Kirkpatrick, James N

Abstract Background and Aims Accurate differentiation of cardiac amyloidosis (CA) from phenotypic mimics remains challenging using current clinical and echocardiographic techniques. The accuracy of a novel artificial intelligence (AI) screening algorithm for echocardiography-based CA detection was assessed. Methods Utilizing a multisite, multiethnic dataset (n = 2612, 52% CA), a convolutional neural network was trained to differentiate CA from phenotypic controls using transthoracic apical four-chamber video clips. External validation was conducted globally across 18 sites including 597 CA cases and 2122 controls. Classification accuracy was assessed on the entire external validation dataset, and subgroup analyses were performed both on technetium pyrophosphate scintigraphy referrals, and individuals matched for age, sex, and wall thickness. Model accuracy was also compared with the transthyretin CA score and the increased wall thickness score within a subset of older heart failure with preserved ejection fraction patients with increased wall thickness. Results Cardiac amyloidosis patients and controls displayed similar age, sex, race, and comorbidities. After the removal of uncertain AI predictions (13%), model discrimination and classification were excellent for the entire external validation dataset [area under the receiver operating characteristic curve (AUROC) 0.93, sensitivity 85%, specificity 93%], irrespective of CA subtype (sensitivity: light-chain = 84%, wild-type transthyretin = 85%, and hereditary transthyretin = 86%). Performance was maintained in subgroup analysis in patients clinically referred for technetium pyrophosphate scintigraphy imaging (AUROC 0.86, sensitivity 77%, specificity 86%) and matched patients (AUROC 0.92, sensitivity 84%, specificity 91%). The AI model (AUROC 0.93) also outperformed transthyretin CA score (AUROC 0.73) and increased wall thickness (AUROC 0.80) scores. Conclusions This AI screening model—using only an apical four-chamber view—effectively differentiated CA from other causes of increased left ventricular wall thickness.

Background: Guidelines recommend involvement of palliative care (PC) for patients with cardiovascular (CV) disease and their families. Little is known about the current integration of PC and CV services. Research Objectives: Our national survey aimed to describe current practices and to identify benefits, challenges, and barriers with collaboration. Methods: Qualitative content analysis of open-response questions in an investigator-developed electronic survey study of CV and PC providers (MDs, NPs, PAs, and other allied health) using email listservs, social media, and crowdsourcing. Frequencies were tabulated using SAS statistical software. Results: Of 134 respondents, most were physicians (n=56, 57%) or advanced practice RNs or PAs (n=37, 28%), from 52 U.S. institutions, representing 33 states. The most common care for which PC was integrated were mechanical circulatory support, advanced heart failure, and heart transplantation; the least common care for which PC was integrated were TAVR, ECMO, and pulmonary hypertension. Integrated practice (n=80, 61%), PC identification of goals of care (n=20, 15%) and PC aid in patient/family communication (n=15, 11%) were the most commonly identified as positives in current practice. PC provider workforce (n=22, 16%), underutilization of PC referrals (n=20, 15%), late disease PC referral (n=19, 14%), and fundamental knowledge deficit of specialty scope (n=18, 14%) were most frequently identified as challenges. Other barriers specifically noted were underdeveloped health infrastructure and limited allocated resources (n=23,17%) and mis-/negative perception of services (n=15, 11%). Conclusion: PC and CV collaboration occurs for a high proportion of CV patients and is viewed as overwhelming positive, despite the challenges of limited PC specialists availability, underdeveloped healthcare infrastructure, limited understanding of specialty practice, and late referrals. Priorities includes increasing PC provider availability, expanding knowledge of PC services, educating providers on models of collaboration, and improving institutional support.