Citations

Background: Enlargement or dilation of the left ventricle (LV) is associated with increased cardiovascular morbidity and mortality, and is an established precursor of ventricular dysfunction and heart failure in almost all major cardiovascular conditions. Although there are existing artificial intelligence frameworks that make use of deep learning to detect LV enlargement, many entail LV segmentation, which can be error-prone especially for point-of-care ultrasound (POCUS) images. Goal: To develop a fully end-to-end deep learning framework that takes as input either transthoracic echocardiographic (TTE) or POCUS 2D image clips, and classifies directly (i.e., without first segmenting the LV) whether a patient has an enlarged LV. Methods: Using a sample of retrospective TTE data enriched for LV enlargement (out of 13,868 patients total, 3,351 had an enlarged LV defined using sex-specific guideline-directed criteria), we trained a classifier that takes as input apical 2-chamber and parasternal long axis videos, and provides as output a binary label denoting whether a patient has an enlarged LV. Then, we evaluated the trained model using a holdout testing dataset of retrospective TTE data (2,087 patients) as well as data from a prospective cohort of 428 patients from whom TTE and POCUS were collected simultaneously. Results: For the retrospective TTE testing dataset, the AUC was 0.851 (95% confidence interval (CI) of 0.830-871). For the prospective cohort, the model performed comparably for both TTE and POCUS video clips (TTE: AUC of 0.865, 95% CI of 0.823-0.906; POCUS: AUC of 0.840, 95% CI of 0.797-0.883). Conclusions: The current deep learning model performed comparably well for both TTE and POCUS echocardiograms. We regard these results as a proof-of-concept of the potential utility of this model in helping point-of-care clinicians make decisions regarding whether patients should receive further evaluation for LV enlargement and associated conditions.

Introduction: Multiple Valvular Heart Disease (VHD), defined as at least moderate stenotic or regurgitant lesions in ≥2 valves, mixed VHD as combination of lesions in the same valve and mitral annular calcification (MAC) are common conditions. Association between multiple-mixed VHD (MMVHD), MAC and MACE in patients exposed to Radiation Therapy (RT) and/or chemotherapy (CT) who underwent Transcatheter Aortic Valve Replacement (TAVR) has not been studied. Aim: Assess the presence of MMVHD and MAC in cancer patients with prior RT and/or CT and their correlation with MACE (cardiovascular death, myocardial infarction, revascularization, stroke and hospitalization for heart failure) after TAVR. Methods: 544 patients were included and divided into 3 groups: 187 with prior chest RT and CT (RT/CT), 155 CT only, and 202 without CT/RT as controls (Table 1). Data was obtained from the pre-procedure echocardiogram and quantified in a 1-6 scale (none, mild, mild/moderate, moderate, moderate/severe and severe). Fisher’s exact test or chi-square were used to compare categorical. Multiple VHD-MACE correlation was evaluated through multivariable Cox analysis using a proportional hazards model. Results: The prevalence of Multiple VHD was 37.4% in RT/CT, 23.2% in CT, and 13.9% in controls p<0.001(Figure 1). The RT/CT group had a significantly higher prevalence of severe MAC. Multiple VHD predicted MACE at 18 months after TAVR in RT/CT (HR 3.42, CI 1.93-6.08, p<0.001) and in CT (HR 2.55, CI 1.39-4.66, p=0.002) (Table 2). In RT/CT, severe MAC also predicted MACE (HR 3.68, CI 2.13-6.37, p<0.001), while it was not a predictor in the other groups. Stenotic or regurgitant VHD was more prevalent in the RT/CT group (Figure 2). Conclusions: Multiple VHD was found higher in RT/CT and predicted MACE at 18 months post-TAVR, including CT only patients. Severe MAC was also a strong predictor of the outcome in RT/CT patients. Pre-TAVR evaluation of MMVHD lesions is crucial for optimal patient management.

Background: Diagnosis of heart failure with preserved ejection fraction (HFpEF) is challenging due to non-diagnostic imaging outputs and discordant clinical features. Using only a single videoclip from a standard transthoracic echocardiogram (TTE), we developed an artificial intelligence (AI) model to differentiate patients with HFpEF from those without HFpEF. In a separate test population, we assessed the model’s ability to predict cardiac mortality. Methods: A 3-dimensional convolutional neural network was developed and trained on apical 4-chamber videoclips to classify patients with HFpEF (cases) versus without HFpEF (controls). Overall and cardiac mortality were obtained from the National Death Index. Results: The model was independently tested in 646 cases and 638 controls from 8 centers in 4 states. Sensitivity (87.8%; 84.5-90.9%) and specificity (81.9%; 78.2-85.6%) were high and sustained in various subgroups, including increased left atrial volume index, average E/e’ ≥15, and pulmonary artery systolic pressure >35 mm Hg. During follow-up (median [IQR] 3.4 [1.7-6.5] years), 540 patients died. There were 135 cardiac deaths attributable to heart failure (47%), coronary artery disease (41%), valve disease (4%), arrhythmia (4%), and others (5%). Compared to a negative output, all-cause mortality was higher in patients with a positive (HR 2.9 [2.4-3.5]) or uncertain output (HR 1.8 [1.2-2.5]), and cardiac mortality (Figure) was also higher in patients with a positive (HR 7.7 [4.5-13.3]) or uncertain output (HR 3.4 [1.4-8.1]). Cardiac mortality differences according to AI model prediction remained after age adjustment (positive: HR 5.9 [3.3-10.4], p<0.001; uncertain: HR 2.8 [1.2-6.8], p=0.02). Conclusion: A novel AI model to detect HFpEF based on a single routinely acquired TTE videoclip also identifies those at increased risk of cardiac mortality.

Introduction: Rate of aortic stenosis (AS) progression in patients with concurrent atrial fibrillation (AF) has not been previously described. Objectives: To describe changes over time in aortic valve area (AVA) and associated hemodynamics during AS progression in patients in AF versus sinus rhythm (SR). Methods: Patients with AVA ≤ 1 cm 2 and preserved left ventricular ejection fraction ≥50% were identified from the Mayo Clinic Echocardiographic Laboratory Database. Serial echocardiograms prior to the development of AVA ≤ 1 cm 2 (Time 0) were examined. Inverse probability weighting was used for statistical analysis. Results: A total of 166 patients were included (SR=79 and AF=87), mean age 78.1 ± 7.8 years, females 31%. The rates of AVA reduction (-0.14±0.01 vs -0.12±0.01 cm2/year, p=0.31) and increase in trans-aortic peak velocity (+0.23 ± 0.02 vs +0.22 ± 0.02 m/sec, p=0.55) and mean gradient (MG) (3.9 ± 0.3 vs 3.8 ± 0.4 mmHg, p=0.83) did not differ between AF and SR (Figure 1). However, AF was associated with systematically lower forward stroke volume index (SVi), peak velocity and MG for the same AVA compared to SR (p<0.04 for all) throughout AS progression. When AVA reached 1 cm 2 , SVi (38.8±6.6 vs 45.7 ±8.9, p=0.02), peak velocity (3.9 ± 0.6 vs 4.1 ± 0.6 m/sec, p=0.04) and MG (36.6±10.9 vs 41±12.8 mmHg, p=0.03) were lower in AF compared to SR. Conclusions: The rate of AS progression was not different in AF versus SR. However, forward flow was systematically lower in AF resulting in discordant AS during AS progression and when AVA reached 1 cm 2 . Doppler velocity and MG criteria for severe AS appear to be lower in AF versus SR which has implications for timely diagnosis of severe AS and patient management.

Background: Recently, our team developed an end-to-end artificial intelligence (AI) framework that can successfully estimate left ventricular ejection fraction (LVEF) from echocardiogram videos. However, this framework requires specific views (A2C and PLAX), and cannot estimate LVEF for studies from which these views are missing. Goal: To develop a deep learning model to estimate LVEF from any type and number of echocardiogram video(s). Methods: We built a deep learning model for B-mode echocardiogram videos of the left ventricle (A2C, A3C, A4C, or PLAX views), using retrospective transthoracic echocardiography (TTE) data. The model was evaluated with two test datasets: one with random valid (i.e., showing the left ventricle) views, and one with preselected views (both having 433 patients). Later, the model was tested with a prospective patient cohort that had both TTE and point-of-care ultrasound (POCUS) data collected simultaneously (393 patients). Results: On the retrospective TTE test set, we observed excellent performance (five random valid views per study: RMSE of 6.87% and Pearson correlation (PC) of 0.82 on LVEF estimation, and an AUC of 0.96 (95% CI: of 0.94-0.98) on low LVEF classification (<=40%); preselected views: RMSE of 6.75%, PC of 0.83, and an AUC of 0.96 (95% CI: 0.94-0.98)). For both TTE and POCUS data from the prospective cohort, we also observed strong performance (TTE: RMSE of 5.62%, PC of 0.87, and an AUC of 0.97; POCUS: RMSE of 6.12%, PC of 0.84, and an AUC of 0.96). For the prospective test sets as well as for the retrospective TTE test set with preselected views, results reflect the estimated LVEF average of A2C, A3C, A4C, and PLAX videos from each patient. Conclusions: For both TTE and POCUS data, the current model showed strong performance which was comparable to that of our previously established view-specific model. Alongside this comparable performance, the current model surpasses our previous model in terms of flexibility, as it isn't dependent on view classification and allows a broader selection in terms of the number and types of videos per study or patient. This innovative approach could prove particularly beneficial in point-of-care situations in which it may not be feasible to obtain high-quality, view-specific videos.

Introduction: Doppler mean gradient (MG) can underestimate the severity of aortic stenosis (AS) in patients with atrial fibrillation (AF) compared to patients in sinus rhythm (SR). Patients with AF and severe AS may experience delayed diagnosis and more advanced disease at time of referral for transcatheter aortic valve replacement (TAVR). Methods: Patients who underwent TAVR from 2013 to 2017 for native valve severe AS were identified from an institutional database. MG and aortic valve calcium score (AVCS) at time of referral were compared in patients in AF and SR. Retrospective theoretical AVCS in AF patients were derived assuming an average progression of 152 AU/year (published data). Results: There were 820 patients included; mean age was 81.3+/- 8.2 years and 41.6% were female. AF was present in 356 patients at time of referral. Patients in AF were older (82.2 vs. 80.5, p = 0.003), had lower MG compared to SR patients (42.0 vs. 44.9, p = 0.002) and a lower peak velocity (4.1 vs. 4.2, p = 0.010) with a similar indexed aortic valve area (0.4 vs. 0.4, p = 0.17). Stratified by sex, the median calcium score for AF patients was higher (by around 300 AU) among both males (AF 2850.0 vs. SR 2561.0, p = 0.044) and females (AF 1942.0 vs. 1610.5, p = 0.025) ( figure 1 ). A density plot of retrospective theoretical AVCS in AF patients (projected assuming referral to TAVR approximately two years prior) resulted in nearly identical median AVCS between the two cohorts ( figure 2 ). Conclusions: Older age and higher AVCS in patients with AF compared to SR suggests that AS was both underestimated and more advanced at time of referral to TAVR. Patients in AF may have severe AS as early as 2 years prior to TAVR referral.

Background: Clinically significant tricuspid regurgitation (TR) is an important contributor to morbidity and mortality. The Tricuspid Regurgitation Impact on Outcomes (TRIO) score based on 8 parameters (age, gender, chronic heart failure, chronic lung disease, heart rate, creatinine, aspartate transaminase level, and TR severity) is used for risk stratification. The performance of the TRIO score in patients with TR secondary to severe pulmonary hypertension (PH) is unknown. Research Questions: To evaluate whether the TRIO score can be applied in patients with TR and pulmonary hypertension (PH), and to identify other predictors of mortality. Methods: Retrospective study including patients with TR ≥ moderate. Severe PH was defined as right ventricular systolic pressure (RVSP) ≥50 mmHg. The impact of clinical, echocardiographic and laboratory variables on mortality was evaluated with the Cox proportional hazard method. Results: A total of 13,482 patients from the TRIO population were included; severe PH was present in 6,530 (48.4%); mean age 73.4 + 13.3, 55.7% females. TRIO score performance was modest (AUC 0.62) in risk stratification (Figure A). PH patients had significantly higher mortality than those without PH at all levels of TRIO score (Figure B); differences were progressively lower with increasing TRIO scores. At multivariate analysis, only TRIO score [HR = 1.54 (1.35-1.77) per unit change], presence of an elevated NT-proBNP [HR = 1.02 (1.02-1.03) per 1000 pg/ml change], RVSP (HR = 1.08 (1.02-1.16) per 10 mmHg change], presence of RV dysfunction [HR = 1.15, (1.05-1.26)] and pulmonary artery pulsatility index (PAPi) ≤ 4 [HR = 1.34 (1.07-1.67)] were significant predictors of mortality (model AUC 0.65). Conclusions: TRIO score allows risk stratification in PH patients, but performance is modest; incorporating additional factors marginally increased model performance. PH patients have higher mortality at all levels of TRIO score, more so at low scores.

Introduction: Isolated functional tricuspid regurgitation (FTR) in the absence of structural heart disease may develop secondary to elevation in left heart pressures caused by left ventricular diastolic dysfunction (DD), as in heart failure with preserved ejection fraction (HFpEF). FTR may also herald the presence of occult DD or indicate greater risk for new-onset DD. However, prevalence and incidence of diastolic dysfunction (DD) in isolated FTR have not been studied. Aims: Investigate the prevalence and incidence of DD across the different severities of FTR of unclear cause. Methods: Adults with normal EF and without structural heart disease undergoing echocardiography at a tertiary medical center with a repeat study ≥6 months from baseline were identified. Severe DD was defined by ≥3/4 abnormal DD parameters (medial e’, medial E/e’, tricuspid regurgitation velocity, left atrial volume index) and moderate DD by ≥2. Results: Among 30,428 patients (median age 60; 50% women), FTR was absent in 73%, mild in 22%, moderate in 4%, and severe in 0.4%. Severe DD was present in 2%, 5%, 11%, and 13% patients, respectively, (p<.001) and moderate DD in 9%, 19%, 31%, and 48%, respectively (p<.001). The association of DD with increasing FTR was independent of all clinical characteristics. Over median 3.0 (IQR 1.5-5.4) years, incident severe and moderate DD developed more frequently with increasing FTR severity ( Figure) . Findings were confirmed in a propensity-matched subset where patients were matched for age, sex, BMI, atrial fibrillation, and comorbidities and in patients without lung disease or ≥moderate right ventricular enlargement. Conclusions: Patients with FTR of undefined etiology commonly have DD suggesting the presence of underlying left heart disease. Patients without apparent DD or HF at baseline who have FTR remain at significantly increased risk of developing DD over follow-up and may be a target population for therapies to prevent progression to clinical HFpEF.

Introduction: Tricuspid regurgitation is a common echocardiographic finding leading to excess morbidity and mortality in adult population. Hypothesis: Racial and ethnic disparities have been observed in various cardiovascular disorders’ prevalence and natural course, including valvular lesions. However, little is known about the epidemiology and clinical correlations of TR among non-Hispanic Black adults. Methods: To examine risk factors and clinical outcomes in non-Hispanic Black adults with moderate or more severe TR, 685 patients (7%) self-identified as non-Hispanic Black and 9127 (93%) self-identified as non-Hispanic White with a first echocardiographic report of moderate or more severe TR between 2005-2016 were studied. Results: Non-Hispanic Black patients had more severe TR when compared to white patients (25% vs. 20%, p<0.001). After adjusting for age and sex, non-Hispanic Black patients had significantly higher 10-year all-cause mortality (HR=1.34 (1.18, 1.52), p<0.001). Black race remained a risk factor for all-cause mortality even after adjustment for comorbidities like CHF, COPD, DM, CKD, hypertension, and ischemic heart disease (HR=1.23 (1.08, 1.40), p=0.002). Conclusions: Significant racial disparities exist in demographic, clinical and echocardiographic characteristics between non-Hispanic Black and White patients with moderate or more severe TR. Black race is a potential disease modifier leading to excess mortality.

ABSTRACT Aim Left atrial (LA) myopathy is increasingly recognized as an important phenotypic trait in heart failure (HF) with preserved ejection fraction (HFpEF). Right atrial (RA) remodelling and dysfunction also develop in HFpEF, but little data are available regarding the clinical characteristics and pathophysiology among patients with isolated LA, RA, or biatrial myopathy. Methods and results Patients with HFpEF underwent invasive haemodynamic exercise testing, comprehensive imaging including speckle tracking strain echocardiography, and clinical follow-up at Mayo Clinic between 2006 and 2018. LA myopathy was defined as LA volume index &gt;34 ml/m2 and/or LA reservoir strain ≤24% and RA myopathy by RA volume index &gt;39 ml/m2 in men and &gt;33 ml/m2 in women and/or RA reservoir strain ≤19.8%. Of 476 consecutively evaluated patients with HFpEF defined by invasive exercise testing with evaluable atrial structure/function, 125 (26%) had no atrial myopathy, 147 (31%) had isolated LA myopathy, 184 (39%) had biatrial myopathy, and 20 (4%) had isolated RA myopathy. Patients with HFpEF and biatrial myopathy had more atrial fibrillation, poorer left ventricular systolic and diastolic function, more severe pulmonary vascular disease, tricuspid regurgitation, ventricular interdependence and right ventricular dysfunction, and poorer cardiac output reserve with exercise. There were 94 patients with events over a median follow-up of 2.9 (interquartile range 1.4–4.6) years. Individuals with biatrial myopathy had an 84% higher risk of HF hospitalization or death as compared to those with isolated LA myopathy (hazard ratio 1.84; 95% confidence interval 1.16–2.92, p = 0.01). Conclusions Biatrial myopathy identifies patients with more advanced HFpEF characterized by more severe pulmonary vascular disease, right HF, poorer cardiac reserve, and a greater risk for adverse outcomes. Further study is required to define optimal strategies to treat and prevent biatrial myopathy in HFpEF.