Newman, Hana

Aims:Increased left ventricular (LV) wall thickness is frequently encountered in transthoracic echocardiography (TTE). While accurate and early diagnosis is clinically important, given the differences in available therapeutic options and prognosis, an extensive workup is often required to establish the diagnosis. We propose the first echo-based, automated deep learning model with a fusion architecture to facilitate the evaluation and diagnosis of increased left ventricular (LV) wall thickness. Methods and Results: Patients with an established diagnosis of increased LV wall thickness (hypertrophic cardiomyopathy (HCM), cardiac amyloidosis (CA), and hypertensive heart disease (HTN)/others) between 1/2015 and 11/2019 at Mayo Clinic Arizona were identified. The cohort was divided into 80%/10%/10% for training, validation, and testing sets, respectively. Six baseline TTE views were used to optimize a pre-trained InceptionResnetV2 model. Each model output was used to train a meta-learner under a fusion architecture. Model performance was assessed by multiclass area under the receiver operating characteristic curve (AUROC). A total of 586 patients were used for the final analysis (194 HCM, 201 CA, and 191 HTN/others). The mean age was 55.0 years, and 57.8% were male. Among the individual view-dependent models, the apical 4-chamber model had the best performance (AUROC: HCM: 0.94, CA: 0.73, and HTN/other: 0.87). The final fusion model outperformed all the view-dependent models (AUROC: HCM: 0.93, CA: 0.90, and HTN/other: 0.92). Conclusion: The echo-based InceptionResnetV2 fusion model can accurately classify the main etiologies of increased LV wall thickness and can facilitate the process of diagnosis and workup.

Background. End-stage kidney disease patients with concomitant heart failure (HF) with reduced ejection fraction are often denied kidney transplantation. The aims of this study were to explore factors predictive of suitability for kidney transplant and to assess cardiovascular outcomes in patients with impaired left ventricular ejection fraction (LVEF) after transplant. Methods. We evaluated 109 consecutive adults with LVEF ≤40% at the time of initial kidney transplant evaluation between 2013 and 2018. Posttransplant cardiovascular outcomes were defined as nonfatal myocardial infarction (MI), admission for HF, cardiovascular death, and all-cause mortality. Results. A cardiologist participated in kidney transplant evaluation for 87% of patients and was present at 49% of transplant selection conferences. Twenty-four patients (22%) were denied by a cardiologist for kidney transplant‚ and 59 (54%) were denied by the selection committee, of whom 43 were because of cardiovascular risk. Forty-two (38%) patients were approved for kidney transplant. On univariate analysis, the variables associated with denial for kidney transplant included cardiologist denial, higher cardiac troponin T, prior coronary intervention, cardiovascular event, positive stress study, lower ejection fraction, and lower VO2 max (all P < 0.05). Cardiologist denial was the most significant predictor of denial for kidney transplant in different multivariate models. At a median follow-up of 15 mo, 5 (5%) suffered nonfatal MI, 13 (12%) were hospitalized for HF exacerbation, and 17 (16%) died. Only 22 patients, 52% of those approved, underwent kidney transplant. After kidney transplant, there was 1 death, 1 nonfatal MI, and 3 hospitalizations for HF. Median LVEF improved from 38% before listing to 55% posttransplant. Conclusions. Cardiologist denial was the primary predictor of rejection for kidney transplant. Despite careful selection, prevalence of cardiovascular events and mortality after kidney transplant was 23%. There is need for a structured multidisciplinary approach for patients with impaired LVEF.