Key result
A decision tree classification algorithm utilizing the maximum amplitude in the frequency spectrum and R-R interval irregularity detected atrial fibrillation with 98.9% accuracy, 97.93% sensitivity, and 99.63% specificity.
Why the study?
Accurate and rapid AF detection on ECG is vital, but signal interference and poorly distinguishable features can cause poor algorithm classification performance.
Does a time-frequency analysis algorithm using CART decision tree accurately detect atrial fibrillation in ECG signals?
Population
ECG signals from the MIT-BIH database
Comparison
Sinus rhythm signals vs AF signals
Design
Algorithm development and validation study
Authors
Loading...
High accuracy supports further algorithm refinement; leaves open prospective clinical validation before adoption.
Does a time-frequency analysis algorithm using CART decision tree accurately detect atrial fibrillation in ECG signals?
A novel algorithm combining time-domain and frequency-domain features with a decision tree classifier achieved high accuracy (98.9%) in detecting atrial fibrillation from ECG signals.
Hu et al. (2020) studied Atrial fibrillation (n=23). Decision tree classification algorithm using time-frequency domain features was evaluated on Accuracy of classifying sinus rhythm and atrial fibrillation signals. A decision tree classification algorithm utilizing the maximum amplitude in the frequency spectrum and R-R interval irregularity detected atrial fibrillation with 98.9% accuracy, 97.93% sensitivity, and 99.63% specificity.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: