A systematic review of EEG based automated schizophrenia classification through machine learning and deep learning.

The electroencephalogram (EEG) serves as an essential tool in exploring brain activity and holds particular importance in the field of mental health research. This review paper examines the application of artificial intelligence (AI), encompassing machine learning (ML) and deep learning (DL), for classifying schizophrenia (SCZ) through EEG. It includes a thorough literature review that addresses the difficulties, methodologies, and discoveries in this field. ML approaches utilize conventional models like Support Vector Machines and Decision Trees, which are interpretable and effective with smaller data sets. In contrast, DL techniques, which use neural networks such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), are more adaptable to intricate EEG patterns but require significant data and computational power. Both ML and DL face challenges concerning data quality and ethical issues. This paper underscores the importance of integrating various techniques to enhance schizophrenia diagnosis and highlights AI's potential role in this process. It also acknowledges the necessity for collaborative and ethically informed approaches in the automated classification of SCZ using AI.

Automated detection of myocardial infarction using binary Harry Hawks feature selection and ensemble KNN classifier.

Myocardial infarction (MI), referred to as a heart attack, is a life-threatening condition that happens due to blood clots, typically, blood flow to a portion of the heart muscle is blocked. The cardiac muscle may become permanently damaged if there is insufficient oxygen and blood flow to the affected area. It's crucial to treat MI as soon as possible because even a small delay might have serious effects. The primary diagnostic tool to track and identify the signs of MI is the electrocardiogram (ECG). The complexity of MI signals combined with noise makes it difficult for clinicians to make a precise and prompt diagnosis. It might be laborious and time-consuming to manually analyse an enormous quantity of ECG data. Therefore, techniques for autonomously diagnosing from the ECG data are required. There have been numerous research on the topic of MI espial, but the majority of the algorithms are cognitively intensive when working with empirical data. The current study suggests a unique method for the efficient and reliable identification of MI. We employed circulant singular spectrum analysis (CSSA) for baseline wander removal, a 4-stage Savitzky-Golay (SG) filter to expunge powerline interference from the ECG signal and segmented in the preprocessing stage. Thus segmented ECG has been decomposed using CSSA, entropy based features are extracted. The best features are selected by using binary Harris hawk optimization (BHHO) and to machine learning (ML) classifiers like Naive Bayes, Decision tree, K-nearest neighbor (KNN), Support vector machine (SVM), and Ensemble subspace KNN. Our suggested method has been examined from both class as well as subject oriented perspectives. While the subject-oriented technique uses data from one patient for testing while using data from the other subjects for training, the class-wise strategy divides data as test data as well as training data regardless of subjects. We succeeded in achieving accuracy (Ac%) of 99.8, sensitivity (Se%) of 99, and 100 specificity (Sp%) under the class-oriented approach. Similarly, for the subject wise strategy we achieved a mean Ac%, Se%, and Sp% of 85.2, 83.1, and 84.5, respectively.

Multi-stage glaucoma classification using pre-trained convolutional neural networks and voting-based classifier fusion.

Aim: To design an automated glaucoma detection system for early detection of glaucoma using fundus images. Background: Glaucoma is a serious eye problem that can cause vision loss and even permanent blindness. Early detection and prevention are crucial for effective treatment. Traditional diagnostic approaches are time consuming, manual, and often inaccurate, thus making automated glaucoma diagnosis necessary. Objective: To propose an automated glaucoma stage classification model using pre-trained deep convolutional neural network (CNN) models and classifier fusion. Methods: The proposed model utilized five pre-trained CNN models: ResNet50, AlexNet, VGG19, DenseNet-201, and Inception-ResNet-v2. The model was tested using four public datasets: ACRIMA, RIM-ONE, Harvard Dataverse (HVD), and Drishti. Classifier fusion was created to merge the decisions of all CNN models using the maximum voting-based approach. Results: The proposed model achieved an area under the curve of 1 and an accuracy of 99.57% for the ACRIMA dataset. The HVD dataset had an area under the curve of 0.97 and an accuracy of 85.43%. The accuracy rates for Drishti and RIM-ONE were 90.55 and 94.95%, respectively. The experimental results showed that the proposed model performed better than the state-of-the-art methods in classifying glaucoma in its early stages. Understanding the model output includes both attribution-based methods such as activations and gradient class activation map and perturbation-based methods such as locally interpretable model-agnostic explanations and occlusion sensitivity, which generate heatmaps of various sections of an image for model prediction. Conclusion: The proposed automated glaucoma stage classification model using pre-trained CNN models and classifier fusion is an effective method for the early detection of glaucoma. The results indicate high accuracy rates and superior performance compared to the existing methods.

EEG rhythm based emotion recognition using multivariate decomposition and ensemble machine learning classifier.

Recently, electroencephalogram (EEG) signals have shown great potential to recognize human emotions. The goal of effective computing is to assist computers in understanding various types of emotions via human-computer interaction (HCI). Multichannel EEG signals are used to measure the electrical activity of the brain in space and time. Automated emotion recognition using multichannel EEG signals is an interesting area of cognitive neuroscience and affective computing research. This research proposes EEG multichannel rhythmic features and ensemble machine learning (EML) classifiers with leave-one-subject-out cross-validation (LOSOCV) for automatic emotion classification from multichannel EEG recordings. Multivariate fast iterative filtering (MvFIF) is used to assess the EEG rhythm sequences. EEG rhythms delta(δ), theta(θ), alpha(α), beta(ß), and gamma(γ) are separated based on the mean frequency of the EEG rhythm sequence. Three Hjorth parameters and nine entropy features were extracted from multichannel EEG rhythms. Extracted features are selected using the minimum redundancy maximum relevance (mRMR) approach. The experimental design was performed on two emotional datasets (GAMEEMO and DREAMER). The validation showed that gamma rhythm multichannel features with EML-based subspace K-nearest neighbor (SS KNN) were as high as 93.5%-99.8%, achieving high classification accuracy. The comparisons of δ, θ, α, ß, and γ rhythms with EML, support vector machine (SVM), and artificial neural network (ANN) were performed. we also analyzed multi-class emotions (HVHA, HVLA, LVHA, LVLA) with an ensemble-based bagging tree on gamma rhythm. It provides a novel solution for multichannel rhythm-specific features in EEG data analysis.

Circulant Singular Spectrum Analysis and Discrete Wavelet Transform for Automated Removal of EOG Artifacts from EEG Signals.

Background: Portable electroencephalogram (EEG) systems are often used in health care applications to record brain signals because their ease of use. An electrooculogram (EOG) is a common, low frequency, high amplitude artifact of the eye blink signal that might confuse disease diagnosis. As a result, artifact removal approaches in single EEG portable devices are in high demand. Materials: Dataset 2a from the BCI Competition IV was employed. It contains the EEG data from nine subjects. To determine the EOG effect, each session starts with 5 min of EEG data. This recording lasted for two minutes with the eyes open, one minute with the eyes closed, and one minute with eye movements. Methodology: This article presents the automated removal of EOG artifacts from EEG signals. Circulant Singular Spectrum Analysis (CiSSA) was used to decompose the EOG contaminated EEG signals into intrinsic mode functions (IMFs). Next, we identified the artifact signal components using kurtosis and energy values and removed them using 4-level discrete wavelet transform (DWT). Results: The proposed approach was evaluated on synthetic and real EEG data and found to be effective in eliminating EOG artifacts while maintaining low frequency EEG information. CiSSA-DWT achieved the best signal to artifact ratio (SAR), mean absolute error (MAE), relative root mean square error (RRMSE), and correlation coefficient (CC) of 1.4525, 0.0801, 18.274, and 0.9883, respectively. Comparison: The developed technique outperforms existing artifact suppression techniques according to performance measures. Conclusions: This advancement is important for brain science and can contribute as an initial pre-processing step for research related to EEG signals.

Artificial intelligence based approach for categorization of COVID-19 ECG images in presence of other cardiovascular disorders.

Coronavirus disease (COVID-19) is a class of SARS-CoV-2 virus which is initially identified in the later half of the year 2019 and then evolved as a pandemic. If it is not identified in the early stage then the infection and mortality rates increase with time. A timely and reliable approach for COVID-19 identification has become important in order to prevent the disease from spreading rapidly. In recent times, many methods have been suggested for the detection of COVID-19 disease have various flaws, to increase diagnosis performance, fresh investigations are required. In this article, automatically diagnosing COVID-19 using ECG images and deep learning approaches like as Visual Geometry Group (VGG) and AlexNet architectures have been proposed. The proposed method is able to classify between COVID-19, myocardial infarction, normal sinus rhythm, and other abnormal heart beats using Lead-II ECG image only. The efficacy of the technique proposed is validated by using a publicly available ECG image database. We have achieved an accuracy of 77.42% using Alexnet model and 75% accuracy with the help of VGG19 model.

QRS complex detection using stationary wavelet transform and adaptive thresholding.

Purpose. Electrocardiogram (ECG) signal is a record of the electrical activity of the heart and contains important clinical data about cardiovascular-related misfunctioning. The goal of the present work is to develop an improved QRS detection algorithm for the detection of heart abnormalities.Methods. In this present work stationary wavelet transforms (SWT) based method has been proposed for precise detection of QRS complex with 'sym2' mother wavelet. The stationary wavelet transform is a systematic mathematical tool to decompose the signal without downsampling using scale analysis and provides high detection of QRS complex and accurate localization of signal components. In the proposed method four level of decomposition is applied and the initial thresholding value is computed by the maximum amplitude of scale one at level four in SWT coefficients without the zero-crossing amplitude detection method. The multi-layered dynamic thresholding method has been applied to detect the true R-peak values and locate the QRS complex in the ECG signal.Results. For evaluation of results, the presented methodology is assessed on MIT-BIH, QTDB, and Noise stress test databases. In MIT-BIH, the sensitivity = 99.88%, positive predictivity = 99.93%, accuracy = 99.80% and detection error rate = 0.18% is achieved. In NSTD database, sensitivity = 97.46%, positive predictivity = 94.20%, accuracy = 91.95% and detection error rate = 8.47% and in QTDB, sensitivity = 99.95%, positive predictivity = 99.90%, accuracy = 99.71% and detection error rate = 0.16% is executed.Conclusion. In the presented proposed methodology, the computation complexity is low and exhibits a simple technique rather than an empirical approach. The proposed technique corroborates the performance for the detection of QRS complex with improved accuracy.

Short duration Vectorcardiogram based inferior myocardial infarction detection: class and subject-oriented approach.

Myocardial infarction (MI) happens when blood stops circulating to an explicit segment of the heart causing harm to the heart muscles. Vectorcardiography (VCG) is a technique of recording direction and magnitude of the signals that are produced by the heart in a 3-lead representation. In this work, we present a technique for detection of MI in the inferior portion of heart using short duration VCG signals. The raw signal was pre-processed using the median and Savitzky-Golay (SG) filter. The Stationary Wavelet Transform (SWT) was used for time-invariant decomposition of the signal followed by feature extraction. The selected features using minimum-redundancy-maximum-relevance (mRMR) based feature selection method were applied to the supervised classification methods. The efficacy of the proposed method was assessed under both class-oriented and a more real-life subject-oriented approach. An accuracy of 99.14 and 89.37% were achieved respectively. Results of the proposed technique are better than existing state-of-art methods and used VCG segment is shorter. Thus, a shorter segment and a high accuracy can be helpful in the automation of timely and reliable detection of MI. The satisfactory performance achieved in the subject-oriented approach shows reliability and applicability of the proposed technique.

A novel and lightweight P, QRS, and T peaks detector using adaptive thresholding and template waveform.

Accurate detection of key components in an electrocardiogram (ECG) plays a vital role in identifying cardiovascular diseases. In this work, we proposed a novel and lightweight P, QRS, and T peaks detector using adaptive thresholding and template waveform. In the first stage, we proposed a QRS complex detector, which utilises a novel adaptive thresholding process followed by threshold initialisation. Moreover, false positive QRS complexes were removed using the kurtosis coefficient computation. In the second stage, the ECG segment from the S wave point to the Q wave point was extracted for clustering. The template waveform was generated from the cluster members using the ensemble average method, interpolation, and resampling. Next, a novel conditional thresholding process was used to calculate the threshold values based on the template waveform morphology for P and T peaks detection. Finally, the min-max functions were used to detect the P and T peaks. The proposed technique was applied to the MIT-BIH arrhythmia database (MIT-AD) and the QT database for QRS detection and validation. Sensitivity (Se%) values of 99.81 and 99.90 and positive predictivity (+P%) values of 99.85 and 99.94 were obtained for the MIT-AD and QT database for QRS complex detection, respectively. Further, we found that Se% = 96.50 and +P% = 96.08 for the P peak detection, Se% = 100 and +P% = 100 for the R peak detection, and Se% = 99.54 and +P% = 99.68 for the T peak detection when using the manually annotated QT database. The proposed technique exhibits low computational complexity and can be implemented on low-cost hardware, since it is based on simple decision rules rather than a heuristic approach.

Exploratory data analysis based efficient QRS-complex detection technique with minimal computational load.

Detection of QRS-complex in the electrocardiogram (ECG) plays a decisive role in cardiac disorder detection. We face many challenges in terms of powerline interference, baseline drift, and abnormal varying peaks. In this work, we propose an exploratory data analysis (EDA) based efficient QRS-complex detection technique with minimal computational load. This paper includes median and moving average filter for pre-processing of the ECG. The peak of filtered ECG is enhanced to third power of the signal. The root mean square (rms) of the signal is estimated for the decision making rule. This technique adapted the new concept for isoelectric line identification and EDA based QRS-complex detection. In this paper, total 10,70,981 beats were used for validation from MIT BIH-Arrhythmia Database (MIT-BIH), Fantasia Database (FDB), European ST-T database (ESTD), a self recorded dataset (SDB), and fetal ECG database (FTDB). Overall sensitivity of 99.65 % and positive predictivity rate of 99.84 % have been achieved. The proposed technique doesn't require selection, setting, and training for QRS-complex detection. Thus, this paper presents a QRS-complex detection technique based on simple decision rules.

Novel T-wave Detection Technique with Minimal Processing and RR-Interval Based Enhanced Efficiency.

PURPOSE: T-wave in electrocardiogram (ECG) is a vital wave component and has potential of diagnosing various cardiac disorders. The present work proposes a novel technique for T-wave peak detection using minimal pre-processing and simple root mean square based decision rule. METHODS: The technique uses a two-stage median filter and a Savitzky-Golay smoothing filter for pre-processing. P-QRS-complex is removed from the filtered ECG, and T-wave is left as the most prominent wave segment, which can be detected using a root mean square based adaptive threshold. An RR-interval based T-wave peak correction strategy has been proposed which can handle the challenges of morphological variations in the T-wave, thus increases the detection accuracy. RESULTS: The proposed technique has been substantiated on a standard QT-database. The detection sensitivity = 97.01%, positive predictivity = 99.61%, detection error rate = 3.36%, and accuracy = 96.66% have been achieved. CONCLUSIONS: A T-wave detection technique requiring minimal pre-processing and with simple decision rule has been designed. The noticeably high positive predictivity rate of the proposed technique shows its efficiency to detect T-wave peak.