Deep Learning-Based Automated Echocardiographic Quantification of Left Ventricular Ejection Fraction: A Point-of-Care Solution.

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.

Diastolic Function and Transcatheter Aortic Valve Replacement.

BACKGROUND: Little is known about baseline diastolic dysfunction and changes in diastolic dysfunction grade after transcatheter aortic valve replacement (TAVR) for aortic stenosis (AS) and its impact on overall outcomes. The aim of this study was to describe baseline diastolic dysfunction and changes in diastolic dysfunction grade that occur with TAVR and their relationship to mortality and rehospitalization. METHODS: This was a single-center study evaluating all TAVRs from January 2012 to June 2014. We compared parameters of diastolic dysfunction grade on pre-TAVR and 1 month post-TAVR echocardiograms for all patients undergoing the procedure. Descriptive statistics, Kaplan-Meier time-to-event analysis, and multivariate logistic regression were used. RESULTS: Of a sample size of 120 patients undergoing TAVR for symptomatic severe AS, 90 were included in the final analysis after excluding significant mitral valve disease. There were improvements in individual parameters of diastolic dysfunction grade such as lateral e' velocity, E/lateral e', and left atrial volume index (nonsignificant trend) in the setting of improvement in aortic valve area and gradients and functional class pre- and post-TAVR. Multivariate analysis revealed that baseline diastolic dysfunction grade, but not post-TAVR or changes in diastolic dysfunction grade, was associated with 1-year death (hazard ratio, 1.163; 95% CI, 1.049-1.277, P = .005) and combined death/cardiovascular hospitalization (hazard ratio, 1.174; 95% CI, 1.032-1.318; P = .018). CONCLUSIONS: In this single-center retrospective study of patients with symptomatic severe AS who underwent TAVR, several diastolic function parameters improved on echocardiography, but baseline diastolic dysfunction grade remained the most important echocardiographic factor associated with adverse 1-year outcomes.

Coronary CT angiography versus standard evaluation in acute chest pain.

BACKGROUND: It is unclear whether an evaluation incorporating coronary computed tomographic angiography (CCTA) is more effective than standard evaluation in the emergency department in patients with symptoms suggestive of acute coronary syndromes. METHODS: In this multicenter trial, we randomly assigned patients 40 to 74 years of age with symptoms suggestive of acute coronary syndromes but without ischemic electrocardiographic changes or an initial positive troponin test to early CCTA or to standard evaluation in the emergency department on weekdays during daylight hours between April 2010 and January 2012. The primary end point was length of stay in the hospital. Secondary end points included rates of discharge from the emergency department, major adverse cardiovascular events at 28 days, and cumulative costs. Safety end points were undetected acute coronary syndromes. RESULTS: The rate of acute coronary syndromes among 1000 patients with a mean (±SD) age of 54±8 years (47% women) was 8%. After early CCTA, as compared with standard evaluation, the mean length of stay in the hospital was reduced by 7.6 hours (P<0.001) and more patients were discharged directly from the emergency department (47% vs. 12%, P<0.001). There were no undetected acute coronary syndromes and no significant differences in major adverse cardiovascular events at 28 days. After CCTA, there was more downstream testing and higher radiation exposure. The cumulative mean cost of care was similar in the CCTA group and the standard-evaluation group ($4,289 and $4,060, respectively; P=0.65). CONCLUSIONS: In patients in the emergency department with symptoms suggestive of acute coronary syndromes, incorporating CCTA into a triage strategy improved the efficiency of clinical decision making, as compared with a standard evaluation in the emergency department, but it resulted in an increase in downstream testing and radiation exposure with no decrease in the overall costs of care. (Funded by the National Heart, Lung, and Blood Institute; ROMICAT-II ClinicalTrials.gov number, NCT01084239.).

The effect of Definity on systemic and pulmonary hemodynamics in patients.

BACKGROUND: The purpose of this study was to evaluate the pulmonary and systemic hemodynamic effects of Definity in patients with normal as well as those with elevated pulmonary artery pressure at baseline. Secondary objectives of the study were to evaluate safety and determine whether any potential immunologic reactions develop after Definity administration. METHODS: Patients with normal and elevated pulmonary artery systolic pressure undergoing right-heart catheterization received Definity (10 µL/kg) as a slow bolus over 30 to 60 sec. Multiple sequential measurements of right atrial pressure, pulmonary artery systolic pressure, pulmonary artery diastolic pressure, mean pulmonary artery pressure, cardiac output, and pulmonary capillary wedge pressure were made before and after Definity administration. Vital signs, electrocardiograms, and blood samples were taken at multiple time points. Patients were followed for the development of adverse events. RESULTS: A total of 32 patients (16 with elevated pulmonary artery systolic pressure > 35 mm Hg) were enrolled. No significant changes in any pulmonary or systemic hemodynamic parameters, vital sign values, electrocardiographic data, or laboratory variables were found for data obtained before versus after receipt of Definity. CONCLUSIONS: The administration of Definity at the approved dosage does not change pulmonary or systemic hemodynamics in control patients or those with mild to moderate pulmonary hypertension. No significant changes were noted in a wide array of clinical and laboratory safety assessments after patients were exposed to Definity.

Cardiac magnetic resonance imaging is more diagnostic than 2-dimensional echocardiography in determining the presence of bicuspid aortic valve.

OBJECTIVE: This study compares 2-dimensional, transthoracic echocardiography with cardiac magnetic resonance imaging in the preoperative identification of bicuspid aortic valve before aortic valve surgery. METHODS: Of 1203 patients who underwent an aortic valve operation, 218 had both preoperative transthoracic echocardiography and cardiac magnetic resonance imaging. Patients in the study group were aged 56 years and had an ejection fraction of 56%, 76% were male, and 29% had associated coronary artery disease. The results of transthoracic echocardiography and cardiac magnetic resonance imaging were classified as bicuspid aortic valve, trileaflet aortic valve, or nondiagnostic. Of the 218 patients, 123 (56%) had bicuspid aortic valve as determined at the time of surgery and 116 (53%) had an ascending aortic aneurysm. RESULTS: Of the 123 patients with bicuspid aortic valve confirmed at surgery, by transthoracic echocardiography 76 (62%) were identified preoperatively with bicuspid aortic valve, 12 (10%) were misidentified with trileaflet aortic valve, and 35 (28%) were nondiagnostic for valve morphology. In the same patients with bicuspid aortic valve, by cardiac magnetic resonance imaging 115 (93%) were identified with bicuspid aortic valve, 5 (4%) were misidentified with trileaflet aortic valve, and 3 (2%) were nondiagnostic. The difference between transthoracic echocardiography and cardiac magnetic resonance imaging to determine the presence of bicuspid aortic valve was statistically significant (P<.001). In the entire cohort of patients, transthoracic echocardiography was diagnostic for valve morphology in 155 patients (71%) compared with cardiac magnetic resonance imaging, which was diagnostic in 212 patients (97%) (P<.001). CONCLUSIONS: Cardiac magnetic resonance imaging is more diagnostic than transthoracic echocardiography in determining the presence of bicuspid aortic valve. A significant factor is the rate of nondiagnostic transthoracic echocardiography for aortic valve morphology. Cardiac magnetic resonance imaging can be performed as a complementary test when transthoracic echocardiography is nondiagnostic for aortic valve morphology.

The CT-STAT (Coronary Computed Tomographic Angiography for Systematic Triage of Acute Chest Pain Patients to Treatment) trial.

OBJECTIVES: The purpose of this study was to compare the efficiency, cost, and safety of a diagnostic strategy employing early coronary computed tomographic angiography (CCTA) to a strategy employing rest-stress myocardial perfusion imaging (MPI) in the evaluation of acute low-risk chest pain. BACKGROUND: In the United States, >8 million patients require emergency department evaluation for acute chest pain annually at an estimated diagnostic cost of >$10 billion. METHODS: This multicenter, randomized clinical trial in 16 emergency departments ran between June 2007 and November 2008. Patients were randomly allocated to CCTA (n = 361) or MPI (n = 338) as the index noninvasive test. The primary outcome was time to diagnosis; the secondary outcomes were emergency department costs of care and safety, defined as freedom from major adverse cardiac events in patients with normal index tests, including 6-month follow-up. RESULTS: The CCTA resulted in a 54% reduction in time to diagnosis compared with MPI (median 2.9 h [25th to 75th percentile: 2.1 to 4.0 h] vs. 6.3 h [25th to 75th percentile: 4.2 to 19.0 h], p < 0.0001). Costs of care were 38% lower compared with standard (median $2,137 [25th to 75th percentile: $1,660 to $3,077] vs. $3,458 [25th to 75th percentile: $2,900 to $4,297], p < 0.0001). The diagnostic strategies had no difference in major adverse cardiac events after normal index testing (0.8% in the CCTA arm vs. 0.4% in the MPI arm, p = 0.29). CONCLUSIONS: In emergency department acute, low-risk chest pain patients, the use of CCTA results in more rapid and cost-efficient safe diagnosis than rest-stress MPI. Further studies comparing CCTA to other diagnostic strategies are needed to optimize evaluation of specific patient subsets. (Coronary Computed Tomographic Angiography for Systematic Triage of Acute Chest Pain Patients to Treatment [CT-STAT]; NCT00468325).

A randomized cross-over study for evaluation of the effect of image optimization with contrast on the diagnostic accuracy of dobutamine echocardiography in coronary artery disease The OPTIMIZE Trial.

OBJECTIVES: The purpose of this study was to evaluate whether the addition of a contrast agent to dobutamine stress echocardiography (DSE) improves its diagnostic accuracy for coronary artery disease (CAD) and to determine the effect of image quality on the diagnostic impact of contrast agent use in this setting. BACKGROUND: Contrast agents can improve endocardial border definition. To date, however, there are no randomized trials that have evaluated the impact of contrast agent use on the accuracy of DSE. METHODS: Patients referred for stress testing with dobutamine echocardiography underwent 2 DSE studies: 1 with and 1 without a contrast agent, at least 4 h apart in a randomized order and within a 24-h period. RESULTS: A total of 101 patients underwent both DSE studies. Similar hemodynamics were achieved during the 2 stress testing sessions. The use of a contrast agent improved the percentage of segments adequately visualized at baseline (from 72 +/- 24% to 95 +/- 8%) and more so at peak stress (67 +/- 28% to 96 +/- 7%); both p < 0.001. Interpretation of wall motion with high confidence also increased with contrast agent use from 36% to 74% (p < 0.001). Segment visualization with the use of a contrast agent improved in all views, but was more pronounced in the apical views. In unenhanced DSE, 36% of studies were normal, 51% had ischemia, and 8% were uninterpretable-all of which became interpretable with the use of a contrast agent. When compared with angiography (n = 92; 55 patients with CAD), accurate detection of ischemia was higher with contrast-enhanced studies versus nonenhanced studies (p = 0.02). As endocardial visualization and confidence of interpretation decreased in unenhanced studies, a greater impact of the use of a contrast agent on DSE accuracy was observed (p < 0.01). CONCLUSIONS: During dobutamine stress echocardiography, contrast agent administration improves endocardial visualization at rest and more so during stress, leading to a higher confidence of interpretation and greater accuracy in evaluating CAD. The lesser the endocardial border visualization, the higher the impact of contrast echocardiography on accuracy.

Non-blood contacting biventricular support for severe heart failure.

BACKGROUND: Direct mechanical ventricular actuation (DMVA) is a non-blood contacting method of biventricular support. DMVA employs a vacuum attached, pneumatically regulated, flexible membrane to transfer both systolic and diastolic forces to the ventricular myocardium. The purpose of this study was to determine if DMVA effectively restores pump performance when applied to the severely failing heart. METHODS: Bovines (n = 10) underwent thoracotomy and were instrumented for continuous hemodynamic monitoring. Cardiac failure was induced by beta1-blockade to achieve a cardiac index of < 1.5 l/min/m2 for 1 hour. Heart rate was maintained at 100 bpm by atrioventricular sequential pacing. Synchronous DMVA support was then applied for 3 hours. RESULTS: Eight animals achieved significant reductions in cardiac index and mean arterial pressures (35%* and 43%* control, respectively; *p < 0.05). DMVA restored cardiac index to baseline and significantly increased arterial pressures (p < 0.05; DMVA versus cardiac failure). Pulmonary flow and mean pulmonary artery pressures were similar to baseline during DMVA (p = NS). Pathologic exam did not demonstrate evidence of significant device trauma. CONCLUSIONS: DMVA support can effectively restore pump performance of the acutely failing heart. Synchronization may be inherent to the stimulus of cardiac compression. These data further substantiate DMVA's potential as an adjunct to the field of circulatory support.