Critical Care (Dec 2022)

Machine learning for the real-time assessment of left ventricular ejection fraction in critically ill patients: a bedside evaluation by novices and experts in echocardiography

  • Rita Varudo,
  • Filipe A. Gonzalez,
  • João Leote,
  • Cristina Martins,
  • Jacobo Bacariza,
  • Antero Fernandes,
  • Frederic Michard

DOI
https://doi.org/10.1186/s13054-022-04269-6
Journal volume & issue
Vol. 26, no. 1
pp. 1 – 5

Abstract

Read online

Abstract Background Machine learning algorithms have recently been developed to enable the automatic and real-time echocardiographic assessment of left ventricular ejection fraction (LVEF) and have not been evaluated in critically ill patients. Methods Real-time LVEF was prospectively measured in 95 ICU patients with a machine learning algorithm installed on a cart-based ultrasound system. Real-time measurements taken by novices (LVEFNov) and by experts (LVEFExp) were compared with LVEF reference measurements (LVEFRef) taken manually by echo experts. Results LVEFRef ranged from 26 to 80% (mean 54 ± 12%), and the reproducibility of measurements was 9 ± 6%. Thirty patients (32%) had a LVEFRef < 50% (left ventricular systolic dysfunction). Real-time LVEFExp and LVEFNov measurements ranged from 31 to 68% (mean 54 ± 10%) and from 28 to 70% (mean 54 ± 9%), respectively. The reproducibility of measurements was comparable for LVEFExp (5 ± 4%) and for LVEFNov (6 ± 5%) and significantly better than for reference measurements (p < 0.001). We observed a strong relationship between LVEFRef and both real-time LVEFExp (r = 0.86, p < 0.001) and LVEFNov (r = 0.81, p < 0.001). The average difference (bias) between real time and reference measurements was 0 ± 6% for LVEFExp and 0 ± 7% for LVEFNov. The sensitivity to detect systolic dysfunction was 70% for real-time LVEFExp and 73% for LVEFNov. The specificity to detect systolic dysfunction was 98% both for LVEFExp and LVEFNov. Conclusion Machine learning-enabled real-time measurements of LVEF were strongly correlated with manual measurements obtained by experts. The accuracy of real-time LVEF measurements was excellent, and the precision was fair. The reproducibility of LVEF measurements was better with the machine learning system. The specificity to detect left ventricular dysfunction was excellent both for experts and for novices, whereas the sensitivity could be improved. Trial registration: NCT05336448. Retrospectively registered on April 19, 2022.

Keywords