Partial potentials of selected cardiac muscle regions and heart activity model based on single fibres

Comparative Analysis of the Diagnostic Effectiveness of SATRO ECG in the Diagnosis of Ischemia Diagnosed in Myocardial Perfusion Scintigraphy Performed Using the SPECT Method

There is a great need for early diagnosis of ischemic heart disease (IHD), the most common cause of which is haemodynamic disorders caused mainly by obstructive atherosclerosis of the coronary arteries. The diagnosis of IHD is usually made with the use of functional tests, which include resting ECG (R) or examination of significant perfusion disorders during exercise using the SPECT method. Despite the fact that the ECG (R) test is commonly used in cardiological diagnostics, it has a limited diagnostic value, especially in people with a low probability of coronary artery disease (CAD). In order to increase the effectiveness of the ECG (R) examination, SATRO ECG software, based on the single fibres heart activity model (SFHAM), was used to evaluate the electrocardiograms. The introduction of new classifiers from the available medical data to the analysis made it possible to evaluate the diagnostic efficacy of SATRO ECG (TOT) in predicting significant perfusion disorders in the exercise SPECT (TOT 2). These disorders are most often caused by obstructive atherosclerosis of the coronary arteries, which is the main cause of CAD. The database of 316 patients (219 men and 97 women, aged 57 ± 10 years) was analyzed using resting and stress ECG, perfusion scintigraphy performed using the SPECT method, and SATRO ECG analysis. The diagnostic efficacy parameters of SATRO ECG (TOT) in predicting significant perfusion abnormalities in the exercise-induced SPECT (TOT 2) study were: sensitivity, 99%; specificity, 91%; concordance, 96%; and positive, 96%, and negative, 97%, predictive values. The Kappa–Cohen coefficient was 0.92, and the statistical significance coefficient was p < 0.001. These results indicate a statistically significant agreement in the diagnosis of IHD in both diagnostic methods used.

GK BASED FUZZY CLUSTERING FOR THE DIAGNOSIS OF CARDIAC ARRHYTHMIA

Abstract-Cardiac arrhythmia is one of the major causes of human death, and most of the time it cannot be predicted well in advance at the right time. Computational intelligence algorithms can help in extracting the hidden patterns of biological datasets. This paper explores the use of advanced and intelligent computational algorithms for automated detection, classification and clustering of cardiac arrhythmia (CA). Application of Fuzzy C-Mean and Extended Fuzzy C-Mean method to the arrhythmia dataset (165 normal healthy and 138 with CA) demonstrated their good CA classification capabilities. Fuzzy C Mean algorithm was able to classify the two group of data set with an overall accuracy of 97.2% [sensitivity 96.4%, specificity 98.12% and area under the receiver operating curve (AUC-ROC = 0.963)]. The classification accuracy improved significantly when GK-based extended Fuzzy was employed, and an overall accuracy of 99.14% was achieved (sensitivity 97.11%, specificity 99.18% and AUC-ROC = 0.995). These accuracy results were respectively, 19.02%, 7%, 9.14% and 11.06% higher when compared to multi-input single layer perceptron (SLP), feed forward back propagation (FFBP), self organizing maps (SOM) and support vector machine (SVM). The performance measures of fuzzy techniques were found to be better if a Principal Component Analysis (PCA) technique was used to preprocess the arrhythmia datasets.