Improved assessment of left ventricular ejection fraction using artificial intelligence in echocardiography: A comparative analysis with cardiac magnetic resonance imaging

BACKGROUND: Left ventricular ejection fraction (LVEF) measurement in echocardiography (Echo) using the recommended modified biplane Simpson (MBS) method is operator-dependent and exhibits variability. We aimed to assess the accuracy of a novel fully automated (Auto) artificial intelligence (AI) in view selection and biplane LVEF calculation compared to MBS-Echo, with cardiac magnetic resonance imaging (CMR) as reference. METHODS: Each of the 301 consecutive patients underwent CMR and Echo on the same day. LVEF was measured independently by Auto-Echo, MBS-Echo and CMR. Interobserver (n = 40) and test-retest (n = 14) analysis followed. RESULTS: A total of 229 patients (76%) underwent complete analysis. Auto-Echo and MBS-Echo showed high correlations with CMR (R = 0.89 and 0.89) and with each other (R = 0.93). Auto underestimated LVEF (bias: 2.2%; limits of agreement [LOA]: -13.5 to 17.9%), while MBS overestimated it (bias: -2.2%; LOA: 18.6 to 14.1%). Despite comparable areas under the curves of Auto- and MBS-Echo (0.93 and 0.92), 46% (n = 70) of MBS-Echo misclassified LVEF by ≥5% units in patients with a reduced CMR-LVEF <51%. Although LVEF bias variability across different LV function ranges was significant (p < 0.001), Auto-Echo was closer to CMR for patients with reduced LVEF, wall motion abnormalities, and poor image quality than MBS-Echo. The interobserver correlation coefficient of Auto-Echo was excellent compared to MBS-Echo (1.00 vs. <0.91) for different readers. True test-retest variability was higher for MBS-Echo than for Auto-Echo (7.9% vs. 2.5%). CONCLUSION: The tested AI has the potential to improve the clinical utility of Echo by reducing user-related variability, providing more accurate and reliable results than MBS.