The role of beat-by-beat cardiac features in machine learning classification of ischemic heart disease (IHD) in magnetocardiogram (MCG).

Cardiac electrical changes associated with ischemic heart disease (IHD) are subtle and could be detected even in rest condition in magnetocardiography (MCG) which measures weak cardiac magnetic fields. Cardiac features that are derived from MCG recorded from multiple locations on the chest of subjects and some conventional time domain indices are widely used in Machine learning (ML) classifiers to objectively distinguish IHD and control subjects. Most of the earlier studies have employed features that are derived from signal-averaged cardiac beats and have ignored inter-beat information. The present study demonstrates the utility of beat-by-beat features to be useful in classifying IHD subjects (n = 23) and healthy controls (n = 75) in 37-channel MCG data taken under rest condition of subjects. The study reveals the importance of three features (out of eight measured features) namely, the field map angle (FMA) computed from magnetic field map, beat-by-beat variations of alpha angle in the ST-T region and T wave magnitude variations in yielding a better classification accuracy (92.7 %) against that achieved by conventional features (81 %). Further, beat-by-beat features are also found to augment the accuracy in classifying myocardial infarction (MI) Versus control subjects in two public ECG databases (92 % from 88 % and 94 % from 77 %). These demonstrations summarily suggest the importance of beat-by-beat features in clinical diagnosis of ischemia.

A method for noninvasive beat-by-beat visualization of His bundle signals.

BACKGROUND: Invasive recording of His bundle signals (HBS) in electrophysiological study (EPS) is important in determining HV interval, the time taken to activate the ventricles from the His bundle. Noninvasive surface measurements of HBS are attempted by averaging typically 100-200 cardiac cycles of ECG time series in body surface potential mapping (BSPM) and in magnetocardiography (MCG) which records weak cardiac magnetic fields by highly sensitive detectors. However, noninvasive beat-by-beat extraction of HBS is challenged by ramp-like atrial signals and noise in PR segment of the cardiac cycle. METHODS: By making use of a signal-averaged trace showing prominent HBS as a guide trace, we developed a method combining interval-dependent wavelet thresholding (IDWT) and signal space projection (SSP) technique to eliminate artifacts from single beats. The method was applied on MCG recorded on 21 subjects with known HV intervals based on EPS and noninvasive signal-averaging, including five subjects with BSPM recorded subsequently. The method was also applied on stress-MCG of a subject featuring autonomic dynamics. RESULTS: HBS could be extracted from 19 out of 21 subjects by signal-averaging whose timing differed from EPS between -8 and 11 ms as tested by 2 observers. HBS in single beats were seen as aligned patterns in inter-beat contours and were appreciable in stress-MCG and conspicuous than BSPM. The performance of the method was evaluated on simulated and measured MCG to be adequate if the signal-to-noise ratio was at least 20 dB. CONCLUSIONS: These results suggest the use of this method for noninvasive assessments on HBS.

EEG power spectrum analysis for schizophrenia during mental activity.

Cognitive dysfunction is a core defect for schizophrenia subjects. This is due to structural and functional abnormalities of the brain which can be determined using Electroencephalogram (EEG). The objective of this study is to analyze EEG in patients with schizophrenia using power spectral density during mental activity. The subjects included in this study are 52 schizophrenia subjects and 29 Normal subjects. EEG is recorded under resting condition and during mental activity. Two modified odd ball paradigms are designed to stimulate mental activity and named as stimulus 1 and stimulus 2. EEG signal is filtered using FIR band pass filter to extract delta, theta, alpha, and beta band EEG. This method measures powers of each band using Welch power spectral density method called absolute power. The absolute power of alpha band is low and beta band is high for schizophrenia subjects compared to normal subjects during rest and two stimuli. Student's t-test is used to find the significant features (p < 0.05) at each recording condition. The significant features from each recording condition are used to classify Schizophrenia using both BPN and SVM classifier. SVM classifier is produced maximum sensitivity of 91% when features from all recording conditions are combined together. Thus this work concludes that the mental activity EEG supports for classifying Schizophrenia from normal and hence absolute band powers can be used as features to identify Schizophrenia.

Optic nerve head segmentation using fundus images and optical coherence tomography images for glaucoma detection.

BACKGROUND: Glaucoma is a common causes of blindness. The associated elevation in intra ocular pressure leads to progressive degeneration of the optic nerve and resultant structural changes with functional failure of the visual field. Since, glaucoma is asymptomatic in the early stages and the associated vision loss is irreparable, its early detection and timely medical treatment is essential to prevent further visual damage. OBJECTIVE: This paper presents a novel method for glaucoma detection using digital fundus image and optical coherence tomography (OCT) image. METHOD: The first section focuses on the features such as cup to disc ratio (CDR) and the inferior superior nasal temporal (ISNT) ratio which were obtained from fundus images.The above features were used for classifying the normal and glaucoma condition using back propagation neural network (BPN) and Support Vector Machine (SVM) classifiers. In the second part of the article, features such as CDR and two novel features, cup depth and retinal thickness were obtained from the OCT image. These features were evaluated by the BPN and SVM classifier. RESULTS AND CONCLUSION: The combined features from fundus and OCT images were analyzed. The system proposed here is able to classify glaucoma automatically. The accuracy of BPN and SVM Classifiers was 90.76% and 96.92% respectively.