Shankara Bonthu Reddy

An adaptive fuzzy model for ECG interpretation

A new pattern recognition model has been designed for ECG signal classification in general and acute myocardial infarction in specific. This model combines a fuzzy logic inference system with neural network adaptive learning. In this paper, we compare the performance of the proposed system to a neural network only model and a previously designed ECG interpretation program. The initial classification results based on a chest-pain patient database show that the new model has potential for classification accuracy while retaining the knowledge which is particularly useful for clinicians to understand the process of the model.

QT dispersion and principal component analysis in prehospital patients with chest pain

The objective of this study was to measure QT dispersion (QTD) and principal component analysis (PCA) ratio, using a newly developed algorithm, in a broad range of chest pain patients to determine potential value in diagnosing ischemic heart disease. The algorithm for determining QTD is based on least-square-fit technique, which has better reproducibility than threshold and simple slope methods. QTD and PCA measurements were retrospectively computer-calculated in adults with a chief or secondary complaint of chest pain or equivalent syndrome who had prehospital 12-lead ECGs acquired by paramedics. There were 2157 patients with evaluable data in the final study population. 53% were males, 47% females. Using a threshold of 46 ms, QTp global measurement had a sensitivity/specificity of 60%/90% for AMI and 28%/90% for angina. For AMI, using a threshold of 31, PCA ratio had a sensitivity/specificity of 35%/90%. These data support the contention that QTD and PCA may be useful diagnostic adjuncts for detection of ischemic heart disease.