Key result
Deep learning models using 12-lead ECGs predict incident arrhythmia and AF within 14 days.
Why the study?
This study aimed to compare the effectiveness of using discrete heartbeats versus an entire 12-lead ECG as deep learning input for predicting future arrhythmia and atrial fibrillation.
Does using discrete heartbeats from normal sinus rhythm ECG signals improve the prediction of future cardiac arrhythmias using deep learning models compared to entire 10-s 12-lead ECG signals?
Observational (n=134,447)
Does using discrete heartbeats from normal sinus rhythm ECG signals improve the prediction of future cardiac arrhythmias using deep learning models compared to entire 10-s 12-lead ECG signals?
Deep learning models using discrete heartbeats from normal sinus rhythm ECGs can predict future incidences of atrial fibrillation and clinically important arrhythmias within 14 days.
May aid near-term arrhythmia risk stratification from NSR ECGs; hypothesis-generating and requires prospective validation.
This study aims to compare the effectiveness of using discrete heartbeats versus an entire 12-lead electrocardiogram (ECG) as the input for predicting future occurrences of arrhythmia and atrial fibrillation using deep learning models. Experiments were conducted using two types of inputs: a combination of discrete heartbeats extracted from 12-lead ECG and an entire 12-lead ECG signal of 10 s. This study utilized 326,904 ECG signals from 134,447 patients and categorized them into three groups: true-normal sinus rhythm (T-NSR), atrial fibrillation-normal sinus rhythm (AF-NSR), and clinically important arrhythmia-normal sinus rhythm (CIA-NSR). The T-NSR group comprised patients with at least three normal rhythms in a year and no atrial fibrillation or arrhythmias history. Clinically important arrhythmia included atrial fibrillation, atrial flutter, atrial premature contraction, atrial tachycardia, ventricular premature contraction, ventricular tachycardia, right and left bundle branch block, and atrioventricular block over the second degree. The AF-NSR group included normal sinus rhythm paired with atrial fibrillation or atrial flutter within 14 days, and the CIA-NSR group comprised normal sinus rhythm paired with CIA occurring within 14 days. Three deep learning models, ResNet-18, LSTM, and Transformer-based models, were utilized to distinguish T-NSR from AF-NSR and T-NSR from CIA-NSR. The experiments demonstrated the potential of using discrete heartbeats in predicting future arrhythmia and atrial fibrillation incidences extracted from 12-lead electrocardiogram (ECG) signals alone, without any additional patient information. The analysis reveals that these discrete heartbeats contain subtle patterns that deep learning models can identify. Focusing on discrete heartbeats may lead to more timely and accurate diagnoses of these conditions, improving patient outcomes and enabling automated diagnosis using ECG signals as a biomarker.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2023) conducted an observational in Cardiac Arrhythmias and Atrial Fibrillation (n=134,447). Deep learning models using discrete heartbeats vs. Entire 10-second 12-lead ECG signal was evaluated on Prediction of future occurrences of arrhythmia and atrial fibrillation (distinguishing T-NSR from AF-NSR and CIA-NSR). Deep learning models using discrete heartbeats extracted from 12-lead ECG signals demonstrated the potential to predict future arrhythmia and atrial fibrillation incidences within 14 days.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: