Regularized linear discriminant analysis of EEG features in dementia patients
The present study explores if EEG spectral parameters can discriminate between healthy elderly controls (HC), Alzheimer’s disease (AD) and vascular dementia (VaD) using. We considered EEG data recorded during normal clinical routine with 114 healthy controls (HC), 114 AD and 114 vascular dementia Va...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2016-11-01
|
| Series: | Frontiers in Aging Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnagi.2016.00273/full |
| _version_ | 1819065653150089216 |
|---|---|
| author | Emanuel Filipe Neto Emanuel Filipe Neto Felix Bießmann Harald Aurlien Helge Nordby Tom Eichele Tom Eichele Tom Eichele |
| author_facet | Emanuel Filipe Neto Emanuel Filipe Neto Felix Bießmann Harald Aurlien Helge Nordby Tom Eichele Tom Eichele Tom Eichele |
| author_sort | Emanuel Filipe Neto |
| collection | DOAJ |
| description | The present study explores if EEG spectral parameters can discriminate between healthy elderly controls (HC), Alzheimer’s disease (AD) and vascular dementia (VaD) using. We considered EEG data recorded during normal clinical routine with 114 healthy controls (HC), 114 AD and 114 vascular dementia VaD patients. The spectral features extracted from the EEG were the absolute delta power, decay from lower to higher frequencies, amplitude, center and dispersion of the alpha power and baseline power of the entire frequency spectrum. For discrimination, we submitted these EEG features to regularized linear discriminant analysis algorithm with a 10 fold cross-validation. To check the consistency of the results obtained by our classifiers, we applied bootstrap statistics. Four binary classifiers were used to discriminate HC from AD, HC from VaD, AD from VaD and HC from dementia patients (AD or VaD). For each model, we measured the discrimination performance using the area under curve (AUC) and the accuracy of the cross-validation (cv-ACC). We applied this procedure using two different sets of predictors. The first set considered all the features extracted from the 22 channels. For the second set of features we automatically rejected features poorly correlated with their labels. Fairly good results were obtained when discriminating HC from dementia patients with AD or VaD (AUC=0.84). We also obtained AUC=0.74 for discrimination of AD from HC, AUC=0.77 for discrimination of VaD from HC and finally AUC=0.61 for discrimination of AD from VaD. Our models were able to separate healthy controls from dementia patients, and also and to discriminate AD from VaD above chance. Our results suggest that these features may be relevant for the clinical assessment of patients with dementia. |
| first_indexed | 2024-12-21T15:49:53Z |
| format | Article |
| id | doaj.art-a098de1497ed4b168efd383a2eace1ba |
| institution | Directory Open Access Journal |
| issn | 1663-4365 |
| language | English |
| last_indexed | 2024-12-21T15:49:53Z |
| publishDate | 2016-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging Neuroscience |
| spelling | doaj.art-a098de1497ed4b168efd383a2eace1ba2022-12-21T18:58:16ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652016-11-01810.3389/fnagi.2016.00273223076Regularized linear discriminant analysis of EEG features in dementia patientsEmanuel Filipe Neto0Emanuel Filipe Neto1Felix Bießmann2Harald Aurlien3Helge Nordby4Tom Eichele5Tom Eichele6Tom Eichele7University of BergenHaukeland university HospitalAmazon Development Center GermanyHaukeland university HospitalUniversity of BergenUniversity of BergenHaukeland university HospitalK.G. Jebsen Center for Neuropsychiatric DisordersThe present study explores if EEG spectral parameters can discriminate between healthy elderly controls (HC), Alzheimer’s disease (AD) and vascular dementia (VaD) using. We considered EEG data recorded during normal clinical routine with 114 healthy controls (HC), 114 AD and 114 vascular dementia VaD patients. The spectral features extracted from the EEG were the absolute delta power, decay from lower to higher frequencies, amplitude, center and dispersion of the alpha power and baseline power of the entire frequency spectrum. For discrimination, we submitted these EEG features to regularized linear discriminant analysis algorithm with a 10 fold cross-validation. To check the consistency of the results obtained by our classifiers, we applied bootstrap statistics. Four binary classifiers were used to discriminate HC from AD, HC from VaD, AD from VaD and HC from dementia patients (AD or VaD). For each model, we measured the discrimination performance using the area under curve (AUC) and the accuracy of the cross-validation (cv-ACC). We applied this procedure using two different sets of predictors. The first set considered all the features extracted from the 22 channels. For the second set of features we automatically rejected features poorly correlated with their labels. Fairly good results were obtained when discriminating HC from dementia patients with AD or VaD (AUC=0.84). We also obtained AUC=0.74 for discrimination of AD from HC, AUC=0.77 for discrimination of VaD from HC and finally AUC=0.61 for discrimination of AD from VaD. Our models were able to separate healthy controls from dementia patients, and also and to discriminate AD from VaD above chance. Our results suggest that these features may be relevant for the clinical assessment of patients with dementia.http://journal.frontiersin.org/Journal/10.3389/fnagi.2016.00273/fullAlzheimer’s diseaseVascular Dementiaquantitative analysisElectroencephalogramLDAqEEG |
| spellingShingle | Emanuel Filipe Neto Emanuel Filipe Neto Felix Bießmann Harald Aurlien Helge Nordby Tom Eichele Tom Eichele Tom Eichele Regularized linear discriminant analysis of EEG features in dementia patients Frontiers in Aging Neuroscience Alzheimer’s disease Vascular Dementia quantitative analysis Electroencephalogram LDA qEEG |
| title | Regularized linear discriminant analysis of EEG features in dementia patients |
| title_full | Regularized linear discriminant analysis of EEG features in dementia patients |
| title_fullStr | Regularized linear discriminant analysis of EEG features in dementia patients |
| title_full_unstemmed | Regularized linear discriminant analysis of EEG features in dementia patients |
| title_short | Regularized linear discriminant analysis of EEG features in dementia patients |
| title_sort | regularized linear discriminant analysis of eeg features in dementia patients |
| topic | Alzheimer’s disease Vascular Dementia quantitative analysis Electroencephalogram LDA qEEG |
| url | http://journal.frontiersin.org/Journal/10.3389/fnagi.2016.00273/full |
| work_keys_str_mv | AT emanuelfilipeneto regularizedlineardiscriminantanalysisofeegfeaturesindementiapatients AT emanuelfilipeneto regularizedlineardiscriminantanalysisofeegfeaturesindementiapatients AT felixbießmann regularizedlineardiscriminantanalysisofeegfeaturesindementiapatients AT haraldaurlien regularizedlineardiscriminantanalysisofeegfeaturesindementiapatients AT helgenordby regularizedlineardiscriminantanalysisofeegfeaturesindementiapatients AT tomeichele regularizedlineardiscriminantanalysisofeegfeaturesindementiapatients AT tomeichele regularizedlineardiscriminantanalysisofeegfeaturesindementiapatients AT tomeichele regularizedlineardiscriminantanalysisofeegfeaturesindementiapatients |