Phase Space Reconstruction Based CVD Classifier Using Localized Features

Abstract

This paper proposes a generalized Phase Space Reconstruction (PSR) based Cardiovascular Diseases (CVD) classification methodology by exploiting the localized features of the ECG. The proposed methodology first extracts the ECG localized features including PR interval, QRS complex, and QT interval from the continuous ECG waveform using features extraction logic, then the PSR technique is applied to get the phase portraits of all the localized features. Based on the cleanliness and contour of the phase portraits CVD classification will be done. This is first of its kind approach where the localized features of ECG are being taken into considerations unlike the state-of-art approaches, where the entire ECG beats have been considered. The proposed methodology is generic and can be extended to most of the CVD cases. It is verified on the PTBDB and IAFDB databases by taking the CVD including Atrial Fibrillation, Myocardial Infarction, Bundle Branch Block, Cardiomyopathy, Dysrhythmia, and Hypertrophy. The methodology has been tested on 65 patients’ data for the classification of abnormalities in PR interval, QRS complex, and QT interval. Based on the obtained statistical results, to detect the abnormality in PR interval, QRS complex and QT interval the Coefficient Variation (CV) should be greater than or equal to 0.1012, 0.083, 0.082 respectively with individual accuracy levels of 95.3%, 96.9%, and 98.5% respectively. To justify the clinical significance of the proposed methodology, the Confidence Interval (CI), the p-value using ANOVA have been computed. The p-value obtained is less than 0.05, and greater F-statistic values reveal the robust classification of CVD using localized features.

A review on remote health monitoring sensors and their filtering techniques

“…In [42] , the authors achieve a higher efficiency and accuracy rate using SVM classifier by reducing the features using the Gaussian Discriminant Analysis (GDA) algorithm. The article, [43] gives the clear efficiency difference of SVM classifier and k-nearest neighbors (KNN) classifier for QRS complex detection for various models in Fig 1 , Fig 2 , which are taken from the above-mentioned paper.

Fig 1 Accuracy- SVM-91.3%, KNN-89.9% [43]

Fig 2 Accuracy- SVM-92.9%, KNN-88.4% [43]

…”

“…The article, [43] gives the clear efficiency difference of SVM classifier and k-nearest neighbors (KNN) classifier for QRS complex detection for various models in Fig 1 , Fig 2 , which are taken from the above-mentioned paper.

Fig 1 Accuracy- SVM-91.3%, KNN-89.9% [43]

Fig 2 Accuracy- SVM-92.9%, KNN-88.4% [43]

…”

Deep learning methods for screening patients' S-ICD implantation eligibility

“…Machine learning methods have been used for ECG analysis in a variety of applications. There has been a wealth of work in the classification of various Cardiovascular Diseases (CVDs) from ECG data [30,29,27,26,31,25,14,8,33]. Other applications of machine learning in ECG analysis include detecting seizures and heart attacks [18,19], predicting patients' blood pressure [24], detecting a patients facial expressions [6] and analysis of ECG of the brain has been used for creating brain computer interfaces (BCI) capable of detecting which body Figure 2.…”

“…Box counting as well as column and row statistics are features o en extracted from the PSR matrix of ECG data. These methods have been used in the prediction of CVD [30,29,27,26], creating BCIs [5,7], and detecting facial expressions [6]. These approaches all centre around manually selecting features to extract from the PSR matrix.…”

“…where τ is the time delay between points in the series and d is the number of dimensions of the phase space which we are mapping this data to. While using high dimensional PSR has given good results in the field of BCI [5,7], the majority of the work in ECG analysis uses two-dimensional PSR, corresponding to d = 2 [27,16,30,26]. For this reason we transform our time series data into a normalized matrix of two-dimensional phase space vectors…”