Data mining EEG signals in depression for their diagnostic value

dc.contributor.authorMohammadi, Mahdi
dc.contributor.authorAl-Azab, Fadwa
dc.contributor.authorRaahemi, Bijan
dc.contributor.authorRichards, Gregory
dc.contributor.authorJaworska, Natalia
dc.contributor.authorSmith, Dylan
dc.contributor.authorde la Salle, Sara
dc.contributor.authorBlier, Pierre
dc.contributor.authorKnott, Verner
dc.identifier.citationBMC Medical Informatics and Decision Making. 2015 Dec 23;15(1):108
dc.description.abstractAbstract Background Quantitative electroencephalogram (EEG) is one neuroimaging technique that has been shown to differentiate patients with major depressive disorder (MDD) and non-depressed healthy volunteers (HV) at the group-level, but its diagnostic potential for detecting differences at the individual level has yet to be realized. Quantitative EEGs produce complex data sets derived from digitally analyzed electrical activity at different frequency bands, at multiple electrode locations, and under different vigilance (eyes open vs. closed) states, resulting in potential feature patterns which may be diagnostically useful, but detectable only with advanced mathematical models. Methods This paper uses a data mining methodology for classifying EEGs of 53 MDD patients and 43 HVs. This included: (a) pre-processing the data, including cleaning and normalization, applying Linear Discriminant Analysis (LDA) to map the features into a new feature space; and applying Genetic Algorithm (GA) to identify the most significant features; (b) building predictive models using the Decision Tree (DT) algorithm to discover rules and hidden patterns based on the reduced and mapped features; and (c) evaluating the models based on the accuracy and false positive values on the EEG data of MDD and HV participants. Two categories of experiments were performed. The first experiment analyzed each frequency band individually, while the second experiment analyzed the bands together. Results Application of LDA and GA markedly reduced the total number of utilized features by ≥ 50 % and, with all frequency bands analyzed together, the model showed average classification accuracy (MDD vs. HV) of 80 %. The best results from model testing with additional test EEG recordings from 9 MDD patients and 35 HV individuals demonstrated an accuracy of 80 % and showed an average sensitivity of 70 %, a specificity of 76 %, and a positive (PPV) and negative predictive value (NPV) of 74 and 75 %, respectively. Conclusions These initial findings suggest that the proposed automated EEG analytical approach could be a useful adjunctive diagnostic approach in clinical practice.
dc.titleData mining EEG signals in depression for their diagnostic value
dc.typeJournal Article
dc.rights.holderMohammadi et al.
CollectionLibre accès - Publications // Open Access - Publications