Artificial intelligence-enabled ECG for left ventricular diastolic function and filling pressure

Artificial intelligence-enabled ECG for left ventricular diastolic function and filling pressure

2024 | Eunjung Lee, Saki Ito, William R. Miranda, Francisco Lopez-Jimenez, Garvan C. Kane, Samuel J. Asirvatham, Peter A. Noseworthy, Paul A. Friedman, Rickey E. Carter, Barry A. Borlaug, Zachi I. Attia and Jae K. Oh
This study aimed to develop an artificial intelligence (AI)-enabled electrocardiogram (ECG) model to identify echocardiographically determined diastolic dysfunction and increased filling pressure. The model was trained, validated, and tested on large cohorts of patients with no exclusion criteria. The AI-enabled ECG model demonstrated high accuracy in detecting increased filling pressure and grading diastolic dysfunction, with AUCs of 0.911 for increased filling pressure and 0.847, 0.911, and 0.943 for grades ≥1, ≥2, and 3, respectively. During a median follow-up of 5.9 years, patients with increased filling pressure predicted by the AI-ECG had higher mortality compared to those with normal filling pressure, after adjusting for age, sex, and comorbidities. The AI-ECG model showed similar prognostic value to echocardiography, making it a promising tool for enhancing the detection of diastolic dysfunction and increased filling pressure in cardiac diseases, including heart failure with preserved ejection fraction.This study aimed to develop an artificial intelligence (AI)-enabled electrocardiogram (ECG) model to identify echocardiographically determined diastolic dysfunction and increased filling pressure. The model was trained, validated, and tested on large cohorts of patients with no exclusion criteria. The AI-enabled ECG model demonstrated high accuracy in detecting increased filling pressure and grading diastolic dysfunction, with AUCs of 0.911 for increased filling pressure and 0.847, 0.911, and 0.943 for grades ≥1, ≥2, and 3, respectively. During a median follow-up of 5.9 years, patients with increased filling pressure predicted by the AI-ECG had higher mortality compared to those with normal filling pressure, after adjusting for age, sex, and comorbidities. The AI-ECG model showed similar prognostic value to echocardiography, making it a promising tool for enhancing the detection of diastolic dysfunction and increased filling pressure in cardiac diseases, including heart failure with preserved ejection fraction.
Reach us at info@study.space
[slides and audio] Artificial intelligence-enabled ECG for left ventricular diastolic function and filling pressure