Oguz Tan

Classification of Obsessive Compulsive Disorder by EEG Complexity and Hemispheric Dependency Measurements

In the present study, both single channel electroencephalography (EEG) complexity and two channel interhemispheric dependency measurements have newly been examined for classification of patients with obsessive-compulsive disorder (OCD) and controls by using support vector machine classifiers. Three embedding entropy measurements (approximate entropy, sample entropy, permutation entropy (PermEn)) are used to estimate single channel EEG complexity for 19-channel eyes closed cortical measurements. Mean coherence and mutual information are examined to measure the level of interhemispheric dependency in frequency and statistical domain, respectively for eight distinct electrode pairs placed on the scalp with respect to the international 10-20 electrode placement system. All methods are applied to short EEG segments of 2 s. The classification performance is measured 20 times with different 2-fold cross-validation data for both single channel complexity features (19 features) and interhemispheric dependency features (eight features). The highest classification accuracy of 85 ±5.2% is provided by PermEn at prefrontal regions of the brain. Even if the classification success do not provided by other methods as high as PermEn, the clear differences between patients and controls at prefrontal regions can also be obtained by using other methods except coherence. In conclusion, OCD, defined as illness of orbitofronto-striatal structures [Beucke et al., JAMA Psychiatry70 (2013) 619-629; Cavedini et al., Psychiatry Res.78 (1998) 21-28; Menzies et al., Neurosci. Biobehav. Rev.32(3) (2008) 525-549], is caused by functional abnormalities in the pre-frontal regions. Particularly, patients are characterized by lower EEG complexity at both pre-frontal regions and right fronto-temporal locations. Our results are compatible with imaging studies that define OCD as a sub group of anxiety disorders exhibited a decreased complexity (such as anorexia nervosa [Toth et al., Int. J. Psychophysiol.51(3) (2004) 253-260] and panic disorder [Bob et al., Physiol. Res.55 (2006) S113-S119]).

Transcranial magnetic stimulation for treating depression in elderly patients

Purpose The aim of the study reported here was to examine the safety and effectiveness of high-frequency repetitive transcranial magnetic stimulation (rTMS) in elderly patients with depression. Patients and methods Sixty-five depressed elderly patients received rTMS over their left prefrontal cortex for 6 days per week, from Monday to Saturday, for 3 weeks. The rTMS intensity was set at 100% of the motor threshold and 25 Hz stimulation with a duration of 2 seconds and was delivered 20 times at 30-second intervals. A full course comprised an average of 1000 magnetic pulses. Depression was rated using the Hamilton Depression Rating Scale (HAMD) before and after treatment. Response was defined as a 50% reduction in HAMD score. Patients with HAMD scores < 8 were considered to be in remission. Results The mean HAMD score for the study group decreased from 21.94 ± 5.12 before treatment to 11.28 ± 4.56 after rTMS (P < 0.001). Following the treatment period, 58.46% of the study group demonstrated significant mood improvement, as indexed by a reduction of more than 50% on the HAMD score. Nineteen of these 38 patients attained remission (HAMD score < 8), while 41.54% of all study patients achieved a partial response. None of the patients had a worsened HAMD score at the end of the treatment. Treatment was generally well tolerated and no serious adverse effects were reported. Conclusion In this study, rTMS was found to be a safe, well-tolerated treatment, and a useful adjunctive treatment to medications in elderly treatment-resistant depressed patients. This study contributes to the existing evidence on the antidepressant effect of rTMS in the treatment of depression in patients over 60 years of age.

EEG power, cordance and coherence differences between unipolar and bipolar depression

INTRODUCTION Understanding the biological underpinnings of unipolar (UD) and bipolar depression (BD) is vital for avoiding inappropriate treatment through the misdiagnosis of bipolar patients in their first depressive episode. One plausible way to distinguish between UD and BD is to compare EEG brain dynamics to identify potential neurophysiological biomarkers. Here we aimed to test group differences in EEG power, cordance and coherence values between UD and BD. METHODS Twenty-five bipolar and 56 unipolar depression patients were recruited. Sociodemographic and clinical variables were collected in addition to resting state EEG. Data was analyzed with multivariate and repeated analyses of variance where parametric assumptions were met. RESULTS Accordingly, we did not find any differences in the EEG absolute power and frontal asymmetry indexes between UD and BD. Regarding cordance, significant group differences were observed in the right theta cordance values (p=0.031). Regarding coherence, BD patients (as compared to UD) exhibited greater central-temporal theta (p=0.003), and parietal-temporal alpha (p=0.007) and theta (p=0.001) coherence. Lastly, less alpha coherence in BD was present at right frontal-central (p=0.007) and central inter-hemispheric (p=0.019) regions. CONCLUSIONS Our results demonstrate that EEG cordance and coherence values have potential to discriminate between UD and BD. The loss of temporal synchronization in the frontal interhemispheric and right sided frontolimbic neuronal networks may be a unique feature that distinguishes between BD and UD.

Feature Selection and Classification of Electroencephalographic Signals An Artificial Neural Network and Genetic Algorithm Based Approach

Feature selection is an important step in many pattern recognition systems aiming to overcome the so-called curse of dimensionality. In this study, an optimized classification method was tested in 147 patients with major depressive disorder (MDD) treated with repetitive transcranial magnetic stimulation (rTMS). The performance of the combination of a genetic algorithm (GA) and a back-propagation (BP) neural network (BPNN) was evaluated using 6-channel pre-rTMS electroencephalographic (EEG) patterns of theta and delta frequency bands. The GA was first used to eliminate the redundant and less discriminant features to maximize classification performance. The BPNN was then applied to test the performance of the feature subset. Finally, classification performance using the subset was evaluated using 6-fold cross-validation. Although the slow bands of the frontal electrodes are widely used to collect EEG data for patients with MDD and provide quite satisfactory classification results, the outcomes of the proposed approach indicate noticeably increased overall accuracy of 89.12% and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.904 using the reduced feature set.

Efficacy of High-Frequency Repetitive Transcranial Magnetic Stimulation in Treatment-Resistant Depression

We examined the efficacy of high-frequency repetitive transcranial magnetic stimulation (rTMS) in 419 patients with treatment-resistant depression. The patients received daily sessions of rTMS over the left prefrontal cortex as an adjuvant to pharmacotherapy. The rTMS intensity was set at 100% of the motor threshold and 25 Hz stimulation, with train duration of 2 seconds delivered at 30-second intervals. A full course comprised 1000 magnetic pulses. Depression was rated using the Hamilton Depression Rating Scale (HAMD) before and after treatment. Response was defined as a 50% reduction in the HAMD score. Patients with HAMD scores of less than 8 were considered to be in remission. The mean HAMD score for the study group decreased from 22.59 ± 5.92 to 10.50 ± 5.83 (P < .001). After the treatment period, 268 (64%) out of 419 patients demonstrated significant mood improvements, as indexed by a reduction of more than 50% on the HAMD score. In addition, 140 patients (33.4%) attained remission (HAMD score <8); and 11 patients achieved a partial response. Treatment was generally well tolerated, and no serious adverse effects were reported. In conclusion, high-frequency (25 Hz) rTMS was well tolerated and found to be statistically and clinically effective in patients with treatment-resistant depression. This study contributed to the existing evidence of the antidepressant effect of rTMS in the treatment of depression.

A hybrid artificial intelligence method to classify trichotillomania and obsessive compulsive disorder

Classification of psychiatric disorders is becoming one of the major focuses of research using artificial intelligence approach. The combination of feature selection and classification methods generates satisfactory outcomes using biological biomarkers. The use of quantitative electroencephalography (EEG) cordance has enhanced the clinical utility of the EEG in psychiatric and neurological subjects. Trichotillomania (TTM), a kind of body focused repetitive behavior, is defined as a disorder characterized by repetitive hair pulling that results in noticeable hair loss. Phenomenological observations underline similarities between hair-pulling behaviors and compulsions seen in obsessive-compulsive disorder (OCD). Despite the recognized similarities between OCD and TTM, there is evidence of important differences between these two disorders. In order to dichotomize the subjects of each disorder, artificial intelligence approach was employed using quantitative EEG (QEEG) cordance values with 19 electrodes from 10 brain regions (prefrontal, frontocentral, central, left temporal, right temporal, left parietal, occipital, midline, left frontal and right frontal) in 4 frequency bands (delta, theta, alpha and beta). Machine learning methods, artificial neural networks (ANN), support vector machine (SVM), k-nearest neighbor (k-NN) and Naive Bayes (NB), were used in order to classify 39 TTM and 40 OCD patients. SVM, with its relatively better performance, was then combined with an improved ant colony optimization (IACO) approach in order to select more informative features with less iterations. The noteworthy performance of the hybrid approach underline that it is possible to discriminate OCD and TTM subjects with 81.04% overall accuracy. We used cordance as a biomarker combining absolute and relative power of EEG spectra.We used ACO for feature selection of 19 electrodes from 10 brain regions in 4 frequency bands.We used an improved ACO (IACO) to reduce computational complexity.We used SVM to classify trichotillomania and OCD subjects using their cordance values.We increased overall classification accuracy from 67.12% to 81.04% and increased AUC value from 0.698 to 0.816 decreasing used features from 40 to 13.

Decreased global field synchronization of multichannel frontal EEG measurements in obsessive-compulsive disorders

Global field synchronization (GFS) quantifies the synchronization level of brain oscillations. The GFS method has been introduced to measure functional synchronization of EEG data in the frequency domain. GFS also detects phase interactions between EEG signals acquired from all of the electrodes. If a considerable amount of local brain neurons has the same phase, these neurons appear to interact with each other. EEG data were received from 17 obsessive-compulsive disorder (OCD) patients and 17 healthy controls (HC). OCD effects on local and large-scale brain circuits were studied. Analysis of the GFS results showed significantly decreased values in the delta and full frequency bands. This research suggests that OCD causes synchronization disconnection in both the frontal and large-scale regions. This may be related to motivational, emotional and cognitive dysfunctions.

The impact of high-frequency repetitive transcranial magnetic stimulation on executive functioning of drug-free patients with treatment-resistant depression

ABSTRACT OBJECTIVES: The aim of the present study was to examine the impact of 25 Hz high-frequency repetitive transcranial magnetic stimulation (rTMS) on neuropsychological testing in treatment-resistant depression patients who were receiving no other concomitant medications for the treatment. METHODS: A total of 19 patients with treatment-resistant depression and 20 healthy controls were included in the study. A 25 Hz, 1000 pulse stimulation was set at 100% of the motor threshold and delivered 20 times for 2 s with 30 s intervals as 20 sessions to the depression group, and sham treatment was applied to the control group. Brief Psychiatric Rating Scale (BPRS), Stroop task, trail-making test (TMT), and Wisconsin card sorting test (WCST) were performed both before and 3 days after the rTMS treatment. Seventeen-item Hamilton Depression Rating Scale (HAMD) and Beck Depression Inventory (BDI) were obtained at baseline and after the rTMS treatment, as well. RESULTS: After the rTMS treatment, 52.6% (10 of 19 patients) met the response criteria (>50% improvement in HAMD score), with 5 (26.3%) patients meeting the criteria for remission of depression (HAMD score ≤ 8). None of the patients had a worsened HAMD score at the end of treatment. Reflecting the antidepressant effect of rTMS treatment, the mean BDI score, BPRS score, and Stroop task scores significantly differed following the treatment (p < .001, p < .001, and p = .017, respectively). TMT score difference did not reach statistical significance, whereas WCST scores showed significance in “correct responses” and “perseverative errors” categories (p < .05, and p < .05, respectively). None of the test scores at the end of rTMS treatment showed a significant difference when compared to baseline scores for the control group (p > .05, for all). CONCLUSIONS: Results suggest that rTMS can be used as a beneficial treatment option to ameliorate cognitive functions, especially executive functions. Patients had an improvement in depressive symptoms with the rTMS treatment without any concomitant medication, as well. Therefore, improvement in cognitive performance might be associated with improvement in depressive symptoms.

Classification of band-specific regional hemispheric connectivity in obsessive compulsive disorder

In the present study, inter-electrode hemispheric dependency has been estimated by using frequency, time and phase domain methods (Fourier Correlation, Wavelet Correlation (WC), Hilbert Correlation) for eight individual brain lobes (pre-frontal, anterio-frontal, central, occipital, parietal, posterio-frontal, anterio-temporal, posterio-temporal) in five frequency band activities (Delta (0.5–4 Hz), Theta (4–8 Hz), Alpha (8–16 Hz), Beta (16–32 Hz) and, Gamma (32–64 Hz)) for detection of obsessive compulsive disorder (OCD). For this purpose, patients and controls are classified by using non-linear Least-Squares Support-Vector-Machine with 10-fold cross validation for both eight features in each sub-band and single ban-specific feature at each lobe. The best classification performance (87,15% and 96, 65% in Beta and Gamma) is obtained for eight features estimated by using WC. In particular, single feature through WC has provided the relatively lower but useful classification performance in Beta (72, 34% at prefrontal, (72, 59% at occipital, 76, 39% at posterio-frontal, 70, 89% at anterio-temporal, 71,14% at posterio-temporal) and Gamma (71, 84% at prefrontal, 76, 39% at occipital, 76, 39% at posterio-frontal, 70, 89% at anterio-temporal, 71, 77% at posterio-temporal). In detail, OCD is found to be characterized by low hemispheric dependency in Gamma over cortex. In conclusion, OCD causes abnormalities at almost every hemispheric lobe. WC provides the best estimations to compute band specific asymmetry levels due to non-linear and non-stationary nature of EEG.

Seasonal mood changes in patients with obsessive–compulsive disorder

Obsessive-compulsive disorder (OCD) is frequently associated with mood disorders. However, to date, the co-occurrence of OCD with seasonal affective disorder (SAD) has not been investigated. We have aimed to estimate the prevalence of seasonal mood changes in patients with OCD and explore the contribution of seasonality in mood to the severity of OCD. The Seasonal Pattern Assessment Questionnaire (SPAQ), the Yale-Brown Obsession and Compulsion Scale (Y-BOCS), the Hamilton Depression Rating Scale-17 Items (HDRS-17), and the Beck Anxiety Inventory (BAI) were administered to patients with OCD (n=104) and controls (n=125). The degree of seasonality was measured by the Global Seasonality Score (GSS) calculated from the SPAQ. SAD and subsyndromal seasonal affective disorder (S-SAD) were significantly more prevalent in patients with OCD (53%, n=55) than controls (25%, n=31). When patients were assessed in the season in which SAD occurs, depression and compulsions (but not obsessions, OCD or anxiety) were more severe than those assessed in a season during which SAD does not occur. SAD frequently co-occurs with OCD and, given this co-occurrence, depression symptoms in some patients with OCD might be expected to vary on a seasonal basis.