Key result
RR interval deep learning model detects AF with ~99% sensitivity in real-world screening.
Why the study?
Manual identification of AF from long-term dynamic ECG data is time-consuming, subjective, and limited by a scarcity of experienced cardiologists.
Does a deep learning model based on RR intervals accurately automate primary screening for atrial fibrillation in adults undergoing 24-hour Holter monitoring?
Observational (n=23,452)
Does a deep learning model based on RR intervals accurately automate primary screening for atrial fibrillation in adults undergoing 24-hour Holter monitoring?
Effect estimate: Sensitivity 0.995, Specificity 0.985 (hospital scenario)
A deep learning algorithm analyzing RR intervals can accurately and fully automate the primary screening of atrial fibrillation from 24-hour Holter monitors, addressing the shortage of experienced cardiologists.
May automate Holter AF screening in hospitals; leaves open prospective validation before clinical adoption.
Aims: As the demand for atrial fibrillation (AF) screening increases, clinicians spend a significant amount of time identifying AF signals from massive amounts of data obtained during long-term dynamic electrocardiogram (ECG) monitoring. The identification of AF signals is subjective and depends on the experience of clinicians. However, experienced cardiologists are scarce. This study aimed to apply a deep learning-based algorithm to fully automate primary screening of patients with AF using 24-h Holter monitoring. Methods and results: A deep learning model was developed to automatically detect AF episodes using RR intervals and was trained and evaluated on 23 621 (2297 AF and 21 324 non-AF) 24-h Holter recordings from 23 452 patients. Based on the AF episode detection results, patients with AF were automatically identified using the criterion of at least one AF episode lasting 6 min or longer. Performance was assessed on an independent real-world hospital-scenario test set (19 227 recordings) and a community-scenario test set (1299 recordings). For the two test sets, the model obtained high performance for the identification of patients with AF (sensitivity: 0.995 and 1.000; specificity: 0.985 and 0.997, respectively). Moreover, it obtained good and consistent performance (sensitivity: 1.000; specificity: 0.972) for an external public data set. Conclusion: Using the criterion of at least one AF episode of 6 min or longer, the deep learning model can fully automatically screen patients for AF with high accuracy from long-term Holter monitoring data. This method may serve as a powerful and cost-effective tool for primary screening for AF.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2023) conducted an observational in Atrial fibrillation screening (n=23,452). Deep learning model using RR intervals vs. Clinical diagnosis by cardiologists (reference standard) was evaluated on Patient-level identification of atrial fibrillation (using criterion of ≥1 AF episode lasting ≥6 minutes) (Sensitivity 0.995, Specificity 0.985 (hospital scenario)). The RR interval-based deep learning model automatically screened patients for atrial fibrillation with 99.5% sensitivity and 98.5% specificity in a real-world hospital setting.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: