Mohamed A. Mneimneh

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.

A cardiac electro-physiological model based approach for filtering high frequency ECG noise

With an increasing focus on automatic diagnoses of cardiac disease through ECG signals, de-noising techniques that do not introduce artifacts have become necessary. This paper proposes a model based approach for removing high frequency noise from ECG signals. The proposed modeling technique is based on the propagation of the electric waves over the cardiac tissue. The proposed approach models the crucial nodes as a difference between two sigmoid functions. The ECG signal is modeled as the sum of the activity at the SA node, AV node, Bundle branches, Purkenji fibers, and right and left ventricles. The model is adapted to the targeted ECG signal using a nonlinear least squares optimization technique. The proposed filtering approach is applied to randomly selected ECGs from the long-term ST database. A quantitative analysis is performed on simulated ECG signals perturbed with white noise with ST signal to noise ratios ranging from -25 to 5 dB.

An electrophysiological cardiac model approach to measuring T-wave alternans

The 2008 Computers in Cardiology Challenge is to automatically identify and measure T-wave alternans. The study presented here applies an electrophysiological cardiac model to the problem of characterizing the T-wave variability. Thus, the hypothesis is that the existence and magnitude of T-wave alternans can be identified and measured using a cardiac inverse problem approach, where the magnitude of the alternans are measured in the model space. The dataset used in this study is a collection of records from selected databases in the Physionet databank. Additionally, a simulated ECG dataset is used to study the sensitivity and specificity of the proposed approach under various noise conditions. Results on the simulated ECG data set show that the approach is able to differentiate between 5, 10, 20, and 100 microvolt T-wave alternans in the presence of various noises between -25 and 5dB SNR. The score from the challenge, which is the Kendall rank correlation coefficient, is 0.331.