Retraining an Artificial Intelligence Algorithm to Calculate Left Ventricular Ejection Fraction in Pediatrics

• Published in: Journal of cardiothoracic and vascular anesthesia Vol. 36; no. 9; pp. 3610 - 3616
• Main Authors: Zuercher, Mael, Ufkes, Steven, Erdman, Lauren, Slorach, Cameron, Mertens, Luc, Taylor, Katherine
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.09.2022
• Subjects: artificial intelligence; cardiac function; deep learning; pediatric patients; deep learning; cardiac function; artificial intelligence; pediatric patients
• ISSN: 1053-0770; 1532-8422; 1532-8422
• DOI: 10.1053/j.jvca.2022.05.004

Identifying patients with low left ventricular ejection fraction (LVEF) and monitoring LVEF responses to treatment are important clinical goals. Can a deep-learning algorithm predict pediatric LVEF within clinically acceptable error? The study authors wanted to fine-tune an adult deep-learning algorithm to calculate LVEF in pediatric patients. A priori, their objective was to refine the algorithm to perform LVEF calculation with a mean absolute error (MAE) ≤5%. A quaternary pediatric hospital A convenience sample (n = 321) of echocardiograms from newborns to 18 years old with normal cardiac anatomy or hemodynamically insignificant anomalies. Echocardiograms were chosen from a group of healthy controls with known normal LVEF (n = 267) and a dilated cardiomyopathy patient group with reduced LVEF (n = 54). The artificial intelligence model EchoNet-Dynamic was tested on this data set and then retrained, tested, and further validated to improve LVEF calculation. The gold standard value was LVEF calculated by clinical experts. In a random subset of subjects (n = 40) not analyzed prior to selection of the final model, EchoNet-Dynamic calculated LVEF with a MAE of 8.39%, R2 = 0.47 without, and MAE 4.47%, R2 = 0.87 with fine-tuning. Bland-Altman analysis suggested that the model slightly underestimates LVEF (bias = –2.42%). The 95% limits of agreement between actual and calculated values were –12.32% to 7.47%. The fine-tuned model calculates LVEF in a range of pediatric patients within clinically acceptable error. Potential advantages include reducing operator error in LVEF calculation and supporting independent LVEF assessment by inexperienced users. [Display omitted]