Echocardiographic Left Ventricular Mass Assessment: Correlation between 2D-Derived Linear Dimensions and 3-Dimensional Automated, Machine Learning-Based Methods in Unselected Patients

Abstract

A recently developed algorithm for 3D analysis based on machine learning (ML) principles detects left ventricular (LV) mass without any human interaction. We retrospectively studied the correlation between 2D-derived linear dimensions using the ASE/EACVI-recommended formula and 3D automated, ML-based methods (Philips HeartModel) regarding LV mass quantification in unselected patients undergoing echocardiography. We included 130 patients (mean age 60 ± 18 years; 45% women). There was only discrete agreement between 2D and 3D measurements of LV mass (r = 0.662, r2 = 0.348, p < 0.001). The automated algorithm yielded an overestimation of LV mass compared to the linear method (Bland–Altman positive bias of 13.1 g with 95% limits of the agreement at 4.5 to 21.6 g, p = 0.003, ICC 0.78 (95%CI 0.68−8.4). There was a significant proportional bias (Beta −0.22, t = −2.9) p = 0.005, the variance of the difference varied across the range of LV mass. When the published cut-offs for LV mass abnormality were used, the observed proportion of overall agreement was 77% (kappa = 0.32, p < 0.001). In consecutive patients undergoing echocardiography for any indications, LV mass assessment by 3D analysis using a novel ML-based algorithm showed systematic differences and wide limits of agreements compared with quantification by ASE/EACVI- recommended formula when the current cut-offs and partition values were applied.

Three-Dimensional Automated, Machine-Learning-Based Left Heart Chamber Metrics: Associations with Prevalent Vascular Risk Factors and Cardiovascular Diseases

“…LVGFI, originally developed utilizing CMR, is an appealing new cardiac parameter supported by proof of a predictive value more significant than EF in different patient populations [13][14][15][38][39][40] integrating global function (LVEF) with heart size, including LV mass. Therefore, the potential clinical use of LVGFI could be maintained with the more precise DHM metrics [5,6,11,41] which are much easier to apply than CMR. However, still being a derived parameter, postprocessing algorithms should hopefully be developed to calculate LVGFI with minimal time delay in terms of transferability to the clinic.…”

“…We used a single-beat acquisition mode and multiple cardiac cycles (3-5 beats) in patients with atrial fibrillation. Analysis of DHM methodology was described in detail in our recent publication [11].…”

LncRNA-GAS5 and β-Catenin as Independent Predictors of Asymptomatic Organ Damage in Nondiabetic Hypertensive Patients

“…Using the recommended formula for the calculation of the left ventricle mass (LVM) from the left ventricle linear dimensions based on modeling the left ventricle as a prolate ellipse of rotation, the LVM was determined as follows: LVM (g) = 0.8(1.04(LVIDD + IVST + PWT)3 LVIDD3) + 0.6. 20 The left ventricle mass index (LVMI) was calculated by the following formula: LVMI = LVM/body surface area. For a case to be classified as having left ventricular hypertrophy, LVMI must be greater than 115 g/m 2 for men and 95 g/m 2 for women.…”

Three-Dimensional Echocardiography Based on Automation and Machine Learning Principles and the Renaissance of Cardiac Morphometry

“…Our approach was to integrate 3DE within a 2DE protocol from the beginning if a 3DE probe was available and apply it routinely to all patients to evaluate left chambers and selectively for the right chambers. Our echo lab’s rate of acquiring a 3DE LV and LA volume is about 80%, including consecutive inpatient and outpatient studies [ 15 , 16 ]. Based on our and other [ 17 ] experiences, six major obstacles remain that prevent a wider spread of 3DE: (1) the underappreciation of the added clinical value of 3DE vs. conventional 2DE, (2) the finite number of 3DE probes available, (3) the need to organize a formal program of training and competency, (4) the presence of still unresolved technical issues of poor image quality, (5) the propriety algorithms to post-process and analyze 3DE datasets, and (6) the way to communicate the clinical significance of reporting changes from 2DE to 3DE, which remains to be defined.…”

“…Significantly, the high-performance, automated, adaptive analytics software offers the most accurate and reproducible quantitation of volumes, geometry, and function of the left heart and has the great potential to revolutionize our practice expanding potential clinical applications in ways that were inconceivable until recently. Indeed, we have at our disposal new algorithms for 3DE LV mass analysis [ 16 ]. Furthermore, these algorithms overcome many pitfalls of the conventional 2DE volumetric method, for example, for proper quantification of the mitral regurgitation, and the correct diagnosis of the low-flow state [ 20 ].…”