Pub Date : 2026-01-01DOI: 10.1016/j.jcmg.2025.08.011
Mostafa A. Al-Alusi MD, MS , Emily S. Lau MD, MPH , Aeron M. Small MD, MTR , Christopher Reeder PhD , Tal Shnitzer PhD , Carl T. Andrews MS , Shinwan Kany MD , Joel T. Rämö MD , Julian S. Haimovich MD , Shaan Khurshid MD, MPH , Danita Y. Sanborn MD, MMSc , Michael H. Picard MD , Jennifer E. Ho MD , Mahnaz Maddah PhD , Patrick T. Ellinor MD, PhD
Background
Mitral valve prolapse (MVP) has a prevalence of 2% to 3% and increases risk of heart failure and sudden death, but diagnosis by transthoracic echocardiography requires time and expertise.
Objectives
This study aims to develop a deep learning model DROID-MVP (Dimensional Reconstruction of Imaging Data–Mitral Valve Prolapse) to classify MVP from digital echocardiogram videos.
Methods
DROID-MVP was trained and validated using 1,043,893 echocardiogram videos (48,829 studies) from 16,902 cardiology patients at MGH (Massachusetts General Hospital), and externally validated in 8,888 MGH primary care patients and 257 primary care patients at BWH (Brigham and Women’s Hospital). The authors tested associations among DROID-MVP predictions (range: 0-1), mitral regurgitation (MR) severity, and mitral valve repair or replacement (MVR).
Results
Of 16,902 patients (6,391 [38%] women; age 61 ± 16 years) in the derivation sample, 783 (4.6%) had MVP. DROID-MVP accurately identified MVP across the MGH cardiology internal validation set (area under the receiver-operating characteristic curve [AUROC]: 0.947 [95% CI: 0.910-0.984]; average precision [AP]: 0.682 [95% CI: 0.565-0.784]; prevalence: 0.036), MGH primary care external validation set (AUROC: 0.964 [95% CI: 0.951-0.977]; AP: 0.651 [95% CI: 0.578-0.716]; prevalence: 0.022), and BWH primary care external validation set (AUROC: 0.968 [95% CI: 0.946-0.989]; AP: 0.774 [95% CI: 0.666-0.797]; prevalence: 0.113). A high (>0.67) vs low (<0.33) DROID-MVP score was associated with moderate or severe MR (adjusted OR: 2.0 [95% CI: 1.1-3.8]; P = 0.030) and future MVR (adjusted HR: 3.7 [95% CI: 1.5-8.9]; P = 0.004).
Conclusions
A deep learning model identifies MVP from echocardiogram videos, and model predictions are associated with clinical endpoints including MR and future MVR. Deep learning can automate MVP diagnosis and potentially generate digital markers of clinically significant MVP.
背景：二尖瓣脱垂（MVP）的患病率为2%至3%，并增加心力衰竭和猝死的风险，但经胸超声心动图诊断需要时间和专业知识。目的建立深度学习模型DROID-MVP （Dimensional Reconstruction of Imaging data -二尖瓣脱垂），对数字超声心动图视频中的二尖瓣脱垂进行分类。方法sdroid - mvp通过来自麻省总医院（MGH） 16902名心脏病患者的1,043,893个超声心动图视频（48,829项研究）进行培训和验证，并在8888名MGH初级保健患者和257名BWH （Brigham and Women Hospital）初级保健患者中进行外部验证。作者测试了DROID-MVP预测（范围：0-1）、二尖瓣反流（MR）严重程度和二尖瓣修复或置换（MVR）之间的关系。结果在衍生样本的16902例患者中（6391例（38%）女性，年龄61±16岁），783例（4.6%）有MVP。DROID-MVP准确识别了MGH心内科内部验证集（患者工作特征曲线下面积[AUROC]: 0.947 [95% CI: 0.910-0.984]，平均精度[AP]: 0.682 [95% CI: 0.565-0.784]，患病率：0.036），MGH初级保健外部验证集（AUROC: 0.964 [95% CI: 0.951-0.977], AP: 0.651 [95% CI: 0.578-0.716]，患病率：0.022），BWH初级保健外部验证集(AUROC: 0.968 [95% CI: 0.946-0.989], AP: 0.774 [95% CI: 0.666-0.797]；流行:0.113)。高（>0.67）vs低（<0.33）DROID-MVP评分与中度或重度MR（校正or: 2.0 [95% CI: 1.1-3.8]; P = 0.030）和未来MVR（校正HR: 3.7 [95% CI: 1.5-8.9]; P = 0.004）相关。结论深度学习模型从超声心动图视频中识别MVP，模型预测与临床终点相关，包括MR和未来MVR。深度学习可以自动诊断MVP，并可能生成具有临床意义的MVP的数字标记。
{"title":"A Deep Learning Model to Identify Mitral Valve Prolapse From the Echocardiogram","authors":"Mostafa A. Al-Alusi MD, MS , Emily S. Lau MD, MPH , Aeron M. Small MD, MTR , Christopher Reeder PhD , Tal Shnitzer PhD , Carl T. Andrews MS , Shinwan Kany MD , Joel T. Rämö MD , Julian S. Haimovich MD , Shaan Khurshid MD, MPH , Danita Y. Sanborn MD, MMSc , Michael H. Picard MD , Jennifer E. Ho MD , Mahnaz Maddah PhD , Patrick T. Ellinor MD, PhD","doi":"10.1016/j.jcmg.2025.08.011","DOIUrl":"10.1016/j.jcmg.2025.08.011","url":null,"abstract":"<div><h3>Background</h3><div>Mitral valve prolapse (MVP) has a prevalence of 2% to 3% and increases risk of heart failure and sudden death, but diagnosis by transthoracic echocardiography requires time and expertise.</div></div><div><h3>Objectives</h3><div>This study aims to develop a deep learning model DROID-MVP (Dimensional Reconstruction of Imaging Data–Mitral Valve Prolapse) to classify MVP from digital echocardiogram videos.</div></div><div><h3>Methods</h3><div>DROID-MVP was trained and validated using 1,043,893 echocardiogram videos (48,829 studies) from 16,902 cardiology patients at MGH (Massachusetts General Hospital), and externally validated in 8,888 MGH primary care patients and 257 primary care patients at BWH (Brigham and Women’s Hospital). The authors tested associations among DROID-MVP predictions (range: 0-1), mitral regurgitation (MR) severity, and mitral valve repair or replacement (MVR).</div></div><div><h3>Results</h3><div>Of 16,902 patients (6,391 [38%] women; age 61 ± 16 years) in the derivation sample, 783 (4.6%) had MVP. DROID-MVP accurately identified MVP across the MGH cardiology internal validation set (area under the receiver-operating characteristic curve [AUROC]: 0.947 [95% CI: 0.910-0.984]; average precision [AP]: 0.682 [95% CI: 0.565-0.784]; prevalence: 0.036), MGH primary care external validation set (AUROC: 0.964 [95% CI: 0.951-0.977]; AP: 0.651 [95% CI: 0.578-0.716]; prevalence: 0.022), and BWH primary care external validation set (AUROC: 0.968 [95% CI: 0.946-0.989]; AP: 0.774 [95% CI: 0.666-0.797]; prevalence: 0.113). A high (>0.67) vs low (<0.33) DROID-MVP score was associated with moderate or severe MR (adjusted OR: 2.0 [95% CI: 1.1-3.8]; <em>P =</em> 0.030) and future MVR (adjusted HR: 3.7 [95% CI: 1.5-8.9]; <em>P =</em> 0.004).</div></div><div><h3>Conclusions</h3><div>A deep learning model identifies MVP from echocardiogram videos, and model predictions are associated with clinical endpoints including MR and future MVR. Deep learning can automate MVP diagnosis and potentially generate digital markers of clinically significant MVP.</div></div>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":"19 1","pages":"Pages 18-29"},"PeriodicalIF":15.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145194449","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}
Pub Date : 2026-01-01DOI: 10.1016/j.jcmg.2025.08.008
Ali Ali MD, William R. Miranda MD, Christopher Francois MD, Sara ElZalabany MBBCh, Amr Moustafa MBBCh, Heidi M. Connolly MD, Alexander C. Egbe MD, MPH, MS
{"title":"Predictors and Prognostic Implications of Progressive Systemic Ventricular Dysfunction in Adults With Fontan Palliation","authors":"Ali Ali MD, William R. Miranda MD, Christopher Francois MD, Sara ElZalabany MBBCh, Amr Moustafa MBBCh, Heidi M. Connolly MD, Alexander C. Egbe MD, MPH, MS","doi":"10.1016/j.jcmg.2025.08.008","DOIUrl":"10.1016/j.jcmg.2025.08.008","url":null,"abstract":"","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":"19 1","pages":"Pages 139-141"},"PeriodicalIF":15.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145068393","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}
Pub Date : 2026-01-01DOI: 10.1016/j.jcmg.2025.08.002
Vignesh Chidambaram MD, MPH, Amudha Kumar MD, Munthir Mansour MD, Ryan Pohlkamp MD, Marie Gilbert Majella MD, Joshua Mueller MD, Jawahar L. Mehta MD, PhD, Mark G. Rabbat MD, Armin Arbab-Zadeh MD, PhD, MPH, Ron Blankstein MD, Roger S. Blumenthal MD, Pamela S. Douglas MD, Subhi J. Al’Aref MD
{"title":"Coronary CTA vs Stress Testing in Stable Angina With Moderate Renal Dysfunction","authors":"Vignesh Chidambaram MD, MPH, Amudha Kumar MD, Munthir Mansour MD, Ryan Pohlkamp MD, Marie Gilbert Majella MD, Joshua Mueller MD, Jawahar L. Mehta MD, PhD, Mark G. Rabbat MD, Armin Arbab-Zadeh MD, PhD, MPH, Ron Blankstein MD, Roger S. Blumenthal MD, Pamela S. Douglas MD, Subhi J. Al’Aref MD","doi":"10.1016/j.jcmg.2025.08.002","DOIUrl":"10.1016/j.jcmg.2025.08.002","url":null,"abstract":"","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":"19 1","pages":"Pages 136-138"},"PeriodicalIF":15.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145032099","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}
Pub Date : 2026-01-01DOI: 10.1016/j.jcmg.2025.08.020
Brittany N. Weber MD, PhD , David W. Biery AB , Milena Petranovic MD , Stephanie A. Besser MSAS, MSPA , Daniel M. Huck MD, MPH , Arthur Shiyovich MD , Rhanderson Cardoso MD , Adam N. Berman MD, MPH , Camila V. Blair MD , Nayruti Trivedi MS , Micheal S. Garshick MD , Joseph Merola MD , Karen Costenbader MD , Leslee J. Shaw PhD , Khurram Nasir MD, MPH , Katherine P. Liao MD , Marcelo F. Di Carli MD , Ron Blankstein MD
Background
Coronary artery calcium (CAC) scoring is strongly associated with cardiovascular (CV) events among the general population; however, its prognostic value among individuals with immune-mediated inflammatory diseases (IMIDs) is not well characterized.
Objectives
This study aims to assess the prevalence of CAC derived from routine chest computed tomography (CT) using a validated artificial intelligence (AI) algorithm and its association with adverse CV events among those with IMIDs.
Methods
The authors studied a retrospective cohort of all patients 40 to 70 years of age with a diagnosis of systemic lupus erythematosus, rheumatoid arthritis, or psoriatic disease, and no prior atherosclerotic cardiovascular disease who underwent chest CT at 2 medical centers in Boston, Massachusetts, USA, from 2000 to 2023 as part of routine care. The presence and severity of CAC was determined using a validated AI methodology. Cox proportional hazards modeling was used to assess the association of CAC-AI categories (CAC-AI = 0, CAC-AI = 1-99, and CAC-AI ≥100) with all-cause mortality and major adverse cardiovascular events (MACE) (nonfatal myocardial infarction, coronary revascularization, nonfatal stroke, or CV mortality). All models were adjusted for age, sex, and traditional CV risk factors.
Results
In total, 2,546 individuals with IMIDs (median age: 59 years [Q1-Q3: 53-65 years]; 1,694 [66.5%] women) were included with a median follow-up of 8.1 years. Among this cohort, 53% had CAC-AI >0 while only 6.0% were on a statin. A low burden of CAC (CAC-AI = 1-99) was associated with an increased risk of all-cause mortality (adjusted HR: 1.41; P = 0.010) and MACE (adjusted HR: 2.05; P < 0.001) with even greater risk observed among individuals with CAC-AI ≥100 (adjusted HR: 2.45; P < 0.001) and MACE (adjusted HR: 3.24; P < 0.001).
Conclusions
Among those with IMIDs, incidental CAC-AI was highly prevalent and significantly associated with both all-cause mortality and MACE. These findings suggest that CAC-AI may provide important prognostic information, allowing for improved risk stratification and treatment within an already high-risk and undertreated population.
背景：在普通人群中，冠状动脉钙（CAC）评分与心血管（CV）事件密切相关；然而，其在免疫介导性炎症性疾病（IMIDs）患者中的预后价值尚未得到很好的表征。目的：本研究旨在利用一种经过验证的人工智能（AI）算法评估常规胸部计算机断层扫描（CT）中CAC的患病率及其与IMIDs患者不良CV事件的关系。方法：作者研究了一项回顾性队列研究，研究对象为年龄在40 - 70岁之间，诊断为系统性红斑狼疮、类风湿性关节炎或银屑病，且既往无动脉粥样硬化性心血管疾病的患者，这些患者于2000年至2023年在美国马萨诸塞州波士顿的2个医疗中心接受了胸部CT检查，作为常规护理的一部分。使用经过验证的人工智能方法确定CAC的存在和严重程度。采用Cox比例风险模型评估CAC-AI类别（CAC-AI = 0、CAC-AI = 1-99和CAC-AI≥100）与全因死亡率和主要不良心血管事件（MACE）（非致死性心肌梗死、冠状动脉血运重建术、非致死性卒中或CV死亡率）的相关性。所有模型都根据年龄、性别和传统的心血管危险因素进行了调整。结果共纳入2546例IMIDs患者（中位年龄59岁[Q1-Q3: 53-65岁]，女性1694例[66.5%]），中位随访8.1年。在该队列中，53%的患者患有CAC-AI，而只有6.0%的患者服用他汀类药物。低CAC负担（CAC- ai = 1-99）与全因死亡（校正HR: 1.41, P = 0.010）和MACE（校正HR: 2.05, P < 0.001）的风险增加相关，且CAC- ai≥100（校正HR: 2.45, P < 0.001）和MACE（校正HR: 3.24, P < 0.001）的风险更大。结论在IMIDs患者中，偶发CAC-AI非常普遍，并与全因死亡率和MACE显著相关。这些发现表明，CAC-AI可能提供重要的预后信息，允许在已经高风险和治疗不足的人群中改进风险分层和治疗。
{"title":"Prevalence and Prognostic Value of Incidentally Detected Coronary Artery Calcium Using Artificial Intelligence Among Individuals With Immune-Mediated Inflammatory Diseases","authors":"Brittany N. Weber MD, PhD , David W. Biery AB , Milena Petranovic MD , Stephanie A. Besser MSAS, MSPA , Daniel M. Huck MD, MPH , Arthur Shiyovich MD , Rhanderson Cardoso MD , Adam N. Berman MD, MPH , Camila V. Blair MD , Nayruti Trivedi MS , Micheal S. Garshick MD , Joseph Merola MD , Karen Costenbader MD , Leslee J. Shaw PhD , Khurram Nasir MD, MPH , Katherine P. Liao MD , Marcelo F. Di Carli MD , Ron Blankstein MD","doi":"10.1016/j.jcmg.2025.08.020","DOIUrl":"10.1016/j.jcmg.2025.08.020","url":null,"abstract":"<div><h3>Background</h3><div>Coronary artery calcium (CAC) scoring is strongly associated with cardiovascular (CV) events among the general population; however, its prognostic value among individuals with immune-mediated inflammatory diseases (IMIDs) is not well characterized.</div></div><div><h3>Objectives</h3><div>This study aims to assess the prevalence of CAC derived from routine chest computed tomography (CT) using a validated artificial intelligence (AI) algorithm and its association with adverse CV events among those with IMIDs.</div></div><div><h3>Methods</h3><div>The authors studied a retrospective cohort of all patients 40 to 70 years of age with a diagnosis of systemic lupus erythematosus, rheumatoid arthritis, or psoriatic disease, and no prior atherosclerotic cardiovascular disease who underwent chest CT at 2 medical centers in Boston, Massachusetts, USA, from 2000 to 2023 as part of routine care. The presence and severity of CAC was determined using a validated AI methodology. Cox proportional hazards modeling was used to assess the association of CAC-AI categories (CAC-AI = 0, CAC-AI = 1-99, and CAC-AI ≥100) with all-cause mortality and major adverse cardiovascular events (MACE) (nonfatal myocardial infarction, coronary revascularization, nonfatal stroke, or CV mortality). All models were adjusted for age, sex, and traditional CV risk factors.</div></div><div><h3>Results</h3><div>In total, 2,546 individuals with IMIDs (median age: 59 years [Q1-Q3: 53-65 years]; 1,694 [66.5%] women) were included with a median follow-up of 8.1 years. Among this cohort, 53% had CAC-AI >0 while only 6.0% were on a statin. A low burden of CAC (CAC-AI = 1-99) was associated with an increased risk of all-cause mortality (adjusted HR: 1.41; <em>P =</em> 0.010) and MACE (adjusted HR: 2.05; <em>P <</em> 0.001) with even greater risk observed among individuals with CAC-AI ≥100 (adjusted HR: 2.45; <em>P <</em> 0.001) and MACE (adjusted HR: 3.24; <em>P <</em> 0.001).</div></div><div><h3>Conclusions</h3><div>Among those with IMIDs, incidental CAC-AI was highly prevalent and significantly associated with both all-cause mortality and MACE. These findings suggest that CAC-AI may provide important prognostic information, allowing for improved risk stratification and treatment within an already high-risk and undertreated population.</div></div>","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":"19 1","pages":"Pages 64-75"},"PeriodicalIF":15.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145373948","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}
Pub Date : 2026-01-01DOI: 10.1016/j.jcmg.2025.09.017
Milind Y. Desai MD, MBA, Susan K. Keen MD
{"title":"Straining the Limits of Sudden Death Risk Stratification","authors":"Milind Y. Desai MD, MBA, Susan K. Keen MD","doi":"10.1016/j.jcmg.2025.09.017","DOIUrl":"10.1016/j.jcmg.2025.09.017","url":null,"abstract":"","PeriodicalId":14767,"journal":{"name":"JACC. Cardiovascular imaging","volume":"19 1","pages":"Pages 46-48"},"PeriodicalIF":15.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145373890","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号