Pursnani, Amit

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.

Abstract Background The MITRAL Trial (Mitral Implantation of TRAnscatheter vaLves) evaluates the safety and feasibility of balloon-expandable aortic transcatheter heart valves in patients with severe mitral valve disease with mitral annular calcification (MAC), failed surgical rings or failed bioprostheses. Purpose We sought to evaluate 4-year outcomes of patients enrolled in the MITRAL trial. Methods This is a prospective study that enrolled 91 high surgical risk patients at 13 sites in the U.S. 30 patients underwent Mitral Valve-in-Valve (MViV), 30 Valve-in-Ring (MViR) and 31 Valve-in-MAC (ViMAC). 4-year outcomes of these patients were evaluated in this analysis. Primary endpoints and key serious adverse events including deaths were adjudicated by an independent Clinical Events Committee. Cardiac computed tomography (CT) and echocardiographic images were evaluated by independent CT and Echocardiographic Core Laboratories. Results Mean age was 74.3±8.9 years. Most patients undergoing MViV and ViMAC were female (MVIV=63.3%, MViR=36.7% and ViMAC=71%). Mean STS score was 9.2±6.6% (MViV 10.2±6.5%, MViR 8.7±4.7%, ViMAC=8.6±8.2%). All-cause mortality at 4 years was higher for ViMAC and MViR: MViV=6.9% (cardiovascular 3.4%), MViR=48.1% (cardiovascular 18.5%), ViMAC=51.9% (cardiovascular 29.6%), p=0.002 (Figure 1). At 4 years, all survivors had ≤1+ mitral regurgitation and most had none or trace mitral regurgitation (MViV=87.5, MViR=33.3% and ViMAC=100%). Mean mitral valve gradients remained stable (MViV=5.9±2.2 mmHg, MViR= 6.6±5.1 mmHg, ViMAC=5.1±1.0 mmHg), Figure 2. Most survivors experienced significant improvement of symptoms and were in NYHA class I-II at 4-year follow-up (MViV=78.9%, MViR=66.7% and ViMAC=66.7%). Conclusions MViV is associated with excellent outcomes at 4 years. MViR and ViMAC were associated with higher mortality at 4 years. However, most survivors in all groups experienced sustained improvement of symptoms and stable THV performance at 4 years. Whether survival bias had an impact on THV performance and improved symptoms at follow-up is not known and deserves further evaluation. Funding Acknowledgement Type of funding sources: Private company. Main funding source(s): Unrestricted Research Grant from Edwards Lifesciences.

Introduction: Transcatheter mitral valve replacement (TMVR) using aortic transcatheter heart valves (THV) is developing as an alternative to surgery for patients with severely degenerated mitral valve (MV) bioprostheses. Retrospective self-reported registries have collected outcomes on these TMVR procedures in the STS/ACC Transcatheter Valve Therapy Registry and in the Valve-in-Valve International Database. Most reported TMVR procedures for failed surgical bioprostheses have been performed using a transapical access approach. A prospective comprehensive evaluation of mitral Valve-in-Valve (VIV) outcomes, including transseptal access has not previously been conducted. Objectives: To evaluate in-hospital and 30-day clinical outcomes of transseptal mitral VIV with SAPIEN 3 THV in patients with very high surgical risk. Methods: Prospective enrollment of very high surgical risk patients with symptomatic severely degenerated MV surgical bioprostheses in 30 patients at 15 sites in the U.S. Candidates were assessed by a case review committee prior to approval. Baseline qualifying echocardiograms and cardiac CT studies were analyzed by independent core labs. Echocardiograms, cardiac CT studies and neurology evaluations were also performed after mitral VIV procedures. Clinical events were adjudicated by a clinical events committee and safety was monitored by a data safety monitoring board. Results: 26 patients have been enrolled between July 2016 and June 2017. Mean age was 83 years, 62% female, mean STS score was 10% and 62% were in New York Heart Association class III or IV. Transseptal access was used in all procedures. Technical success was achieved in all patients and there was no in-hospital mortality. There was no 30-day cardiovascular mortality and 4% (1 patient) 30-day all-cause mortality (1 patient died of asphyxia on day 29 after choking on pills at home), which was lower than the 30-day mortality in the TVT registry (9%). Detailed procedural, in-hospital and 30-day outcomes will be presented on the complete cohort of 30 patients. Conclusions: In patients without surgical alternatives, transseptal mitral ViV procedures in failed surgical bioprostheses are associated with high technical and procedural success and low 30-day mortality.