Continuous three-dimensional transesophageal echocardiography and deep learning for perioperative monitoring of left ventricular longitudinal function.

Abstract

Aims: Continuous monitoring of left ventricular (LV) function may improve cardiopulmonary management. Therefore, we have developed 3D autoMAPSE, a novel method that combines 3D transesophageal echocardiography and deep learning to automatically measure mitral annular plane systolic excursion (MAPSE). We hypothesized that 3D autoMAPSE could provide continuous monitoring of LV function in perioperative patients.

Methods and results: This prospective observational study included 50 adult intensive care patients after cardiac surgery. Single-beat full-volume 3D recordings were obtained every 5 min over a 120-min period using a hands-free method that simulated continuous monitoring with transesophageal echocardiography. Precision and agreement with manual MAPSE were determined by a test-retest study design during hemodynamic stability. Our results show that continuous monitoring by 3D autoMAPSE had excellent feasibility (99%). It analysed 10 cycles instantaneously (55 ± 15 s) with high precision (least significant change 1.6 mm). 3D autoMAPSE had adequate agreement with manual MAPSE (bias -1.4 mm, limits of agreement -4.0 to 1.2 mm). Continuous 3D autoMAPSE was associated with both N-terminal pro B-type natriuretic peptide (rho = -0.37, P = 0.008) and high-sensitivity troponin-T (rho = -0.28, P = 0.047). This association was slightly stronger than for LV ejection fraction or any other single echocardiographic measurement.

Conclusion: 3D autoMAPSE provided continuous monitoring of LV function in perioperative patients by obtaining highly feasible and precise measurements that agree with manual echocardiography and postoperative biomarkers. Thus, continuous 3D autoMAPSE may be an attractive complement to hemodynamic monitoring that can aid cardiopulmonary management.