ants and Arrhythmias--Cardiac

In this paper, a new method for clustering analysis of QRS complexes is proposed. We present an efficient Arrhythmia Clustering and Detection algorithm based on medical experiment and Ant Colony Optimization technique for QRS complex. The algorithm has been developed based on not only the general signal detection knowledge, but also on the ECG signal's specific features. Furthermore, our study brings the power of Ant Colony Optimization technique to the ECG clustering area. ACO-based clustering technique has also been improved using nearest neighborhood interpolation. At the beginning of our algorithm, we implement signal filtering, baseline wandering and parameter extraction procedures. Next is the learning phase which consists of clustering the QRS complexes based on the Ant Colony Optimization technique. A Neural Network algorithm is developed in parallel to verify and measure the success of our novel algorithm. The last stage is the testing phase to control the efficiency and correctness of the algorithm. The method is tested with MIT-BIH database to classify six different arrhythmia types of vital importance. These are normal sinus rhythm, premature ventricular contraction (PVC), atrial premature contraction (APC), right bundle branch block, ventricular fusion and fusion. Our simulation results indicate that this new approach has correctness and speed improvements.

Topics: Algorithms; Animals; Ants; Arrhythmias, Cardiac; Cluster Analysis; Electrocardiography; Models, Theoretical

The paper presents an application of a clustering technique inspired by ant colony metaheuristics. The paper addresses the problem of long-term (Holter) electrocardiogram data processing. Long-term recording produces a huge amount of biomedical data, which must be preprocessed prior to its presentation to the specialist. The paper also discusses relevant aspects improving the robustness, stability and convergence criteria of the method. The method is compared with well known clustering techniques (both classical and nature-inspired), first testing on the known dataset and finally applying them to the real ECG data records from the MIT-BIH database and outperforms the standard methods. Electrocardiogram data clustering can effectively reduce the amount of data presented to the cardiologist: cardiac arrhythmia and significant morphology changes in the ECG can be visually emphasized in a reasonable time. The final evaluation of the ECG recording must still be made by an expert.

Topics: Algorithms; Animals; Ants; Arrhythmias, Cardiac; Behavior, Animal; Biomimetics; Cluster Analysis; Diagnosis, Computer-Assisted; Electrocardiography, Ambulatory; Heart Rate; Humans; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted