Search

Objective: To design a Computer-aided diagnosis (CAD) system using an optimized methodology over the P3b wave in order to objectively and accurately discriminate between healthy controls (HC) and schizophrenic subjects (SZ)., Methods: We train, test, analyze, and compare various machine learning classification approaches optimized in terms of the correct classification rate (CCR), the degenerated Youden's index (DYI) and the area under the receiver operating curve (AUC). CAD system comprises five stages: electroencephalography (EEG) preprocessing, feature extraction, seven electrode groupings, discriminant feature selection, and binary classification., Results: With two optimal combinations of electrode grouping, filtering, feature selection algorithm, and classification machine, we get either a mean CCR = 93.42%, specificity = 0.9673, sensitivity = 0.8727, DYI = 0.9188, and AUC = 0.9567 (total-15 Hz-J5-MLP), or a mean CCR = 92.23%, specificity = 0.9499, sensitivity = 0.8838, DYI = 0.9162, and AUC = 0.9807 (right hemisphere-35 Hz-J5-SVM), which to our knowledge are higher than those available to date., Conclusions: We have verified that a more restrictive low-pass filtering achieves higher CCR as compared to others at higher frequencies in the P3b wave. In addition, results validate previous hypothesis about the importance of the parietal-temporal region, associated with memory processing, allowing us to identify powerful {feature,electrode} pairs in the diagnosis of schizophrenia, achieving higher CCR and AUC in classification of both right and left Hemispheres, and parietal-temporal EEG signals, like, for instance, the {PSE, P4} pair (J5 and mutual information feature selection)., Significance: Diagnosis of schizophrenia is made thoroughly by psychiatrists but as any human-based decision that has a subjective component. This CAD system provides the human expert with an objective complimentary measure to help him in diagnosing schizophrenia.

Schizophrenia is a disease that affects approximately 1% of the population. Its early accurate diagnosis is of vital importance to apply adequate therapy as soon as possible. We present a Statistical Discriminant Diagnosing (SDD) system that discriminates between healthy controls and subjects and that supports diagnosis by a medical professional. The system works with {feature, electrode} EEG pairs which are selected based on the statistical significance of the p‐values computed over the brain P3b wave. A bank of evoked potential pre‐processed and filtered EEG signals is recorded during an auditory odd‐ball (AOD) task and serves as input to the SDD system. These EEG signals comprise 20 features and 17 electrodes, both in time (t) and frequency (f) domain. The relevance of the Parieto‐Temporal region is shown, allowing us to identify highly discriminant {feature, electrode} pairs in the detection of schizophrenia, resulting lower p‐values in both Right and Left Hemispheres, as well as in Parieto‐Temporal EEG signals. See for instance, the {PSE, P4} pair, with p‐value = 0.00003 for (parametric) t Student and p‐value = 0.00019 for (nonparametric) U Mann‐Whitney tests, both under the 15 Hz cutoff frequency of a low pass EEG preprocessing filter. The relevance of this pair is in agreement with previously published related results. The proposed SDD system may provide the human expert (psychiatrist) with an objective complimentary information to help in the early diagnosis of schizophrenia. [ABSTRACT FROM AUTHOR]