An automated heartbeat classification system using optimal orthogonal wavelet filters and a KNN classifier achieved a maximum accuracy of 98.1%, sensitivity of 85.63%, and specificity of 98.27%.
An automated heartbeat classification system using optimal orthogonal wavelet filters and a KNN classifier achieved high accuracy (>98%) for detecting arrhythmias in both noisy and clean ECG signals.
Electrocardiogram (ECG) is commonly used to analyze heartbeats. Arrhythmia is a disturbance of the heartbeat that can potentially be lethal. Arrhythmia can be detected by identifying an individual abnormal heartbeat, which can occur in isolation or sequentially. Heartbeats can be classified into five types: non-ectopic (N), supra ventricular ectopic (S), ventricular ectopic (V), fusion (F) and unknown beats (Q). Automated classification of the incidence and pattern of abnormal heartbeats enables arrhythmia detection, triage and life-threatening arrhythmia. Therefore, it is vital to develop a tool for the classification of these classes. ECG signals are contaminated by noise rendering difficulty and challenging to discriminate between different types of heartbeats. In this work, we used noisy as well as denoised (clean) ECG signals to classify heartbeats. Using stop-band energy (SBE) minimized dyadic orthogonal filter bank, wavelet decomposition of the ECG signals was performed. After this, fuzzy entropy, Renyi entropy and fractal dimension features were extracted for easier and accurate classification into the five classes. These features were then fed to classifiers, achieving maximum accuracy (MAAC) of 98%, maximum sensitivity (MASE) of 85.33% and maximum specificity (MASP) of 98.22% for noisy data, and MAAC of 98.1%, MASE of 85.63% and MASP of 98.27% for clean data, with KNN classifier. Our developed system can be used in intensive care units to assist the clinicians to aid in their diagnosis.
Sharma et al. (Tue,) conducted a other in Arrhythmia. Automated heartbeat classification using optimal orthogonal wavelet filters and KNN classifier was evaluated on Classification accuracy, sensitivity, and specificity for five heartbeat classes. An automated heartbeat classification system using optimal orthogonal wavelet filters and a KNN classifier achieved a maximum accuracy of 98.1%, sensitivity of 85.63%, and specificity of 98.27%.