Feature Selection Using F-statistic Values for EEG Signal Analysis

Automatic classification of seizure and seizure-free EEG signals based on phase space reconstruction features

Epilepsy is a type of brain disorder triggered by an abrupt electrical imbalance of neuronal networks. An electroencephalogram (EEG) is a diagnostic tool to capture the underlying brain mechanisms and detect seizure onset in epileptic patients. To detect seizures, neurologists need to manually monitor EEG recordings for long periods, which is challenging and susceptible to errors depending on expertise and experience. Therefore, automatic identification of seizure and seizure-free EEG signals becomes essential. This study introduces a method based on the features extracted from the phase space reconstruction for classifying seizure and seizure-free EEG signals. The computed features are derived from the elliptical area and interquartile range of the Euclidean distance by varying percentage values of data points ranging from 50 to 100%. We consider two public datasets and evaluate these features in each EEG epoch that includes the healthy, interictal, preictal, and ictal stages of epileptic subjects, utilizing the K-nearest neighbor classifier for classification. Results show that the features have higher values during the seizure than the seizure-free EEG signals and healthy subjects. Furthermore, the proposed features can effectively discriminate seizure EEG signals from the seizure-free and normal subjects with 100% accuracy, sensitivity, and specificity in both datasets. Likewise, the classification between the preictal stage and seizure EEG signals attains 98% accuracy. Overall, the reconstructed phase space features significantly enhance the accuracy of detecting epileptic EEG signals compared with existing methods. This advancement holds great potential in assisting neurologists in swiftly and accurately diagnosing epileptic seizures from EEG signals.

Performance investigation of epilepsy detection from noisy EEG signals using base-2-meta stacking classifier

Epilepsy is a chronic neurological disease, characterized by spontaneous, unprovoked, recurrent seizures that may lead to long-term disability and premature death. Despite significant efforts made to improve epilepsy detection clinically and pre-clinically, the pervasive presence of noise in EEG signals continues to pose substantial challenges to their effective application. In addition, discriminant features for epilepsy detection have not been investigated yet. The objective of this study is to develop a hybrid model for epilepsy detection from noisy and fragmented EEG signals. We hypothesized that a hybrid model could surpass existing single models in epilepsy detection. Our approach involves manual noise rejection and a novel statistical channel selection technique to detect epilepsy even from noisy EEG signals. Our proposed Base-2-Meta stacking classifier achieved notable accuracy (0.98 ± 0.05), precision (0.98 ± 0.07), recall (0.98 ± 0.05), and F1 score (0.98 ± 0.04) even with noisy 5-s segmented EEG signals. Application of our approach to the specific problem like detection of epilepsy from noisy and fragmented EEG data reveals a performance that is not only superior to others, but also is translationally relevant, highlighting its potential application in a clinic setting, where EEG signals are often noisy or scanty. Our proposed metric DF-A (Discriminant feature-accuracy), for the first time, identified the most discriminant feature with models that give A accuracy or above (A = 95 used in this study). This groundbreaking approach allows for detecting discriminant features and can be used as potential electrographic biomarkers in epilepsy detection research. Moreover, our study introduces innovative insights into the understanding of these features, epilepsy detection, and cross-validation, markedly improving epilepsy detection in ways previously unavailable.

Multimodal Early Birth Weight Prediction Using Multiple Kernel Learning

In this work, a novel multimodal learning approach for early prediction of birth weight is presented. Fetal weight is one of the most relevant indicators in the assessment of fetal health status. The aim is to predict early birth weight using multimodal maternal-fetal variables from the first trimester of gestation (Anthropometric data, as well as metrics obtained from Fetal Biometry, Doppler and Maternal Ultrasound). The proposed methodology starts with the optimal selection of a subset of multimodal features using an ensemble-based approach of feature selectors. Subsequently, the selected variables feed the nonparametric Multiple Kernel Learning regression algorithm. At this stage, a set of kernels is selected and weighted to maximize performance in birth weight prediction. The proposed methodology is validated and compared with other computational learning algorithms reported in the state of the art. The obtained results (absolute error of 234 g) suggest that the proposed methodology can be useful as a tool for the early evaluation and monitoring of fetal health status through indicators such as birth weight.

Left ventricular hypertrophy detection using electrocardiographic signal

Left ventricular hypertrophy (LVH) indicates subclinical organ damage, associating with the incidence of cardiovascular diseases. From the medical perspective, electrocardiogram (ECG) is a low-cost, non-invasive, and easily reproducible tool that is often used as a preliminary diagnosis for the detection of heart disease. Nowadays, there are many criteria for assessing LVH by ECG. These criteria usually include that voltage combination of RS peaks in multi-lead ECG must be greater than one or more thresholds for diagnosis. We developed a system for detecting LVH using ECG signals by two steps: firstly, the R-peak and S-valley amplitudes of the 12-lead ECG were extracted to automatically obtain a total of 24 features and ECG beats of each case (LVH or non-LVH) were segmented; secondly, a back propagation neural network (BPN) was trained using a dataset with these features. Echocardiography (ECHO) was used as the gold standard for diagnosing LVH. The number of LVH cases (of a Taiwanese population) identified was 173. As each ECG sequence generally included 8 to 13 cycles (heartbeats) due to differences in heart rate, etc., we identified 1466 ECG cycles of LVH patients after beat segmentation. Results showed that our BPN model for detecting LVH reached the testing accuracy, precision, sensitivity, and specificity of 0.961, 0.958, 0.966 and 0.956, respectively. Detection performances of our BPN model, on the whole, outperform 7 methods using ECG criteria and many ECG-based artificial intelligence (AI) models reported previously for detecting LVH.

On the Treatment and Diagnosis of Attention Deficit Hyperactivity Disorder with EEG Assistance

Attention deficit hyperactivity disorder (ADHD) is a mental disorder most notable in children. The disease may affect the ability to focus and cause a physical and mental restlessness and risky behavior. Recommended treatment consists of stimulant administration and behavioral therapy. However, medicating children is problematic since there are indications that brain development is affected by ADHD medication agents. Therefore, behavioral therapy is the preferred approach in ADHD treatment for children. In order to monitor and optimize the success of such behavioral therapies, neuro-feedback methods can be used. The most notable technology used in such methods is Electroencephalography (EEG). In this article, an overview of the pathology of ADHD, EEG and its usage as a diagnostic and therapeutic tool in the context of ADHD is given. Based on that knowledge, novel EEG measurement modes, new development principles, and system on chip implementations are presented and discussed.

Research on Mental Stress Recognition of Depressive Disorders in Patients With Androgenic Alopecia Based on Machine Learning and Fuzzy K-Means Clustering

Under the new trend of industry 4.0 software-defined network, the value of meta heuristic algorithm was explored in the recognition of depression in patients with androgenic alopecia (AGA), and there was an analysis on the effect of comprehensive psychological interventions in the rehabilitation of AGA patients. Based on the meta heuristic algorithm, the Filter and Wrapper algorithms were combined in this study to form a new feature selection algorithm FAW-FS. Then, the classification accuracy of FAW-FS and the ability to identify depression disorders were verified under different open data sets. 54 patients with AGA who went to the Medical Cosmetic Center of Tongji Hospital were selected as the research objects and rolled into a control group (routine psychological intervention) and an intervention group (routine + comprehensive psychological interventions) according to different psychological intervention methods, with 27 cases in each group. The differences of the self-rating anxiety scale (SAS), self-rating depression scale (SDS), Hamilton depression scale (HAMD), and physical, psychological, social, and substance function scores before and after intervention were compared between the two groups of AGA patients, and the depression efficacy and compliance of the two groups were analyzed after intervention. The results showed that the classification accuracy of FAW-FS algorithm was the highest in logistic regression (LR), decision tree (DT), K-nearest neighbor (KNN) algorithm, support vector machine (SVM) algorithm, and random forest (RF) algorithm, which was 80.87, 79.24, 80.42, 83.07, and 81.45%, respectively. The LR algorithm had the highest feature selection accuracy of 82.94%, and the classification accuracy of depression disorder in RF algorithm was up to 73.01%. Besides, the SDS, SAS, and HAMD scores of the intervention group were lower sharply than the scores of the control group (p < 0.05). The physical function, psychological function, social function, and substance function scores of the intervention group were higher markedly than those of the control group (p < 0.05). In addition, the proportions of cured, markedly effective, total effective, full compliance, and total compliance patients in the intervention group increased obviously in contrast to the proportions of the control group (p < 0.05). Therefore, it indicated that the FAW-FS algorithm established in this study had significant advantages in the recognition of depression in AGA patients, and comprehensive psychological intervention had a positive effect in the rehabilitation of depression in AGA patients.

Personalized EEG Feature Selection for Low-Complexity Seizure Monitoring

Approximately, one third of patients with epilepsy are refractory to medical therapy and thus can be at high risk of injuries and sudden unexpected death. A low-complexity electroencephalography (EEG)-based seizure monitoring algorithm is critically important for daily use, especially for wearable monitoring platforms. This paper presents a personalized EEG feature selection approach, which is the key to achieve a reliable seizure monitoring with a low computational cost. We advocate a two-step, personalized feature selection strategy to enhance monitoring performances for each patient. In the first step, linear discriminant analysis (LDA) is applied to find a few seizure-indicative channels. Then in the second step, least absolute shrinkage and selection operator (LASSO) method is employed to select a discriminative subset of both frequency and time domain features (spectral powers and entropy). A personalization strategy is further customized to find the best settings (number of channels and features) that yield the highest classification scores for each subject. Experimental results of analyzing 23 subjects in CHB-MIT database are quite promising. We have achieved an average F-1 score of 88% with excellent sensitivity and specificity using not more than 7 features extracted from at most 3 channels.