ABSTRACT
Focused cardiac ultrasound (FoCUS) is becoming standard practice in a wide spectrum of clinical settings. There is limited data evaluating the real-world use of FoCUS with artificial intelligence (AI). Our objective was to determine the accuracy of FoCUS AI-assisted left ventricular ejection fraction (LVEF) assessment and compare its accuracy between novice and experienced users. In this prospective, multicentre study, participants requiring a transthoracic echocardiogram (TTE) were recruited to have a FoCUS done by a novice or experienced user. The AI-assisted device calculated LVEF at the bedside, which was subsequently compared to TTE. 449 participants were enrolled with 424 studies included in the final analysis. The overall intraclass coefficient was 0.904, and 0.921 in the novice (n = 208) and 0.845 in the experienced (n = 216) cohorts. There was a significant bias of 0.73% towards TTE (p = 0.005) with a level of agreement of 11.2%. Categorical grading of LVEF severity had excellent agreement to TTE (weighted kappa = 0.83). The area under the curve (AUC) was 0.98 for identifying an abnormal LVEF (<50%) with a sensitivity of 92.8%, specificity of 92.3%, negative predictive value (NPV) of 0.97 and a positive predictive value (PPV) of 0.83. In identifying severe dysfunction (<30%) the AUC was 0.99 with a sensitivity of 78.1%, specificity of 98.0%, NPV of 0.98 and PPV of 0.76. Here we report that FoCUS AI-assisted LVEF assessments provide highly reproducible LVEF estimations in comparison to formal TTE. This finding was consistent among senior and novice echocardiographers suggesting applicability in a variety of clinical settings.
ABSTRACT
BACKGROUND: Aortic stenosis (AS) is a degenerative valve condition that is underdiagnosed and undertreated. Detection of AS using limited two-dimensional echocardiography could enable screening and improve appropriate referral and treatment of this condition. The aim of this study was to develop methods for automated detection of AS from limited imaging data sets. METHODS: Convolutional neural networks were trained, validated, and tested using limited two-dimensional transthoracic echocardiographic data sets. Networks were developed to accomplish two sequential tasks: (1) view identification and (2) study-level grade of AS. Balanced accuracy and area under the receiver operator curve (AUROC) were the performance metrics used. RESULTS: Annotated images from 577 patients were included. Neural networks were trained on data from 338 patients (average n = 10,253 labeled images), validated on 119 patients (average n = 3,505 labeled images), and performance was assessed on a test set of 120 patients (average n = 3,511 labeled images). Fully automated screening for AS was achieved with an AUROC of 0.96. Networks can distinguish no significant (no, mild, mild to moderate) AS from significant (moderate or severe) AS with an AUROC of 0.86 and between early (mild or mild to moderate AS) and significant (moderate or severe) AS with an AUROC of 0.75. External validation of these networks in a cohort of 8,502 outpatient transthoracic echocardiograms showed that screening for AS can be achieved using parasternal long-axis imaging only with an AUROC of 0.91. CONCLUSION: Fully automated detection of AS using limited two-dimensional data sets is achievable using modern neural networks. These methods lay the groundwork for a novel method for screening for AS.
Subject(s)
Aortic Valve Stenosis , Machine Learning , Humans , Neural Networks, Computer , Echocardiography/methods , Reproducibility of ResultsABSTRACT
Venoarterial extracorporeal membrane oxygenation (VA-ECMO) provides cardiovascular and respiratory support for patients in cardiogenic shock; yet, complications are a frequent source of morbidity and mortality. Limb ischemia can be potentially mitigated by limp perfusion protection strategies (LPPS). We performed a systematic review and meta-analysis to evaluate the safety and efficacy of two LPPS in patients treated with peripheral VA-ECMO - prophylactic insertion of a distal perfusion catheter (DPC) and small bore (<17 Fr) arterial return cannula. Among 22 included studies, limb ischemia was reduced in patients receiving a small arterial cannula (OR 0.40, 95% CI 0.24-0.65; p < 0.001) and in patients receiving a prophylactic DPC (OR 0.31, 95% CI 0.21-0.47; p < 0.001). Mortality was not significantly reduced with either a small arterial cannula (OR 0.70, 95% CI 0.23-2.18; p = 0.54) or prophylactic DPC strategy (OR 0.89, 95% CI 0.67-1.17; p = 0.40). As such, prophylactic insertion of a DPC or smaller bore arterial return cannula appear to reduce the risk of lower limb ischemia in this analysis. Further data are needed to confirm these findings. Registration: Registered in PROSPERO Database (Registration CRD42020215677).
