An artificial intelligence model predicted previous or future ventricular fibrillation episodes from Brugada ECGs with a negative predictive value of 0.94±0.11 and a positive predictive value of 0.44±0.29.
Observational
Does an artificial intelligence model applied to 12-lead ECGs predict previous or future ventricular fibrillation episodes in patients with suspected Brugada syndrome?
An AI-enabled algorithm using a convolutional neural network can predict the presence of ventricular fibrillation from a Brugada ECG with high negative predictive value, potentially aiding in risk stratification for sudden cardiac death.
BACKGROUND: Brugada syndrome is a potential cause of sudden cardiac death (SCD) and is characterized by a distinct ECG, but not all patients with A Brugada ECG develop SCD. In this study we sought to examine if an artificial intelligence (AI) model can predict a previous or future ventricular fibrillation (VF) episode from a Brugada ECG. METHODS AND RESULTS: score of 0.81±0.11. The negative predictive value was 0.94±0.11 while its positive predictive value was 0.44±0.29. CONCLUSIONS: This proof-of-concept study showed that an AI-enabled algorithm can predict the presence of VF with a substantial performance. It implies that the AI model may detect a subtle ECG change that is undetectable by humans.
Nakamura et al. (Fri,) führten eine Beobachtungsstudie zum Brugada-Syndrom durch. Das Modell der künstlichen Intelligenz (KI) wurde zur Vorhersage eines früheren oder zukünftigen episodes von ventrikulärer Fibrillation (VF) bewertet. Ein künstliches Intelligenzmodell sagte frühere oder zukünftige Episoden von ventrikulärer Fibrillation aus Brugada-EKGs mit einem negativen prädiktiven Wert von 0,94±0,11 und einem positiven prädiktiven Wert von 0,44±0,29 voraus.