SFShams Farhad

Shams Farhad

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shams Farhad has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • The effect of Motor Imagery on neurorehabilitation: A systematic review

    by May Fakhfakh, Shams Farhad, Baris Metin

    INPLASY202670027 The effect of Motor Imagery on neurorehabilitation: A systematic review Keywords: Motor Imagery; Neurorehabilitation; Neurological rehabilitation; Neurological disorders. Read and …

  • Investigation of Emotion Regulation Skills in Migraine Patients Using Electroencephalography (EEG) Method

    by Begüm Merve Çabuk, Baris Metin, Shams Farhad, Nevzat Tarhan

    Emotion regulation is essential for maintaining daily functioning. Previous studies indicate that individuals with migraine have difficulty identifying emotions and exhibit higher alexithymia scores. The P300 and N400 components, associated with attention and semantic processes, provide insights into neural changes during emotion regulation. The aim of this study is to investigate the relationship between migraine and emotion regulation by evaluating the P300 and N400 responses obtained during emotion regulation tasks. Participants included individuals with and without a migraine diagnosis. They were shown negative and neutral photographs, followed by instructions to enhance, suppress, or maintain their emotional responses. Afterward, they were asked to evaluate negative or neutral words. During EEG recording, event-related potentials were analyzed, focusing on the P300 and N400 components. P300 responses were recorded from the P3, P4, and Pz electrodes, while N400 responses were collected from FC1, FC2, and Cz electrodes. The migraine group generated a higher P300 response to neutral words compared to the control group. However, for negative words, the control group exhibited a higher P300 response than the migraineurs. According to the data from the FC1 channel, the migraine group produced a higher N400 response to negative words compared to the control group. In the FC2 channel, the migraine group showed a higher N400 response to neutral words than the control group. Although the effect of command did not differ between groups, the migraineurs showed inefficient attention allocation to negative stimuli and alterations in semantic processing of the emotional words depending on the electrode location.

  • Deep Learning-Based Artificial Intelligence Can Differentiate Treatment-Resistant and Responsive Depression Cases with High Accuracy

    by Sinem Zeynep Metin, Çağlar Uyulan, Shams Farhad, Türker Tekin Ergüzel, Ömer Türk, Barış Metin, Önder Çerezci, Nevzat Tarhan

    Background: Although there are many treatment options available for depression, a large portion of patients with depression are diagnosed with treatment-resistant depression (TRD), which is characterized by an inadequate response to antidepressant treatment. Identifying the TRD population is crucial in terms of saving time and resources in depression treatment. Recently several studies employed various methods on EEG datasets for automatic depression detection or treatment outcome prediction. However, no previous study has used the deep learning (DL) approach and EEG signals for detecting treatment resistance. Method: 77 patients with TRD, 43 patients with non-TRD, and 40 healthy controls were compared using GoogleNet convolutional neural network and DL on EEG data. Additionally, Class Activation Maps (CAMs) acquired from the TRD and non-TRD groups were used to obtain distinctive regions for classification. Results: GoogleNet classified the healthy controls and non-TRD group with 88.43%, the healthy controls and TRD subjects with 89.73%, and the TRD and non-TRD group with 90.05% accuracy. The external validation accuracy for the TRD-non-TRD classification was 73.33%. Finally, the CAM analysis revealed that the TRD group contained dominant features in class detection of deep learning architecture in almost all electrodes. Limitations: Our study is limited by the moderate sample size of clinical groups and the retrospective nature of the study. Conclusion: These findings suggest that EEG-based deep learning can be used to classify treatment resistance in depression and may in the future prove to be a useful tool in psychiatry practice to identify patients who need more vigorous intervention.


  • Neurocognition across bipolar disorder phases compared to healthy subjects

    by Elvan Ciftci, Shams Farhad, Baris Metin, Nevzat Tarhan

    Bipolar disorder (BD) is associated with cognitive abnormalities that may persist during euthymia and are linked to poor occupational performance. The cognitive differences between phases of BD are not well known. Therefore, a cross-sectional study with a relatively large population was conducted to evaluate the differences among BD phases in a wide range of neurocognitive parameters. Neuropsychological profile of 169 patients with a diagnosis of BD in manic, depressive, mixed, and euthymic phases between the ages of 18 and 70 years were compared to 45 healthy individuals' between ages of 24 and 69 years. The working memory (digit-span backward test), face recognition, executive functions (verbal fluency and Stroop test), face recognition, and visual and verbal memory (immediate and delayed recall) were evaluated. For BD subgroup analyses, we used the Kruskal-Wallis (KW) test. Then, for the comparison of BD versus healthy individuals, we used the Mann-Whitney U (MWU) test. Analyses based on non-parametric tests showed impairments in BD for all tests. There were no significant differences between phases. Cognitive performance in patients with BD appears to be mostly unrelated to the phase of the disorder, implying that cognitive dysfunction in BD is present even during remission.


  • Application of Hybrid DeepLearning Architectures for Identification of Individuals with Obsessive Compulsive Disorder Based on EEG Data

    by Shams Farhad, Sinem Zeynep Metin, Çağlar Uyulan, Sahar Taghi Zadeh Makouei, Barış Metin, Türker Tekin Ergüzel, Nevzat Tarhan

    Objective: Obsessive-compulsive disorder (OCD) is a highly common psychiatric disorder. The symptoms of this condition overlap and co-occur with those of other psychiatric illnesses, making diagnosis difficult. The availability of biomarkers could be useful for aiding in diagnosis, although prior neuroimaging studies were unable to provide such biomarkers. Method: In this study, patients with OCD were classified from healthy controls using 2 different hybrid deep learning models: one-dimensional convolutional neural networks (1DCNN) together with long-short term memory (LSTM) and gradient recurrent units (GRU), respectively. Results: Both models exhibited exceptional classification accuracies in cross-validation and external validation phases. The mean classification accuracies in the cross-validation stage were 90.88% and 85.91% for the 1DCNN-LSTM and 1DCNN-GRU models, respectively. The inferior frontal, temporal, and occipital electrodes were predominant in providing discriminative features. Conclusion: Our findings underscore the potential of hybrid deep learning architectures utilizing EEG data to effectively differentiate patients with OCD from healthy controls. This promising approach holds implications for advancing clinical decision-making by offering valuable insights into diagnostic markers for OCD.


  • Combined use of gray matter volume and neuropsychological test performance for classification of individuals with bipolar I disorder via artificial neural network method

    by Baris Metin, Shams Farhad, Turker Erguzel, Elvan Çiftçi, Nevzat Tarhan

    Diagnosis of patients with bipolar disorder may be challenging and delayed in clinical practice. Neuropsychological impairments and brain abnormalities are commonly reported in bipolar disorder (BD); therefore, they can serve as potential biomarkers of the disorder. Rather than relying on these predictors separately, using both structural and neuropsychiatric indicators together could be more informative and increase the accuracy of the automatic disorder classification. Yet, to our information, no Artificial Intelligence (AI) study has used multimodal data using both neuropsychiatric tests and structural brain changes to classify BD. In this study, we first investigated differences in gray matter volumes between patients with bipolar I disorder (n = 37) and healthy controls (n = 27). The results of the verbal and non-verbal memory tests were then compared between the two groups. Finally, we used the artificial neural network (ANN) method to model all the aforementioned values for group classification. Our voxel-based morphometry results demonstrated differences in the left anterior parietal lobule and bilateral insula gray matter volumes, suggesting a reduction of these brain structures in BD. We also observed a decrease in both verbal and non-verbal memory scores of individuals with BD (p < 0.001). The ANN model of neuropsychiatric test scores combined with gray matter volumes has classified the bipolar group with 89.5% accuracy. Our results demonstrate that when bilateral insula volumes are used together with neuropsychological test results the patients with bipolar I disorder and controls could be differentiated with very high accuracy. The findings imply that multimodal data should be used in AI studies as it better represents the multi-componential nature of the condition, thus increasing its diagnosability.

  • The Deep Learning Method Differentiates Patients with Bipolar Disorder from Controls with High Accuracy Using EEG Data

    by Barış Metin, Çağlar Uyulan, Türker Tekin Ergüzel, Shams Farhad, Elvan Çifçi, Ömer Türk, Nevzat Tarhan

    Background: Bipolar disorder (BD) is a mental disorder characterized by depressive and manic or hypomanic episodes. The complexity in the diagnosis of Bipolar disorder (BD) due to its overlapping symptoms with other mood disorders prompted researchers and clinicians to seek new and advanced techniques for the precise detection of Bipolar disorder (BD). One of these methods is the use of advanced machine learning algorithms such as deep learning (DL). However, no study of BD has previously adopted DL techniques using EEG signals. Method: EEG signals of 169 BD patients and 45 controls were cleaned from the artifacts and processed using two different DL methods: a one-dimensional convolutional neural network (1D-CNN) combined with the long-short term memory (LSTM) and a two-dimensional convolutional neural network (2D-CNN). Additionally, Class Activation Maps (CAMs) acquired from the bipolar and control groups were used to obtain distinctive regions to specify a particular class in an image. Results: Group identifications were confirmed with 95.91% overall accuracy through the 2D-CNN method, demonstrating very high sensitivity and lower specificity. Also, the overall accuracy obtained from the 1D-CNN + LSTM method was 93%. We also found that F4, C3, F7, and F8 electrode activities produce predominant features to detect the bipolar group. Conclusion: To our knowledge, this study used EEG-based DL analysis for the first time in BD. Our results suggest that the raw EEG-based DL algorithm can successfully differentiate individuals with BD from controls. Class Activation Map (CAM) analysis suggests that prefrontal changes are predominant in EEG data of patients with BD.


  • A Class Activation Map-Based Interpretable Transfer Learning Model for Automated Detection of ADHD from fMRI Data

    by Caglar Uyulan, Turker Tekin Erguzel, Omer Turk, Shams Farhad, Baris Metin, Nevzat Tarhan

    Automatic detection of Attention Deficit Hyperactivity Disorder (ADHD) based on the functional Magnetic Resonance Imaging (fMRI) through Deep Learning (DL) is becoming a quite useful methodology due to the curse of-dimensionality problem of the data is solved. Also, this method proposes an invasive and robust solution to the variances in data acquisition and class distribution imbalances. In this paper, a transfer learning approach, specifically ResNet-50 type pre-trained 2D-Convolutional Neural Network (CNN) was used to automatically classify ADHD and healthy children. The results demonstrated that ResNet-50 architecture with 10-k cross-validation (CV) achieves an overall classification accuracy of 93.45%. The interpretation of the results was done via the Class Activation Map (CAM) analysis which showed that children with ADHD differed from controls in a wide range of brain areas including frontal, parietal and temporal lobes.