JACC. Cardiovascular imaging最新文献

{"title":"Electromechanical Window Negativity and Arrhythmic Risk in Arrhythmogenic Mitral Valve Prolapse.","authors":"Peter M Deissler, Anat Berkovitch, Julie Bergh, Karen Harutyunyan, Lobke L Pype, Benedikt Langenberg, Caroline M Van De Heyning, Roy Beinart, Christian Sohns, Philipp Sommer, Paul G A Volders, Kristina H Haugaa, Avi Sabbag, Rachel M A Ter Bekke","doi":"10.1016/j.jcmg.2026.08.017","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.08.017","url":null,"abstract":"<p><strong>Background: </strong>Mitral valve prolapse (MVP) is generally a benign valvular heart disease, but a subset of patients is at particular risk of malignant ventricular arrhythmias (AMVP).</p><p><strong>Objectives: </strong>The authors evaluated the electromechanical window (EMW) as an arrhythmia-risk marker in (A)MVP (the sum of all MVP and AMVP patients).</p><p><strong>Methods: </strong>Healthy controls, patients with MVP without ventricular arrhythmia (MVP/-VA), and patients with AMVP with nonsustained (AMVP/nsVA) or sustained ventricular arrhythmia (AMVP/VA) (ventricular arrhythmia >30 seconds) were retrospectively included from 3 centers (derivation cohort). An independent validation (A)MVP cohort was recruited from 2 centers. EMW was calculated blinded from apical Doppler echocardiography by subtracting the QT time from the simultaneous Q-to-aortic-valve closure time (QAoC).</p><p><strong>Results: </strong>In the derivation cohort (31 controls, 31 MVP/-VA, 29 AMVP/nsVA, 14 AMVP/VA), patients with (A)MVP displayed a borderline shorter QAoCc (P = 0.06) and significantly longer QTc than controls (P < 0.0001), resulting in a more negative EMW (-18 ms [-47 to -8 ms]; P < 0.0001). EMW was most negative in patients with AMVP/VA (-71 ms [-177 to -30 ms]). These findings were reproduced in the validation cohort (n = 76 with [A]MVP), albeit at different absolute values. In a pooled receiver-operating characteristic analysis, EMW identified patients with AMVP/VA with an area under the curve of 0.82 (95% CI: 0.73-0.91), significantly outperforming QTc and QAoCc. An EMW threshold of -30 ms was the optimal cutoff (sensitivity: 0.71; specificity: 0.83). EMW was independently associated with AMVP/VA status and improved model performance in addition to established risk parameters.</p><p><strong>Conclusions: </strong>EMW is markedly negative in patients with AMVP/VA, reflecting electromechanical discordance. Thus, EMW emerges as a promising risk-associated marker in (A)MVP.</p>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149227842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Patient-Level Perivascular Adipose Tissue Density Aggregation and Plaque Progression: Plaque-Free vs Plaque-Adjacent Segments.","authors":"Sang-Eun Lee, Ji Min Sung, Daniele Andreini, Mouaz H Al-Mallah, Matthew J Budoff, Filippo Cademartiri, Kavitha Chinnaiyan, Jung Hyun Choi, Eun Ju Chun, Edoardo Conte, Ilan Gottlieb, Martin Hadamitzky, Yong Jin Kim, Byoung Kwon Lee, Jonathon A Leipsic, Erica Maffei, Hugo Marques, Pedro de Araújo Gonçalves, Gianluca Pontone, Peter H Stone, Renu Virmani, Jagat Narula, Leslee J Shaw, Jeroen J Bax, Fay Y Lin, James K Min, Hyuk-Jae Chang","doi":"10.1016/j.jcmg.2026.08.018","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.08.018","url":null,"abstract":"<p><strong>Background: </strong>Perivascular adipose tissue (PVAT) density on coronary computed tomography angiography (CTA) reflects pericoronary inflammation, but measurements adjacent to existing plaques may be confounded by local inflammatory signaling from the plaque itself-a form of reverse causation. Whether systematically comparing patient-level PVAT aggregation approaches (including measurements restricted to plaque-free segments) can identify a more robust inflammatory biomarker has not been evaluated.</p><p><strong>Objectives: </strong>The authors aimed to compare the predictive performance of 4 patient-level PVAT aggregation approaches for coronary plaque progression.</p><p><strong>Methods: </strong>From the PARADIGM serial coronary CTA registry, 412 patients with baseline coronary plaque who underwent serial coronary CTA at identical tube voltages were included (mean age: 61.1 ± 9.3 years; 61.7% male; mean interval: 3.2 ± 1.2 years). Four patient-level PVAT measures were compared: proximal right coronary artery (pRCA), whole-coronary, plaque-free, and plaque PVAT. Multivariable regression models were constructed for annualized plaque volume (PV) progression with adjustment for clinical risk factors and imaging covariates.</p><p><strong>Results: </strong>Annualized increases in pRCA PVAT (β = 0.804; P = 0.033), whole-coronary PVAT (β = 1.142; P = 0.022), and plaque-free PVAT (β = 1.419; P = 0.007) were each independently associated with total PV progression, whereas plaque PVAT did not reach significance (β = 0.755; P = 0.083). For noncalcified PV progression, plaque-free PVAT was the only significant measure (β = 1.086; P = 0.026). None of the 4 baseline PVAT measures were significantly associated with plaque progression (all P > 0.50). Pairwise comparisons revealed no significant differences among the 4 measures.</p><p><strong>Conclusions: </strong>Changes in pRCA, whole-coronary, and plaque-free PVAT were each independently associated with total PV progression. For noncalcified PV progression, plaque-free PVAT change was the only significant measure. (Progression of AtheRosclerotic PlAque DetermIned by Computed TomoGraphic Angiography Imaging [PARADIGM]; NCT02803411).</p>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149227808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of Severity of Chronic Aortic Regurgitation: Importance of a Hierarchical Approach to Echocardiogram Doppler Parameters.","authors":"Jad Zeitoun, Maan Malahfji, Rowa Attar, Clara Angulo, Dipan J Shah, William A Zoghbi","doi":"10.1016/j.jcmg.2026.08.009","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.08.009","url":null,"abstract":"","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149194136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Calcium Density as a Marker of Coronary Plaque Stabilization in Primary Prevention: The CAUGHT-CAD Trial.","authors":"Sheran A Vasanthakumar, Stephen J Nicholls, Nitesh Nerlekar, Thomas H Marwick, Andrew Lin","doi":"10.1016/j.jcmg.2026.07.029","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.07.029","url":null,"abstract":"<p><strong>Background: </strong>Despite primary prevention statin treatment, a substantial proportion of individuals remain at residual risk for cardiovascular events. Coronary computed tomographic angiography (CTA) enables the quantification of compositional changes in calcified plaque.</p><p><strong>Objectives: </strong>The aim of this study was to examine whether increases in coronary calcified plaque volume and density associated with statin therapy could be used as a marker of plaque stabilization in asymptomatic individuals undergoing serial coronary CTA.</p><p><strong>Methods: </strong>In the CAUGHT-CAD trial, asymptomatic, statin-naive, intermediate-risk individuals were randomized to a primary prevention strategy (including statin treatment) vs usual care. Participants underwent coronary CTA at baseline and 3 years. In this post hoc analysis, volumes of 5 plaque subtypes were quantified: noncalcified (≤350 HU), low-density calcium (351-500 HU), intermediate-density calcium (501-700 HU), high-density calcium (701-1000 HU), and very high density calcium (>1,000 HU). The primary outcome was the per-lesion level change in volumes of calcified plaque subtypes.</p><p><strong>Results: </strong>Eight hundred forty lesions were included from 338 participants (mean age: 58.3 ± 6.9 years, 57.1% men, 161 [47.6%] statin treated). Statin treatment was associated with greater progression in intermediate-density (β = 0.89, SE = 0.39; P = 0.02) and high-density (β = 0.79, SE = 0.24; P = 0.001) calcium, alongside regression of noncalcified plaque (β = -9.83, SE = 1.64; P < 0.001), following adjustment for cardiovascular risk factors, low-density lipoprotein cholesterol (LDL-C) level, and baseline plaque volume. Among statin-treated participants, LDL-C reduction ≥30% was associated with greater progression of high-density (β = 1.11, SE = 0.49; P = 0.03) and very high density (β = 1.68, SE = 0.85; P = 0.04) calcium.</p><p><strong>Conclusions: </strong>In asymptomatic, intermediate-risk individuals, statin treatment was associated with a shift toward higher density calcium within coronary plaques, most marked with effective lowering of LDL-C. (Coronary Artery Calcium Score: Use to Guide Management of Hereditary Coronary Artery Disease [CAUGHT-CAD]; ACTRN12614001294640).</p>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149194132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing Echocardiographic Evaluation of Chronic Mitral Regurgitation: Comparison With Cardiac Magnetic Resonance Imaging and Implications for Guideline Recommendations.","authors":"K Carlos El-Tallawi, Clara Angulo, Mohammed Chamsi-Pasha, Fatima Qamar, Edward A Graviss, Dipan J Shah, William A Zoghbi","doi":"10.1016/j.jcmg.2026.07.025","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.07.025","url":null,"abstract":"<p><strong>Background: </strong>The ASE (American Society of Echocardiography) guidelines recommend the presence of at least 4 specific criteria to confirm a diagnosis of definite severe mitral regurgitation (MR). However, the performance of these criteria, particularly when <4 are present, remains unclear.</p><p><strong>Objectives: </strong>This study aims to evaluate and optimize the ASE native MR guidelines by comparing them with quantitative cardiac magnetic resonance (CMR), considered the reference standard for MR assessment.</p><p><strong>Methods: </strong>In this prospective study, 177 patients underwent near-simultaneous CMR and transthoracic echocardiography for the assessment of MR. MR severity was classified using a 4-grade scale based on CMR-derived regurgitant volume, which was calculated as the difference between total left ventricular (LV) stroke volume and aortic forward flow. MR severity was similarly graded using the ASE algorithm, with quantification performed when necessary, by averaging the regurgitant volume from 3 methods: 1) the proximal isovelocity surface area method; 2) the biplane LV volumetric method; and 3) the mitral valve volumetric method.</p><p><strong>Results: </strong>The study cohort had a median age of 61.7 years, with 55% being men. Primary MR was the predominant pathology (73% of patients), with 42% having mitral valve prolapse and 25% presenting with flail leaflets. There was exact agreement between transthoracic echocardiography and CMR MR grading in 51% of cases, whereas agreement within 1 grade was observed in 89%. Patients who met any of the ASE severe MR criteria were predominantly classified as having grades 3 to 4 MR by CMR. The following ASE parameters demonstrated high specificity for identifying grade 4 MR by CMR: pulmonary vein systolic flow reversal (specificity 88%), enlarged LV with normal systolic function (specificity 85%), proximal isovelocity surface area radius ≥1.0 cm (specificity 83%), and vena contracta width ≥0.7 cm (specificity 80%). Combining color Doppler with either pulmonary vein systolic reversal or enlarged LV with normal function resulted in 91%-95% specificity for severe MR. Importantly, reliance on fewer ASE criteria reduced the need for quantification from 86% (4 criteria) to 73% (3 criteria) and 59% (2 criteria), thereby enhancing diagnostic efficiency.</p><p><strong>Conclusions: </strong>Certain ASE criteria, especially when used in combination, are highly specific for diagnosing severe MR, even when <4 criteria are present. This study suggests that in many cases, the reliance on extensive quantification may be reduced, streamlining the diagnostic process and improving clinical workflow.</p>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149194127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bending the Curve: Revealing Population Risk With Quantitative Atherosclerotic Plaque.","authors":"Leslee J Shaw, Ron Blankstein, Damini Dey, Thomias H Marwick","doi":"10.1016/j.jcmg.2026.09.002","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.09.002","url":null,"abstract":"","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149181903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Left Ventricular Filling Pressure Classification by Electrocardiogram, Echocardiography, and Catheterization: Prognostic Implications.","authors":"Gal Tsaban, Eunjung Lee, Francisco Lopez-Jimenez, William R Miranda, Garvan C Kane, Horng H Chen, Abhishek J Deshmukh, Samuel J Asirvatham, Peter A Noseworthy, Rajiv Gulati, Paul A Friedman, Zachi Attia, Jae K Oh","doi":"10.1016/j.jcmg.2026.08.016","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.08.016","url":null,"abstract":"<p><strong>Background: </strong>Left ventricular diastolic filling pressure (LVFP) is a hallmark of heart failure. Although pulmonary artery wedge pressure (PAWP) measured during right heart catheterization (RHC) is the reference standard, echocardiography is more commonly used in practice.</p><p><strong>Objectives: </strong>The authors previously developed an artificial intelligence-enabled electrocardiographic (AI-ECG) algorithm, trained on echocardiographic assessment, to classify LVFP. The aim of this study was to evaluate the prognostic implications of LVFP classification by AI-ECG, echocardiography, and PAWP among patients undergoing temporally proximate testing.</p><p><strong>Methods: </strong>Adults who underwent echocardiography with electrocardiography within 14 days and RHC within 30 days were included. Elevated LVFP was defined as PAWP ≥15 mm Hg, grade 2 or 3 diastolic dysfunction by echocardiography, or elevated LVFP as classified by AI-ECG. Associations with all-cause mortality and major adverse cardiovascular events were assessed.</p><p><strong>Results: </strong>Among 4,168 patients (median age: 64 years; 47.7% women), elevated LVFP was classified by AI-ECG in 2,383 patients, by echocardiography in 1,643, and by PAWP in 1,841. AI-ECG showed good discrimination for echocardiographic LVFP (AUC: 0.879; 95% CI: 0.867-0.891) and moderate discrimination for PAWP (AUC: 0.711; 95% CI: 0.695-0.727). Over 7.7 years, 1,433 deaths occurred. Elevated LVFP classification by AI-ECG (adjusted HR [aHR]: 1.80; 95% CI: 1.55-2.09) and echocardiography (aHR: 1.74; 95% CI: 1.51-2.02) showed stronger associations with mortality than PAWP (aHR: 1.18; 95% CI: 1.05-1.31); in discordant cases, AI-ECG better predicted survival. Similar associations were observed for major adverse cardiovascular events.</p><p><strong>Conclusions: </strong>Despite moderate agreement with PAWP, echocardiography and AI-ECG showed stronger associations with clinical outcomes, suggesting they capture prognostically relevant myocardial information beyond resting hemodynamic status.</p>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149194159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association of Lipoprotein(a) and Low-Attenuation Plaque Burden With Future Myocardial Infarction.","authors":"Daniel Isenstein, Mohammed N Meah, Andrew R Chapman, Takeshi Fujisawa, Damini Dey, Marc R Dweck, Nicholas L Mills, David E Newby, Michelle C Williams, Ryan Wereski","doi":"10.1016/j.jcmg.2026.09.003","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.09.003","url":null,"abstract":"","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149181820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identifying the High-Risk Arrhythmic Mitral Valve Prolapse Phenotype by Imaging.","authors":"Ritu Thamman, Kristina H Haugaa, Judy Hung, Francesca N Delling","doi":"10.1016/j.jcmg.2026.07.028","DOIUrl":"https://doi.org/10.1016/j.jcmg.2026.07.028","url":null,"abstract":"<p><p>Within arrhythmogenic mitral valve prolapse (AMVP), a distinct subset of mitral valve prolapse (MVP), there is a small group that carries a higher risk of malignant ventricular arrhythmias and sudden cardiac death called malignant MVP. The malignant MVP phenotype is over-represented in young women with unexplained sudden cardiac death on autopsy. AMVP is defined by myxomatous, often bileaflet MVP with mitral annular disjunction, abnormal valvular-myocardial mechanics, complex ventricular ectopy, and nonsustained ventricular tachycardia. Excessive mechanical force from systolic annular expansion, papillary muscle traction, and basal inferolateral \"curling\" promotes focal replacement and diffuse interstitial fibrosis, creating an arrhythmogenic substrate. Premature ventricular contractions act as triggers, whereas autonomic modulation influences the timing of ventricular arrhythmia initiation and progression to ventricular fibrillation or sustained monomorphic ventricular tachycardia. Baseline evaluation with an electrocardiogram and transthoracic echocardiography is necessary to identify AMVP, exclude severe mitral regurgitation, and identify high-risk markers. If no premature ventricular contractions are found on a resting electrocardiogram, exercise stress testing and extended rhythm monitoring can help bring out ventricular premature contractions, which are triggers of ventricular arrhythmias. Cardiac magnetic resonance provides incremental prognostic value with late gadolinium enhancement reflecting replacement fibrosis and T1 mapping identifying diffuse fibrosis, even in those with no late gadolinium enhancement. Machine-learning analysis may further refine risk stratification by integrating high-risk features such as mitral annular disjunction, fibrosis extent, and location that outperform symptom-based assessment. As transcatheter and surgical mitral interventions expand, accurate phenotyping of AMVP is increasingly important, as hemodynamic correction of mitral regurgitation alone does not eliminate the underlying arrhythmogenic substrate. Comprehensive multimodality imaging and integrated rhythm assessment are therefore central to individualized risk stratification and management in this vulnerable population.</p>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":19.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149181875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive Aortic Stenosis Characterization Using Multiview Deep Learning","authors":"Hirotaka Ieki MD, PhD,&nbsp;Yuki Sahashi MD, PhD,&nbsp;Miloš Vukadinovic BS,&nbsp;Meenal Rawlani MSc,&nbsp;Christina Binder MD, PhD,&nbsp;Neal Yuan MD,&nbsp;Andrew P. Ambrosy MD,&nbsp;Alan S. Go MD,&nbsp;Wansu Chen PhD,&nbsp;Ming-Sum Lee MD, PhD,&nbsp;Bryan He PhD,&nbsp;Paul Cheng MD, PhD,&nbsp;David Ouyang MD","doi":"10.1016/j.jcmg.2026.07.013","DOIUrl":"10.1016/j.jcmg.2026.07.013","url":null,"abstract":"<div><h3>Background</h3><div>Accurate assessment of aortic stenosis (AS) requires integration of both structural and functional information characterized by visual traits as well as quantitation of gradients. Existing artificial intelligence models use solely either structural or functional information.</div></div><div><h3>Objectives</h3><div>The authors aimed to develop and validate an automated multiview deep learning framework to assess AS severity.</div></div><div><h3>Methods</h3><div>The authors developed EchoNet-AS, an open-source end-to-end integrated approach combining video-based convolutional neural networks to assess valve motion with segmentation models to automate measurement of aortic valve peak velocity and classify AS severity.</div></div><div><h3>Results</h3><div>EchoNet-AS was trained on 210,193 images from 16,076 studies from KPNC (Kaiser Permanente Northern California) and validated on 1,588 held-out test studies and a temporally distinct cohort of 19,202 studies. The final model was also externally validated on 2,415 studies from SHC (Stanford Healthcare) and 9,038 studies from CSMC (Cedars-Sinai Medical Center). Combining assessments from multiple echocardiographic videos and Doppler measurements, EchoNet-AS achieved excellent discrimination of severe AS with an area under the receiver-operating characteristic curve of 0.964 (95% CI: 0.952-0.973) in the KPNC held-out cohort and 0.986 (0.983-0.989) in the temporally distinct cohort, which was superior to models using single views or only Doppler measurements. The performance was consistently robust in distinct external cohorts with an area under the receiver-operating characteristic curve of 0.985 (0.975-0.992) at SHC and 0.989 (0.986-0.992) at CSMC.</div></div><div><h3>Conclusions</h3><div>EchoNet-AS synthesizes information from both B-mode videos and Doppler images to accurately assess AS severity. Its strong performance generalizes robustly to external validation cohorts and shows potential as an automated clinical decision support tool.</div></div>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":"19 10","pages":"Pages 1186-1200"},"PeriodicalIF":19.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149088760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}