Key result
A MATLAB-based GUI using discrete wavelet transform and a Bayes classifier identified normal heart rates in 18 patients and abnormal heart rates in 9 patients from the MIT database.
A MATLAB-based GUI using discrete wavelet transform and Bayes classifier can successfully process and classify ECG signals by heart rate, potentially aiding non-technical users in diagnostics.
Answers are grounded in this paper and cite their sources.
Wavelet-Bayes ECG classifier feasible in small MIT cohort; leaves open prospective clinical validation before use.
AIM: To process the electrocardiogram (ECG) signals using MATLAB-based graphical user interface (GUI) and to classify the signals based on heart rate. METHOD: The subject condition was identified using R-peak detection based on discrete wavelet transform followed by a Bayes classifier that classifies the ECG signals. The GUI was designed to display the ECG signal plot. RESULTS: Obtained from MIT database 18 patients had normal heart rate and 9 patients had abnormal heart rate; 14.81% of the patients suffered from tachycardia and 18.52% of the patients have bradycardia. CONCLUSION: The proposed GUI display was found useful to analyze the digitized ECG signal by a non-technical user and may help in diagnostics. Further improvement can be done by employing field programmable gate array for the real time processing of cardiac signals.
No takes yet. Share an insight, caveat, or question.
John et al. (2015) studied Arrhythmia (n=27). MATLAB-based graphical user interface with discrete wavelet transform and Bayes classifier was evaluated on Heart rate classification (normal vs abnormal). A MATLAB-based GUI using discrete wavelet transform and a Bayes classifier identified normal heart rates in 18 patients and abnormal heart rates in 9 patients from the MIT database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: