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

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.

Effect of nutritional supports on malnutrition, cognition, function and biomarkers of Alzheimer's disease: a systematic review.

AIM: To summarize the nutritional supplementation on biochemical parameters, cognition, function, Alzheimer's Disease (AD) biomarkers and nutritional status. MATERIALS AND METHODS: PubMed, Web of Science, Korean Journal Database, Russian Science Citation Index, SciELO Citation Index, Cochrane Library and Scopus databases were searched until 16 April 2021. 22.193 records in total were reached according to inclusion and exclusion criteria. Included Studies were evaluated through the Modified Jadad Scale and gathered under four subheadings. RESULTS: Forty-eight studies with a total of 7009 AD patients were included. Souvenaid, ONS (368 ± 69 kcal), Vegenat-med, 500 mg Resveratrol, ONS (200 mL) were effective nutritional supplements on promoting weight gain and protecting malnutrition status but showed conflicting results in Body mass index, Mid-Upper-Arm Circumference and Triceps Skin Fold Thickness. ONS and a lyophilized whole supplementation Vegenat-med intake made an increase in MNA scores. While all nutritional supplements showed controversial results in biochemical parameters but caused a decrease in Hcy levels which caused reductions in brain Aß plaque (increase serum Aß), p-Tau and cognitive improvement. Folic acid and vitamin D decreased serum APP, BACE1, BACE1mRNA. Resveratrol, Hericium erinaceus mycelia, vitamin D and Betaine supplements improved cognitive, functional prognosis and quality of life unlike other nutritional supplements had no effect on cognitive scales. CONCLUSIONS: Better designed trials with holistic measures are needed to investigate the effect of nutritional support on the AD biomarkers, cognitive status, biochemical parameters and functional states. Also, more beneficial results can be obtained by examining the simultaneous effects of nutritional supplements with larger sample groups.

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

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.

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

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.

Diagnostic Performance of Machine Learning Models Based on 18F-FDG PET/CT Radiomic Features in the Classification of Solitary Pulmonary Nodules.

Objectives: This study aimed to evaluate the ability of 18fluorine-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) radiomic features combined with machine learning methods to distinguish between benign and malignant solitary pulmonary nodules (SPN). Methods: Data of 48 patients with SPN detected on 18F-FDG PET/CT scan were evaluated retrospectively. The texture feature extraction from PET/CT images was performed using an open-source application (LIFEx). Deep learning and classical machine learning algorithms were used to build the models. Final diagnosis was confirmed by pathology and follow-up was accepted as the reference. The performances of the models were assessed by the following metrics: Sensitivity, specificity, accuracy, and area under the receiver operator characteristic curve (AUC). Results: The predictive models provided reasonable performance for the differential diagnosis of SPNs (AUCs ~0.81). The accuracy and AUC of the radiomic models were similar to the visual interpretation. However, when compared to the conventional evaluation, the sensitivity of the deep learning model (88% vs. 83%) and specificity of the classic learning model were higher (86% vs. 79%). Conclusion: Machine learning based on 18F-FDG PET/CT texture features can contribute to the conventional evaluation to distinguish between benign and malignant lung nodules.

Major Depressive Disorder Classification Based on Different Convolutional Neural Network Models: Deep Learning Approach.

The human brain is characterized by complex structural, functional connections that integrate unique cognitive characteristics. There is a fundamental hurdle for the evaluation of both structural and functional connections of the brain and the effects in the diagnosis and treatment of neurodegenerative diseases. Currently, there is no clinically specific diagnostic biomarker capable of confirming the diagnosis of major depressive disorder (MDD). Therefore, exploring translational biomarkers of mood disorders based on deep learning (DL) has valuable potential with its recently underlined promising outcomes. In this article, an electroencephalography (EEG)-based diagnosis model for MDD is built through advanced computational neuroscience methodology coupled with a deep convolutional neural network (CNN) approach. EEG recordings are analyzed by modeling 3 different deep CNN structure, namely, ResNet-50, MobileNet, Inception-v3, in order to dichotomize MDD patients and healthy controls. EEG data are collected for 4 main frequency bands (Δ, θ, α, and ß, accompanying spatial resolution with location information by collecting data from 19 electrodes. Following the pre-processing step, different DL architectures were employed to underline discrimination performance by comparing classification accuracies. The classification performance of models based on location data, MobileNet architecture generated 89.33% and 92.66% classification accuracy. As to the frequency bands, delta frequency band outperformed compared to other bands with 90.22% predictive accuracy and area under curve (AUC) value of 0.9 for ResNet-50 architecture. The main contribution of the study is the delineation of distinctive spatial and temporal features using various DL architectures to dichotomize 46 MDD subjects from 46 healthy subjects. Exploring translational biomarkers of mood disorders based on DL perspective is the main focus of this study and, though it is challenging, with its promising potential to improve our understanding of the psychiatric disorders, computational methods are highly worthy for the diagnosis process and valuable in terms of both speed and accuracy compared with classical approaches.

Entropy: A Promising EEG Biomarker Dichotomizing Subjects With Opioid Use Disorder and Healthy Controls.

Electroencephalography (EEG) signals are known to be nonstationary and often multicomponential signals containing information about the condition of the brain. Since the EEG signal has complex, nonlinear, nonstationary, and highly random behaviour, numerous linear feature extraction methods related to the short-time windowing technique do not satisfy higher classification accuracy. Since biosignals are highly subjective, the symptoms may appear at random in the time scale and very small variations in EEG signals may depict a definite type of brain abnormality it is valuable and vital to extract and analyze the EEG signal parameters using computers. The challenge is to design and develop signal processing algorithms that extract this subtle information and use it for diagnosis, monitoring, and treatment of subjects suffering from psychiatric disorders. For this purpose, finite impulse response-based filtering process was employed rather than traditional time and frequency domain methods. Finite impulse response subbands were analyzed further to obtain feature vectors of different entropy markers and these features were fed into a classifier namely multilayer perceptron. The performances of the classifiers were finally compared considering overall classification accuracies, area under receiver operating characteristic curve scores. Our results underline the potential benefit of the introduced methodology is promising and is to be treated as a clinical interface in dichotomizing substance use disorders subjects and for other medical data analysis studies. The results also indicate that entropy estimators can distinguish normal and opioid use disorder subjects. EEG data and theta frequency band have distinctive capability for almost all types of entropies while nonextensive Tsallis entropy outperforms compared with other types of entropies.

Use of EEG for Predicting Treatment Response to Transcranial Magnetic Stimulation in Obsessive Compulsive Disorder.

Aim. In this study we assessed the predictive power of quantitative EEG (qEEG) for the treatment response to right frontal transcranial magnetic stimulation (TMS) in obsessive compulsive disorder (OCD) using a machine learning approach. Method. The study included 50 OCD patients (35 responsive to TMS, 15 nonresponsive) who were treated with right frontal low frequency stimulation and identified retrospectively from Uskudar Unversity, NPIstanbul Brain Hospital outpatient clinic. All patients were diagnosed with OCD according to the DSM-IV-TR and DSM-5 criteria. We first extracted pretreatment band powers for patients. To explore the prediction accuracy of pretreatment EEG, we employed machine learning methods using an artificial neural network model. Results. Among 4 EEG bands, theta power successfully discriminated responsive from nonresponsive patients. Responsive patients had more theta powers for all electrodes as compared to nonresponsive patients. Discussion. qEEG could be helpful before deciding about treatment strategy in OCD. The limitations of our study are moderate sample size and limited number of nonresponsive patients and that treatment response was defined by clinicians and not by using a formal symptom measurement scale. Future studies with larger samples and prospective design would show the role of qEEG in predicting TMS response better.

Entropy-based feature extraction technique in conjunction with wavelet packet transform for multi-mental task classification.

Event-related mental task information collected from electroencephalography (EEG) signals, which are functionally related to different brain areas, possesses complex and non-stationary signal features. It is essential to be able to classify mental task information through the use in brain-computer interface (BCI) applications. This paper proposes a wavelet packet transform (WPT) technique merged with a specific entropy biomarker as a feature extraction tool to classify six mental tasks. First, the data were collected from a healthy control group and the multi-signal information comprised six mental tasks which were decomposed into a number of subspaces spread over a wide frequency spectrum by projecting six different wavelet basis functions. Later, the decomposed subspaces were subjected to three entropy-type statistical measure functions to extract the feature vectors for each mental task to be fed into a backpropagation time-recurrent neural network (BPTT-RNN) model. Cross-validated classification results demonstrated that the model could classify with 85% accuracy through a discrete Meyer basis function coupled with a Renyi entropy biomarker. The classifier model was finally tested in the Simulink platform to demonstrate the Fourier series representation of periodic signals by tracking the harmonic pattern. In order to boost the model performance, ant colony optimization (ACO)-based feature selection method was employed. The overall accuracy increased to 88.98%. The results underlined that the WPT combined with an entropy uncertainty measure methodology is both effective and versatile to discriminate the features of the signal localized in a time-frequency domain.

Binomial Logistic Regression and Artificial Neural Network Methods to Classify Opioid-Dependent Subjects and Control Group Using Quantitative EEG Power Measures.

Logistic regression (LR) and artificial neural networks (ANNs) are widely referred approaches in medical data classification studies. LR, a statistical fitting model, is suggested in medical problems because of its well-established methodology and coefficients contributing to the evaluation of clinical interpretations. ANNs are graphical models structured with node networks interconnected with arcs each of which is expressed in terms of weights discovered throughout the modeling process. Since ANNs have a complex structure with its layers and nodes in the layers, which provides ANNs the ability to model any data with complex relationships. Among the various models having origins in statistics and computer science, LR and ANNs have prevailed in the area of mass medical data classification. In this study, we introduce the 2 aforementioned approaches in order to generate a model dichotomizing 75 opioid-dependent patients and 59 control subjects from each other. Quantitative electroencephalography (QEEG) absolute power value of each electrode were calculated for 4 consecutive frequency bands namely delta, theta, alpha, and beta with the frequencies, 0.5 to 4, 4 to 8, 8 to 12, and 12 to 20 Hz, respectively. Significant independent variables contributing to the classification were underlined in LR while a feature selection (FS) method, genetic algorithm, is being applied to the ANN model to reveal more informative features. The performances of the classifiers were finally compared considering overall classification accuracies, area under receiver operating characteristic curve scores, and Gini coefficient. Although ANN-based classifier outperformed compared with LR, both models performed satisfactorily for absolute power measure in beta frequency band. Our results underline the potential benefit of the introduced methodology is promising and is to be treated as a clinical interface in dichotomizing substance use disorders subjects and for other medical data analysis studies.

Radiation shielding parameters of some antioxidants using Monte Carlo method.

In this paper, radiation shielding parameters such as mass attenuation coefficients and half value layer (HVL) of some antioxidants are investigated using MCNPX (version 2.4.0). The validation of the generated MCNPX simulation geometry for antioxidant structures is provided by comparing the results with standard WinXcom data for radiation mass attenuation coefficients of antioxidants. Very good agreement between WINXCOM and MCNPX was obtained. The results from the validated geometry were used to calculate the shielding parameters of different antioxidants. The radiation attenuation properties of each antioxidant were compared with each other. The results showed that, on average, the highest and the lowest radiation mass attenuation coefficients were observed on hesperidin and delphinidin chloride, respectively. It can be concluded that Monte Carlo simulation is a strong tool and an alternate method where experimental investigations are not possible and a standard simulation setup can be used in further studies for different biological structures. It can also be concluded that the obtained results from this study are very useful for radiology and radiotherapy applications where antioxidants are frequently used.

The Use of Quantitative EEG for Differentiating Frontotemporal Dementia From Late-Onset Bipolar Disorder.

The behavioral variant frontotemporal dementia (bvFTD) usually emerges with behavioral changes similar to changes in late-life bipolar disorder (BD) especially in the early stages. According to the literature, a substantial number of bvFTD cases have been misdiagnosed as BD. Since the literature lacks studies comparing differential diagnosis ability of electrophysiological and neuroimaging findings in BD and bvFTD, we aimed to show their classification power using an artificial neural network and genetic algorithm based approach. Eighteen patients with the diagnosis of bvFTD and 20 patients with the diagnosis of late-life BD are included in the study. All patients' clinical magnetic resonance imaging (MRI) scan and electroencephalography recordings were assessed by a double-blind method to make diagnosis from MRI data. Classification of bvFTD and BD from total 38 participants was performed using feature selection and a neural network based on general algorithm. The artificial neural network method classified BD from bvFTD with 76% overall accuracy only by using on EEG power values. The radiological diagnosis classified BD from bvFTD with 79% overall accuracy. When the radiological diagnosis was added to the EEG analysis, the total classification performance raised to 87% overall accuracy. These results suggest that EEG and MRI combination has more powerful classification ability as compared with EEG and MRI alone. The findings may support the utility of neurophysiological and structural neuroimaging assessments for discriminating the 2 pathologies.

Neural Network Based Response Prediction of rTMS in Major Depressive Disorder Using QEEG Cordance.

OBJECTIVE: The combination of repetitive transcranial magnetic stimulation (rTMS), a non-pharmacological form of therapy for treating major depressive disorder (MDD), and electroencephalogram (EEG) is a valuable tool for investigating the functional connectivity in the brain. This study aims to explore whether pre-treating frontal quantitative EEG (QEEG) cordance is associated with response to rTMS treatment among MDD patients by using an artificial intelligence approach, artificial neural network (ANN). METHODS: The artificial neural network using pre-treatment cordance of frontal QEEG classification was carried out to identify responder or non-responder to rTMS treatment among 55 MDD subjects. The classification performance was evaluated using k-fold cross-validation. RESULTS: The ANN classification identified responders to rTMS treatment with a sensitivity of 93.33%, and its overall accuracy reached to 89.09%. Area under Receiver Operating Characteristic (ROC) curve (AUC) value for responder detection using 6, 8 and 10 fold cross validation were 0.917, 0.823 and 0.894 respectively. CONCLUSION: Potential utility of ANN approach method can be used as a clinical tool in administering rTMS therapy to a targeted group of subjects suffering from MDD. This methodology is more potentially useful to the clinician as prediction is possible using EEG data collected before this treatment process is initiated. It is worth using feature selection algorithms to raise the sensitivity and accuracy values.

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.

Ant Colony Optimization Based Feature Selection Method for QEEG Data Classification.

OBJECTIVE: Many applications such as biomedical signals require selecting a subset of the input features in order to represent the whole set of features. A feature selection algorithm has recently been proposed as a new approach for feature subset selection. METHODS: Feature selection process using ant colony optimization (ACO) for 6 channel pre-treatment electroencephalogram (EEG) data from theta and delta frequency bands is combined with back propagation neural network (BPNN) classification method for 147 major depressive disorder (MDD) subjects. RESULTS: BPNN classified R subjects with 91.83% overall accuracy and 95.55% subjects detection sensitivity. Area under ROC curve (AUC) value after feature selection increased from 0.8531 to 0.911. The features selected by the optimization algorithm were Fp1, Fp2, F7, F8, F3 for theta frequency band and eliminated 7 features from 12 to 5 feature subset. CONCLUSION: ACO feature selection algorithm improves the classification accuracy of BPNN. Using other feature selection algorithms or classifiers to compare the performance for each approach is important to underline the validity and versatility of the designed combination.