Machine learning approaches and non-linear processing of extracted components in frontal region to predict rTMS treatment response in major depressive disorder

Abstract

Predicting the therapeutic result of repetitive transcranial magnetic stimulation (rTMS) treatment could save time and costs as ineffective treatment can be avoided. To this end, we presented a machine-learning-based strategy for classifying patients with major depression disorder (MDD) into responders (R) and nonresponders (NR) to rTMS treatment. Resting state EEG data were recorded using 32 electrodes from 88 MDD patients before treatment. Then, patients underwent 7 weeks of rTMS, and 46 of them responded to treatment. By applying Independent Component Analysis (ICA) on EEG, we identified the relevant brain sources as possible indicators of neural activity in the dorsolateral prefrontal cortex (DLPFC). This was served through estimating the generators of activity in the sensor domain. Subsequently, we added physiological information and placed certain terms and conditions to offer a far more realistic estimation than the classic EEG. Ultimately, those components mapped in accordance with the region of the DLPFC in the sensor domain were chosen. Features extracted from the relevant ICs time series included permutation entropy (PE), fractal dimension (FD), Lempel-Ziv Complexity (LZC), power spectral density, correlation dimension (CD), features based on bispectrum, frontal and prefrontal cordance, and a combination of them. The most relevant features were selected by a Genetic Algorithm (GA). For classifying two groups of R and NR, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) were applied to predict rTMS treatment response. To evaluate the performance of classifiers, a 10-fold cross-validation method was employed. A statistical test was used to assess the capability of features in differentiating R and NR for further research. EEG characteristics that can predict rTMS treatment response were discovered. The strongest discriminative indicators were EEG beta power, the sum of bispectrum diagonal elements in delta and beta bands, and CD. The Combined feature vector classified R and NR with a high performance of 94.31% accuracy, 92.85% specificity, 95.65% sensitivity, and 92.85% precision using SVM. This result indicates that our proposed method with power and nonlinear and bispectral features from relevant ICs time-series can predict the treatment outcome of rTMS for MDD patients only by one session pretreatment EEG recording. The obtained results show that the proposed method outperforms previous methods.

Baseline resting EEG measures differentiate rTMS treatment responders and non-responders

“…Our results indicated that responders to rTMS treatment had significantly less beta power than non-responders in baseline resting EEG recordings in both eyes-open and eyes-closed combined conditions. The result was similar to those reported by Hasanzadeh et al, which they reported high predictive accuracy of 91.3% for beta power 14 , and Ebrahimzadeh et al 24 , who also reported that beta power predicted response to rTMS treatment for depression. However, our result extends their results by demonstrating that the differences in beta power are present in both the resting eyes-closed condition and the eyes open resting state (in contrast to the previous research which only examined the eyes closed state) 14 .…”

“…The correlation dimension has also been used to differentiate people with and without depression with high accuracy compared to other non-linear features (i.e., detrended fluctuation analysis, Higuchi fractal and Lyapunov exponent) 23 . Interestingly, two recent studies using machine learning techniques found that beta power and correlation dimension accurately predicted clinical response to rTMS 14,24 , holding promise for potential clinical application. However, robust determination of an effect that might be used clinically requires replication in independent datasets.…”

Enhancing the accuracy of electroencephalogram-based emotion recognition through Long Short-Term Memory recurrent deep neural networks

“…EEG (electroencephalography) is a technique employed to monitor brain activity through the measurement of voltage changes generated by the collective neural activity within the brain ( San-Segundo et al, 2019 ; Dehghani et al, 2020 , 2022 , 2023 ; Sadjadi et al, 2021 ; Mosayebi et al, 2022 ). EEG serves as a reflection of the brain’s activity and functioning, and it finds diverse applications, including but not limited to emotion recognition ( Dehghani et al, 2011a , b , 2013 ; Ebrahimzadeh and Alavi, 2013 ; Nikravan et al, 2016 ; Soroush et al, 2017 , 2018a , b , 2019a , b , 2020 ; Bagherzadeh et al, 2018 ; Alom et al, 2019 ; Ebrahimzadeh et al, 2019a , b , c , 2021 , 2022 , 2023 ; Bagheri and Power, 2020 ; Karimi et al, 2022 ; Rehman et al, 2022 ; Yousefi et al, 2022 , 2023 ).…”