Left ventricular ejection fraction (LVEF) is the most important parameter in the assessment of cardiac function. A machine-learning algorithm was trained to guide ultrasound-novices to acquire diagnostic echocardiography images. The artificial intelligence (AI) algorithm then estimates LVEF from the captured apical-4-chamber (AP4), apical-2-chamber (AP2), and parasternal-long-axis (PLAX) loops. We sought to test this algorithm by having first-year medical students without previous ultrasound knowledge scan real patients. Nineteen echo-naïve first-year medical students were trained in the basics of echocardiography by a 2.5 h online video tutorial. Each student then scanned three patients with the help of the AI. Image quality was graded according to the American College of Emergency Physicians scale. If rated as diagnostic quality, the AI calculated LVEF from the acquired loops (monoplane and also a “best-LVEF” considering all views acquired in the particular patient). These LVEF calculations were compared to images of the same patients captured and read by three experts (ground-truth LVEF [GT-EF]). The novices acquired diagnostic-quality images in 33/57 (58%), 49/57 (86%), and 39/57 (68%) patients in the PLAX, AP4, and AP2, respectively. At least one of the three views was obtained in 91% of the attempts. We found an excellent agreement between the machine’s LVEF calculations from images acquired by the novices with the GT-EF (bias of 3.5% ± 5.6 and r = 0.92, p < 0.001 in the “best-LVEF” algorithm). This pilot study shows first evidence that a machine-learning algorithm can guide ultrasound-novices to acquire diagnostic echo loops and provide an automated LVEF calculation that is in agreement with a human expert.

Echocardiographic evaluation of right ventricular (RV) function is a challenge due to the complex anatomy of the RV. Several transthoracic echocardiographic methods have been suggested for the quantification of RV function. However, many of the parameters are time consuming and need dedicated hardware and software. We suspected that the majority of the established markers are not used on a wide basis. In a multinational online survey, we evaluated the use of current clinical standards for the quantification of RV function in clinical practice. Through the network of an Ultrasound Online Teaching Platform, echocardiographers were invited to participate in an open online survey. The participants were asked about the parameters (eyeballing, TAPSE, S′, fractional area change, RIMP, 3D-EF, dp/dt, longitudinal strain) they used in clinical practice. A total of 1150 participants from 109 countries completed the survey. Only eyeballing (72%), TAPSE (69%), and S′ (31%) were commonly used in clinical routine. These methods were applied significantly less common in low-income economies when compared to high-income economies. Twenty-three percent of all participants stated to rely on eyeballing only, when evaluating RV function in clinical routine. New technologies, such as global longitudinal strain (3%) and 3D echocardiography (1%) were rarely applied independent of region and economic strength. Eyeballing and TAPSE are the most widely used methods in echocardiography for the assessment of RV function. Although advanced parameters such as longitudinal strain and 3D echocardiography were shown to be highly accurate, they are rarely used in clinical routine.

Summary Symptoms of right ventricular failure include dyspnea, a reduction in exercise capacity, and fluid retention. Right ventricular (dys)function strongly influences functional state and survival. The right ventricle is directly involved in a variety of diseases. A thorough analysis of right ventricular size and function, as well as estimation of pulmonary artery pressures is an important part of every echocardiographic examination. This review analyses the most commonly used parameters for quantification of right ventricular function. It gives a practical approach for estimation of right ventricular size and function, as well as pulmonary artery pressure.

Diastolic dysfunction of the left ventricle is common but frequently under-diagnosed. Particularly in advanced stages affected patients may present with significant functional tricuspid regurgitation (TR) as the most prominent sign on echocardiography. The underlying left ventricular pathology may eventually be missed and symptoms of heart failure are attributed to TR, with respective therapeutic consequences. The aim of the present study was to determine prevalence and mechanisms underlying TR evolution in heart failure with preserved ejection fraction (HFpEF). Consecutive HFpEF patients were enrolled in this prospective, observational study. Confirmatory diagnostic tests including echocardiography and invasive hemodynamic assessments were performed. Of the 175 patients registered between 2010 and 2014, 51% had significant (moderate or severe) TR without structural abnormalities of the tricuspid valve. Significant hemodynamic differences between patients with and without relevant TR were encountered. These included elevated pulmonary vascular resistance (p = 0.038), reduced pulmonary arterial compliance (PAC, p = 0.005), and elevated left ventricular filling pressures (p = 0.039) in the TR group. Multivariable binary logistic regression analysis revealed diastolic pulmonary artery pressure (p = 0.029) and PAC (p = 0.048) as independent determinants of TR. Patients were followed for 18.1±14.1 months, during which 32% had a cardiac event. While TR was associated with outcome in the univariable analysis, it failed to predict event-free survival in the multivariable model. The presence of ´isolated´ functional TR should prompt the suspicion of HFpEF. Our data show that significant TR is a marker of advanced HFpEF but neither an isolated entity nor independently associated with event-free survival.

The complex anatomy and physiology of the right ventricle (RV) is a major limitation of visual echocardiographic gradation of RV systolic function (RVF). The aim of this study was to compare visual assessment (“eyeballing”) of RVF with gold standard magnetic resonance imaging (MRI)-derived right ventricular ejection fraction (RVEF). Medical professionals from a range of clinical settings and with varying degrees of echocardiography experience were recruited via an online ultrasound teaching platform. In an anonymized web-based test, participants graded RVF in 10 patients with varying degrees of RVF via “eyeballing” of an RV-focused four-chamber view. Two skills were evaluated: (1) ability to differentiate between normal and reduced RVF; and (2) ability to determine the correct degree of RV systolic dysfunction. A total of 868 participants from 99 countries were included. For detection of reduced RVF (MRI-RVEF < 50%), sensitivity was 97.1%, 96,8%, 96.5%, and 95.8% and specificity was 55.7%, 52.8%, 54.6%, and 42.5% for the expert, advanced, intermediate, and beginner groups, respectively. For determination of the correct degree of RV dysfunction, even experienced examiners assigned a diagnosis that was discordant with MRI in > 40% of cases. In the present cohort, “eyeballing” was associated with excellent sensitivity but poor specificity in terms of differentiation between normal and abnormal RVF. Even among experts, classification of the degree of RV dysfunction was imprecise. In accordance with current guidelines, the present data suggest that “eyeballing” should be combined with evaluation of other echocardiographic parameters of RVF.

Late allocation of organs for transplant impairs post–liver transplantation (LT) survival. Cardiac dysfunction, especially diastolic and autonomic dysfunction, is frequent and plays an important role in the prognosis of patients with cirrhosis. However, the role of myocardial contractility is unexplored, and its prognostic value is controversially discussed. This study analyses the role of myocardial contractility assessed by speckle tracking echocardiography in LT allocation. In total, 168 patients with cirrhosis (training cohort, 111; validation cohort [VC], 57) awaiting LT in 2 centers were included in this retrospective study. Also, 51 patients from the training and all patients from the VC were transplanted, 36 patients of the training and 38 of the VC were alive at the end of follow‐up, and 21 nontransplanted patients died. Contractility of the left ventricle (LV) increased with severity of the Child‐Pugh score. Interestingly, higher LV contractility in the training cohort patients, especially in those with Child‐Pugh C, was an independent predictor of reduced transplant‐free survival. In male patients, the effects on survival of increased left and right ventricular myocardial contractility were more pronounced. Notably, competing risk analysis demonstrated that increased contractility is associated with earlier LT, which could be confirmed in the VC. Importantly, LV myocardial contractility had no impact on survival of patients not receiving LT or on post‐LT survival. In conclusion, this study demonstrates for the first time that increased myocardial contractility in decompensated patients identifies patients who require LT earlier, but without increased post‐LT mortality. Liver Transplantation 24 15–25 2018 AASLD.