Barrett‐O’Keefe, Zachary

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.

AbstractHeightened muscle sympathetic nerve activity (MSNA) contributes to impaired vasodilatory capacity and vascular dysfunction associated with aging and cardiovascular disease. The contribution of elevated MSNA to the vasodilatory response during passive leg movement (PLM) is not fully understood. This study tested the hypothesis that elevated MSNA diminishes the vasodilatory response to PLM in healthy young males (n = 11, 25 ± 2 yr). Post exercise circulatory occlusion (PECO) following 2 min of isometric handgrip (HG) exercise performed at 25% (ExPECO 25%) and 40% (ExPECO 40%) maximum voluntary contraction was used to incrementally engage the metaboreceptors and augment MSNA. Control trials were performed without PECO (ExCON 25% and ExCON 40%) to account for changes due to HG exercise. PLM was performed 2 min after exercise and hemodynamics were assessed. MSNA was recorded by microneurography in the peroneal nerve (n = 8). Measures of MSNA (i.e., burst incidences) increased during ExPECO 25% (+15 ± 5 burst/100 bpm) and ExPECO 40% (+22 ± 4 burst/100 bpm) and returned to pre‐HG levels during ExCON trials. Leg vascular conductance (vasodilation) during PLM was reduced by 16% and 44% during ExPECO 25% and ExPECO 40%, respectively. These findings indicate elevated MSNA attenuates the vasodilatory response to PLM and the magnitude of reduction in vasodilation during PLM is graded with the degree of sympathoexcitation.