital das Clínicas, University of São Paulo, Rua Arruda Alvim 206, São Paulo, Brazil. 5. Center of Mathematics, Computing and Cognition, Universidade Federal do ABC, Santo André, Brazil.
Abstract
OBJECTIVE: In many decision support systems, some input features can be marginal or irrelevant to the diagnosis, while others can be redundant among each other. Thus, feature selection (FS) algorithms are often considered to find relevant/non-redundant features. This study aimed to evaluate the relevance of FS approaches applied to Alzheimer's Disease (AD) EEG-based diagnosis and compare the selected features with previous clinical findings. METHODS: Eight different FS algorithms were applied to EEG spectral measures from 22 AD patients and 12 healthy age-matched controls. The FS contribution was evaluated by considering the leave-one-subject-out accuracy of Support Vector Machine classifiers built in the datasets described by the selected features. RESULTS: The Filtered Subset Evaluator technique achieved the best performance improvement both on a per-patient basis (91.18% of accuracy) and on a per-epoch basis (85.29±21.62%), after removing 88.76±1.12% of the original features. All algorithms found out that alpha and beta bands are relevant features, which is in agreement with previous findings from the literature. CONCLUSION: Biologically plausible EEG datasets could achieve improved accuracies with pre-processing FS steps. SIGNIFICANCE: The results suggest that the FS and classification techniques are an attractive complementary tool in order to reveal potential biomarkers aiding the AD clinical diagnosis.
OBJECTIVE: In many decision support systems, some input features can be marginal or irrelevant to the diagnosis, while others can be redundant among each other. Thus, feature selection (FS) algorithms are often considered to find relevant/non-redundant features. This study aimed to evaluate the relevance of FS approaches applied to Alzheimer's Disease (AD) EEG-based diagnosis and compare the selected features with previous clinical findings. METHODS: Eight different FS algorithms were applied to EEG spectral measures from 22 ADpatients and 12 healthy age-matched controls. The FS contribution was evaluated by considering the leave-one-subject-out accuracy of Support Vector Machine classifiers built in the datasets described by the selected features. RESULTS: The Filtered Subset Evaluator technique achieved the best performance improvement both on a per-patient basis (91.18% of accuracy) and on a per-epoch basis (85.29±21.62%), after removing 88.76±1.12% of the original features. All algorithms found out that alpha and beta bands are relevant features, which is in agreement with previous findings from the literature. CONCLUSION: Biologically plausible EEG datasets could achieve improved accuracies with pre-processing FS steps. SIGNIFICANCE: The results suggest that the FS and classification techniques are an attractive complementary tool in order to reveal potential biomarkers aiding the AD clinical diagnosis.
Authors: Eduardo Perez-Valero; Christian Morillas; Miguel A Lopez-Gordo; Ismael Carrera-Muñoz; Samuel López-Alcalde; Rosa M Vílchez-Carrillo Journal: Front Neuroinform Date: 2022-07-11 Impact factor: 3.739