Key result
Spatio-temporal filtering combined with clustering achieves ~99% accuracy in distinguishing NSR from atrial arrhythmias.
Why the study?
Atrial fibrillation can be asymptomatic and difficult to diagnose, particularly in early stages of the disease.
A spatio-temporal filtering method combined with clustering algorithms can accurately classify atrial arrhythmias and normal sinus rhythm from multi-lead ECG signals.
Answers are grounded in this paper and cite their sources.
May aid automated ECG arrhythmia screening; hypothesis-generating pending prospective clinical validation.
Atrial fibrillation (AF) is the most common cardiac arrhythmia and increases the risk of suffering stroke. Some people with AF do not have symptoms, so, its diagnosis can be difficult, especially in early stages of the disease. In this paper, we propose the use of the spatio-temporal filter (STF) to characterize atrial activity in ECG recordings and distinguish between normal sinus rhythm (NSR) and atrial arrhythmias. This method allows the effective detection of P waves when they are synchronized with QRS complexes. The distances from the QRS complexes to the detected P waves are characterized by seven dispersion metrics that are used as inputs to three clustering algorithms. The results show classification accuracy of up to 98.88% of NSR and atrial arrhythmias.
No takes yet. Share an insight, caveat, or question.
Giraldo-Guzmán et al. (2021) studied Atrial arrhythmias. Spatio-Temporal filter (STF) and clustering algorithms was evaluated on Classification accuracy of normal sinus rhythm and atrial arrhythmias. The proposed spatio-temporal filtering method combined with clustering algorithms achieved a classification accuracy of up to 98.88% for distinguishing between normal sinus rhythm and atrial arrhythmias.
Synapse has enriched 10 related papers. Consider them for comparative context: