Towards automatic detection of atrial fibrillation: A hybrid computational approach.

In this study, new methods coupling genetic programming with orthogonal least squares (GP/OLS) and simulated annealing (GP/SA) were applied to the detection of atrial fibrillation (AF) episodes. Empirical equations were obtained to classify the samples of AF and Normal episodes based on the analysis of RR interval signals. Another important contribution of this paper was to identify the effective time domain features of heart rate variability (HRV) signals via an improved forward floating selection analysis. The models were developed using the MIT-BIH arrhythmia database. A radial basis function (RBF) neural networks-based model was further developed using the same features and data sets to benchmark the GP/OLS and GP/SA models. The diagnostic performance of the GP/OLS and GP/SA classifiers was evaluated using receiver operating characteristics analysis. The results indicate a high level of efficacy of the GP/OLS model with sensitivity, specificity, positive predictivity, and accuracy rates of 99.11%, 98.91%, 98.23%, and 99.02%, respectively. These rates are equal to 99.11%, 97.83%, 98.23%, and 98.534% for the GP/SA model. The proposed GP/OLS and GP/SA models have a significantly better performance than the RBF and several models found in the literature.