Background: Echocardiographic quantification of left ventricular (LV) ejection fraction (EF) relies on either manual or automated identification of endocardial boundaries followed by model-based calculation of end-systolic and end-diastolic LV volumes. Recent developments in artificial intelligence resulted in computer algorithms that allow near automated detection of endocardial boundaries and measurement of LV volumes and function. However, boundary identification is still prone to errors limiting accuracy in certain patients. We hypothesized that a fully automated machine learning algorithm could circumvent border detection and instead would estimate the degree of ventricular contraction, similar to a human expert trained on tens of thousands of images. Methods: Machine learning algorithm was developed and trained to automatically estimate LVEF on a database of >50 000 echocardiographic studies, including multiple apical 2- and 4-chamber views (AutoEF, BayLabs). Testing was performed on an independent group of 99 patients, whose automated EF values were compared with reference values obtained by averaging measurements by 3 experts using conventional volume-based technique. Inter-technique agreement was assessed using linear regression and Bland-Altman analysis. Consistency was assessed by mean absolute deviation among automated estimates from different combinations of apical views. Finally, sensitivity and specificity of detecting of EF ≤35% were calculated. These metrics were compared side-by-side against the same reference standard to those obtained from conventional EF measurements by clinical readers. Results: Automated estimation of LVEF was feasible in all 99 patients. AutoEF values showed high consistency (mean absolute deviation =2.9%) and excellent agreement with the reference values: r =0.95, bias=1.0%, limits of agreement =±11.8%, with sensitivity 0.90 and specificity 0.92 for detection of EF ≤35%. This was similar to clinicians’ measurements: r =0.94, bias=1.4%, limits of agreement =±13.4%, sensitivity 0.93, specificity 0.87. Conclusions: Machine learning algorithm for volume-independent LVEF estimation is highly feasible and similar in accuracy to conventional volume-based measurements, when compared with reference values provided by an expert panel.

Background: We have recently tested an automated machine-learning algorithm that quantifies left ventricular (LV) ejection fraction (EF) from guidelines-recommended apical views. However, in the point-of-care (POC) setting, apical 2-chamber views are often difficult to obtain, limiting the usefulness of this approach. Since most POC physicians often rely on visual assessment of apical 4-chamber and parasternal long-axis views, our algorithm was adapted to use either one of these 3 views or any combination. This study aimed to (1) test the accuracy of these automated estimates; (2) determine whether they could be used to accurately classify LV function. Methods: Reference EF was obtained using conventional biplane measurements by experienced echocardiographers. In protocol 1, we used echocardiographic images from 166 clinical examinations. Both automated and reference EF values were used to categorize LV function as hyperdynamic (EF>73%), normal (53%–73%), mildly-to-moderately (30%–52%), or severely reduced (<30%). Additionally, LV function was visually estimated for each view by 10 experienced physicians. Accuracy of the detection of reduced LV function (EF<53%) by the automated classification and physicians’ interpretation was assessed against the reference classification. In protocol 2, we tested the new machine-learning algorithm in the POC setting on images acquired by nurses using a portable imaging system. Results: Protocol 1: the agreement with the reference EF values was good (intraclass correlation, 0.86–0.95), with biases <2%. Machine-learning classification of LV function showed similar accuracy to that by physicians in most views, with only 10% to 15% cases where it was less accurate. Protocol 2: the agreement with the reference values was excellent (intraclass correlation=0.84) with a minimal bias of 2.5±6.4%. Conclusions: The new machine-learning algorithm allows accurate automated evaluation of LV function from echocardiographic views commonly used in the POC setting. This approach will enable more POC personnel to accurately assess LV function.

Background Echocardiographic quantification of left ventricular (LV) ejection fraction (EF) relies on either manual or automated identification of endocardial boundaries followed by standard calculation of model-based end-systolic and end-diastolic LV volumes. Recent developments in artificial intelligence resulted in computer algorithms that allow near automated detection of endocardial boundaries and measurement of LV volumes and function. However, boundary identification is still prone to errors limiting accuracy in certain patients. We hypothesized that a fully automated machine learning algorithm could be developed, which circumvents border detection and instead estimates the degree of ventricular contraction, similar to a human expert trained on tens of thousands of images. Purpose This study was designed to test the feasibility and accuracy of this approach. Methods Machine learning algorithm was developed and trained on a database of >50,000 echocardiographic studies, including multiple apical 2- and 4-chamber views, to automatically estimate LVEF (AutoEF, BayLabs). Testing was performed on an independent group of 99 unselected patients, whose automated EF values were compared to reference values obtained by averaging measurements by 3 experts using conventional volume-based technique. Inter-technique agreement was assessed using linear regression and Bland-Altman analysis of bias and limits of agreement (LOA). Consistency was assessed by mean absolute deviation (MAD) among automated estimates based on different combinations of apical views. Finally, sensitivity and specificity of detecting of EF≤35% was calculated. These metrics were compared side-by-side against the same reference standard to those obtained from conventional EF measurements by clinical readers. Results Automated estimation of LVEF was feasible in all 99 patients. AutoEF values showed high consistency (MAD=2.9%) and excellent agreement with the reference values: r=0.95, bias=1.0%, LOA=±11.8%, with sensitivity 0.90 and specificity 0.92 for detection of EF≤35%. This was similar to clinicians' measurements: r=0.94, bias=1.4%, LOA=±13.4%,sensitivity 0.93, specificity 0.87. Conclusions Machine learning algorithm for volume-independent LVEF estimation is highly feasible and similar in accuracy to conventional volume-based measurements, when compared to reference values provided by an expert panel. Acknowledgement/Funding Bay Labs, Inc.

Introduction: Aortic stenosis (AS) is common, with >= moderate severity ~10% above age 75. Despite new therapies, many with AS go undiagnosed due to lack of echo availability and untreated due to improper interpretation. To expand AS diagnosis, we developed an artificial intelligence (AI) algorithm to characterize AS from routine B-mode echo exams without Doppler (AutoAS). Methods: 80,000 de-identified clinical echoes were assembled spanning none, mild, moderate, and severe AS. About 30,000 of these were used to train a convolutional neural network (CNN) using labels derived from a cluster analysis of maximal jet velocity, mean AS gradient, and aortic valve area (AVA). Once labeled, we extracted all available B-mode clips from parasternal long-axis, short axis at aortic level, and apical 5-chamber views, irrespective of image quality. A spatiotemporal CNN was trained to return a probability distribution for none/mild/moderate/severe AS. To assess performance of the model, a hold-out test set of echoes uniformly distributed over patient sex and AS severity was used. Three Level 3 echo trained cardiologists blindly read the complete Doppler echoes and agreed to call AS severity by AVA (< 1 cm2, severe; 1.0-1.5 cm2, moderate; > 1.5 cm2 but restricted, mild; no restriction, none). Results were also dichotomized into none/mild and moderate/severe AS. Results: 40 cases comprised this initial test set. Consistency among the readers was outstanding, with κ = 0.95. The table shows the confusion matrix between AutoAS and panel reads, with excellent accuracy (κ = 0.90). Dichotomous results were also outstanding with sensitivity to detect moderate/severe AS of 91% and specificity of 94%. Conclusions: AI can identify AS from 3 B-mode views and characterize AS severity with accuracy highly congruent to an expert panel using full Doppler data. This may allow AS to be detected in low-resource and screening settings. Further assessment with a larger hold-out test set is planned.

No abstract