RPS/GMM Approach toward the localization of myocardial infarction

Due to the lack between clinical methods and applications used to diagnose ischemic heart disease, the 2007 Physionet/Computers in Cardiology challenge focuses on the ability to identify the segments, extent, and centroid of infarcts through ECG signals and body surface maps. The results from the participants are compared to a gold standard that consists of expert analysis of gadolinium-enhanced MRI data. The main hypothesis in this work is that the ordinary 12 ordinary leads contain the necessary information to identify the segment of the infarct. This hypothesis is tested using a reconstructed phase space and Gaussian Mixture Model approach in order to identify the infarcted segments. Since the challenge dataset consists of only two records for training and two for testing, the RPS/GMM approach is trained on the infarcted records from the PTB Diagnostics database and tested on the challenge data. The final score for the classification method was 1.15 out of maximum of 2.