Galián-Gay, Laura

Abstract Background Aortic valve calcification (AVC), as measured by gold-standard computed tomography (CT) Agatston score, provides an anatomic assessment of aortic stenosis (AS) severity and is a key predictor of AS progression and need for valve replacement. AVC detection and quantification from transthoracic echocardiography (TTE) could expand AS early diagnosis and risk stratification, currently limited by CT availability and radiation exposure. Methods A multi-view video-based deep learning framework was developed using 1166 TTE aortic valve videos from 187 TTE studies acquired in 110 patients with available AVC score by CT. EchoAVC architecture includes a feature extraction model followed by a quality-aware model that aggregates video-level information to obtain patient-level predictions for AVC detection and quantification (score). The framework was validated internally with 173 TTE studies from 86 patients across seven centres, and externally using 430 TTE studies from 280 patients across four different centres. The associations between EchoAVC estimations and AS severity, progression, and need for aortic valve replacement were examined. Results EchoAVC demonstrated excellent performance in AVC detection (AUROC 0.98, accuracy 94.4%), and quantification (R = 0.64) in the external multi-centre testing set. EchoAVC score was correlated with echocardiographic AS severity descriptors, including aortic valve mean pressure gradient (ρ = 0.749) and peak velocity (ρ = 0.757), and predicted future increase in mean pressure gradient (ρ = 0.382), peak velocity (ρ = 0.433) and calcium score by CT (ρ = 0.650). In 361 patients followed for a median of 3.8 years, 139 underwent aortic valve replacement. Baseline presence and extent of AVC as predicted by EchoAVC showed strong risk-stratification power for aortic valve replacement, remarkably in line with those obtained by CT, and incremental over TTE AS descriptors. EchoAVC was further tested in routine clinical practice images, confirming strong associations with AS severity and progression, including stratification for incident AS in previously unaffected individuals (p<0.001). Conclusions EchoAVC enables accurate and non-invasive detection and quantification of AVC, offering substantial diagnostic and prognostic value for aortic stenosis progression and need for valve replacement. This technique holds promise as a scalable tool for early detection and clinical management of aortic valve stenosis. Clinical Perspective What Is New? * Aortic valve calcification can be detected and quantified on standard, two-dimensional transthoracic echocardiography * EchoAVC score is associated with echocardiographic metrics of aortic stenosis severity * EchoAVC predicts progressive increase in aortic stenosis severity and need for aortic valve replacement What Are the Clinical Implications? * This openly available deep learning framework can be used to estimate aortic valve calcium in patients at risk of or presenting aortic stenosis to predict aortic stenosis progression * EchoAVC may help identify patients likely to have high aortic valve calcium and prioritize them for confirmatory CT assessment, thereby supporting earlier identification of calcific aortic valve disease in clinical pathways.

Abstract Background Little is known about clinical outcomes in patients with bicuspid aortic valve (BAV) and ascending aortic diameters ≥50 mm where the elective surgical-indication zone begins. Purpose To assess incident aortic dissection (AoD), post-surgical survival and guideline implementation. Methods Multi-center retrospective study of BAV patients (≥18 years) with maximal root or tubular-ascending aortic diameters ≥50mm detected by transthoracic echocardiography at baseline. Ascertainment of aortic surgery, AoD and death was carried-out at their respective institutions. The primary outcome was AoD: “confirmed” AoD by surgery or death certificate, or “possible” AoD defined as sudden cardiac death of unknown cause by death certificate. Secondary outcomes were aortic surgery, post-surgical survival and guideline implementation. Results We included 506 consecutive BAV patients, mean age 61±14 years, 83% men, mean maximal aortic diameter 52±2 mm at baseline, ascending aorta was the most common segment ≥50mm (85%). During a median follow-up of 7.7 years, 356 (71%) underwent elective surgery (89% of class 1 patients). Early-surgery (≤6 months from baseline) occurred in 195 patients and 311 patients remained “under-surveillance”. Surgery under-surveillance (&gt;6 months from baseline) occurred in 161/311 (52%) patients at 2.6 [IQR: 1.5–4.7] years of follow-up. Surgical mortality was 1.4%. Ten-year post-surgical survival was &gt;90% and similar between early-surgery and surgery under-surveillance (p=0.8). Of 8 AoD events, 3 confirmed and 5 possible (all occurring in unoperated patients under-surveillance), 5 events occurred with maximal aortic baseline diameter ≥55 mm and/or &gt;1 year without clinical follow-up; therefore, under guideline non-compliance. Incidence of confirmed plus possible aortic dissection was 0.37% per year with size 50–54mm, 1.13% per year between 55–59mm, and 10.41% per year with size ≥60mm. Aortic stenosis was associated with AoD (p=0.04) and all-cause death in unoperated patients (p=0.001). Conclusions Our results suggest that BAV patients can be safely followed as per guidelines after aortic diameters enter the elective surgical zone (≥50mm), with excellent post-surgical survival regardless of whether surgery is early- or under-surveillance. Appropriate guideline implementation for surgical thresholds and interval clinical follow-up could have prevented most AoD events. Valvular disease guideline should also be followed to prevent AoD and improve survival in these patients. Funding Acknowledgement Type of funding sources: None.

Background: The aim of this aortic stenosis registry was to investigate the changes of routine echocardiographic indices and strain in patients with moderate-to-severe aortic stenosis over a 6-month follow-up period. Methods: Our aortic stenosis registry is observational, prospective, multicenter registry of nine countries, with 197 patients with aortic valve area less than 1.5 cm 2 . The enrolment took place from January to August 2017. We excluded patients with uncontrolled atrial arrhythmias, pulmonary hypertension or cardiomyopathies, as well as those with hemodynamically significant valvular disease other than aortic stenosis. We included patients who did not require intervention and who had a complete follow-up study. Results: In patients with preserved ejection fraction, left ventricular mass has significantly increased between baseline and follow-up studies (218 ± 34 grams vs 253 ± 29 grams, p = 0.02). However, when indexed to body surface area, there was no significant difference. Left ventricular global longitudinal strain significantly decreased (-19.7 ± -4.8 vs (-16.4 vs -3.8, p = 0.01). Left atrial volume was significantly higher at follow-up (p = 0.035). Right ventricular basal diameter and mid-cavity diameter were greater at the follow-up (p = 0.04 and p = 0.035, respectively). Patients with low-flow low-gradient aortic stenosis had significantly lower global longitudinal strain (-12.3% ± -3.9% vs -19.7% ± -4.8%, p = 0.01). Conclusion: Left atrial dilatation is one of the first changes to take place in low-flow low-gradient aortic stenosis patients even when left ventricular dimensions and function remains intact. Global longitudinal strain is an important determinant of left ventricular systolic and diastolic dysfunction and right ventricular function is an important parameter of aortic stenosis assessment. Accordingly, our registry has further shed the light on these indices role as multisite follow-up of aortic stenosis.