Loading...
2 results
Search Results
Now showing 1 - 2 of 2
- Electroencephalogram hybrid method for alzheimer early detectionPublication . Rodrigues, Pedro Miguel; Freitas, Diamantino Silva; Teixeira, João Paulo; Bispo, Bruno; Alves, Dílio; Garrett, CarolinaAlzheimer’s disease (AD) is a neurocognitive illness that leads to dementia and mainly affects the elderly. As the percentage of old people is strongly increasing worldwide, it is urgent to develop contributions to solve this complex problem. The early diagnosis at AD first stage known as Mild Cognitive Impairment (MCI) needs a better accuracy and there is not a biomarker able to detect AD without invasive tests. In this study, Electroencephalogram (EEG) signals have been used to serve as a way of finding parameters to improve AD diagnosis in first stages. For that, a hybrid method based on a Cepstral analysis of EEG Discrete Wavelet Transform (DWT) multiband decomposition was developed. Several Cepstral Distances (CD) were extracted to verify the lag between cepstra of conventional bands signals. The results showed that this hybrid method is a good tool for describing and distinguishing the AD EEG activity along its different stages because several statistically significant parameters variations were found between controls, MCI, moderate AD and advanced AD (the lowest p-value=0.003<0.05).
- Alzheimer's Early Prediction with ElectroencephalogramPublication . Rodrigues, Pedro Miguel; Teixeira, João Paulo; Garrett, Carolina; Alves, Dílio; Freitas, Diamantino SilvaAlzheimer’s disease (AD) is currently an incurable illness that causes dementia and patient’s condition is progressively worse and it represents one of the greatest public health challenges worldwide. The main objective of this work was to develop a classification methodology for EEG signals to improve discrimination amongst patients at varying stages of the illness, Mild Cognitive Impairment (MCI) patients and non-patients either in order to obtain a more reliable methodology to identify AD in early stages. For this purpose, a surrogate decision tree classifier was used with 2 different ways of cross-validation (leave-one-out-crossvalidation and 10-fold-cross validation). The EEG studied features were the values of maxima (NMax) and minima (NMin), the zero-crossing (Zcr) rate, the mean derivative value at a point (Mdif), the Relative Power (RP) in each of the conventional bands and finally the spectral ratios (r). The best classification was obtained with vectors of 10 features as classifier entries in a leaveone- out-cross validation process, reaching 0.934 AUC, a sensitivity of 86.19%, a specificity of 99.35%, an accuracy of 94.88%, with a low out-of-sample classification error of 6.98% which indicates that the classifier generalizes fairly well.