Key result
The proposed automated classification method using Tunable-Q Wavelet Transform and decision tree achieved 99.25% accuracy in diagnosing cardiac arrhythmias from ECG signals.
Why the study?
Automatic electrocardiogram analysis is critical to diagnosing and treating arrhythmias, motivating the development of effective learning methods to distinguish normal people from those with arrhythmias.
Does a TQWT-based decomposition and decision tree classification method improve the accuracy of automated cardiac arrhythmia detection from ECG signals?
Does a TQWT-based decomposition and decision tree classification method improve the accuracy of automated cardiac arrhythmia detection from ECG signals?
An automated ECG classification method using TQWT and decision trees achieved over 99% accuracy in distinguishing normal rhythms from various arrhythmias in a standard database.
May aid automated ECG arrhythmia detection; leaves open clinical validation before adoption.
Today, cardiovascular disease has become an epidemic. Statistics show that one person dies every 33 seconds due to cardiovascular disease. It is estimated that 33% of men and 10% of women have a heart attack before the age of 60. Arrhythmias are abnormal beats that cause the heart to beat too fast or too slow to pump. Automatic electrocardiogram analysis is critical to the diagnosis and treatment of heart patients. There are several learning methods for analyzing ECG signals to diagnose arrhythmias. In the proposed method, the heart rate signals are decomposed into different sub bands using the Tunable Q-Factor Wavelet Transform (TQWT) method, then the features are extracted and modified using classification with the aim of better classifying and separating data in the process of identifying the clinical features of the class. They are classified so that normal people and people with cardiac arrhythmias can be distinguished from their ECG signals. The results showed that the proposed method classifies the ECG signal with 99.25% accuracy. Since accuracy in diagnosing cardiac arrhythmias in medicine is a vital and important factor, so the proposed method can be very effective for the decision of cardiologists.
No takes yet. Share an insight, caveat, or question.
Sarshar et al. (2021) studied Cardiac arrhythmia. Tunable-Q Wavelet Transform (TQWT) and Decision Tree classification vs. Other machine learning classifiers was evaluated on Classification accuracy. The proposed automated classification method using Tunable-Q Wavelet Transform and decision tree achieved 99.25% accuracy in diagnosing cardiac arrhythmias from ECG signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: