A novel machine-learning algorithm using fractional-Fourier-transform and moving averages achieved 90.7% classification accuracy on the SPH database using only four features, outperforming previous methods.
Does a novel machine-learning algorithm using TERMA and FrFT improve ECG heartbeat classification compared to state-of-the-art algorithms?
A novel machine-learning algorithm using TERMA and FrFT trained on a large database (>10,000 patients) improves ECG heartbeat classification and demonstrates cross-database generalizability.
Absolute Event Rate: 90.7% vs 38.2%
Electrocardiogram (ECG) signals represent the electrical activity of the human hearts and consist of several waveforms (P, QRS, and T). The duration and shape of each waveform and the distances between different peaks are used to diagnose heart diseases. In this work, to better analyze ECG signals, a new algorithm that exploits two-event related moving-averages (TERMA) and fractional-Fourier-transform (FrFT) algorithms is proposed. The TERMA algorithm specifies certain areas of interest to locate desired peak, while the FrFT rotates ECG signals in the time-frequency plane to manifest the locations of various peaks. The proposed algorithm's performance outperforms state-of-the-art algorithms. Moreover, to automatically classify heart disease, estimated peaks, durations between different peaks, and other ECG signal features were used to train a machine-learning model. Most of the available studies uses the MIT-BIH database (only 48 patients). However, in this work, the recently reported Shaoxing People's Hospital (SPH) database, which consists of more than 10,000 patients, was used to train the proposed machine-learning model, which is more realistic for classification. The cross-database training and testing with promising results is the uniqueness of our proposed machine-learning model.
Aziz et al. (2021) studied Cardiovascular diseases (arrhythmias) (n=10,694). FrFT and TERMA fusion algorithm with MLP classifier vs. State-of-the-art algorithms (e.g., TERMA alone, AR+DWT) was evaluated on Classification accuracy on the SPH database. A novel machine-learning algorithm using fractional-Fourier-transform and moving averages achieved 90.7% classification accuracy on the SPH database using only four features, outperforming previous methods.