Vrudhula Amey, Vukadinovic Milos, Haeffele Christiane, Kwan Alan C, Berman Daniel, Liang David, Siegel Robert, Cheng Susan, Ouyang David
Smidt Heart Institute, Department of Cardiology, Cedars-Sinai Medical Center, Los Angeles, California.
Icahn School of Medicine at Mt Sinai, New York, New York.
JAMA Cardiol. 2025 Apr 16. doi: 10.1001/jamacardio.2025.0498.
Accurate assessment of tricuspid regurgitation (TR) is necessary for identification and risk stratification.
To design a deep learning computer vision workflow for identifying color Doppler echocardiogram videos and characterizing TR severity.
DESIGN, SETTING, AND PARTICIPANTS: An automated deep learning workflow was developed using 47 312 studies (2 079 898 videos) from Cedars-Sinai Medical Center (CSMC) between 2011 and 2021. Data analysis was performed in 2024. The pipeline was tested on a temporally distinct test set of 2462 studies (108 138 videos) obtained in 2022 at CSMC and a geographically distinct cohort of 5549 studies (278 377 videos) from Stanford Healthcare (SHC). Training and validation cohorts contained data from 31 708 patients at CSMC receiving care between 2011 and 2021. Patients were chosen for parity across TR severity classes, with no exclusion criteria based on other clinical or demographic characteristics. The 2022 CSMC test cohort and SHC test cohorts contained studies from 2170 patients and 5014 patients, respectively.
Deep learning computer vision model.
The main outcomes were area under the receiver operating characteristic curve (AUC), sensitivity, and specificity in identifying apical 4-chamber (A4C) videos with color Doppler across the tricuspid valve and AUC in identifying studies with moderate to severe or severe TR.
In the CSMC test dataset, the view classifier demonstrated an AUC of 1.000 (95% CI, 0.999-1.000) and identified at least 1 A4C video with color Doppler across the tricuspid valve in 2410 of 2462 studies with a sensitivity of 0.975 (95% CI, 0.968-0.982) and a specificity of 1.000 (95% CI, 1.000-1.000). In the CSMC test cohort, moderate or severe TR was detected with an AUC of 0.928 (95% CI, 0.913-0.943), and severe TR was detected with an AUC of 0.956 (95% CI, 0.940-0.969). In the SHC cohort, the view classifier correctly identified at least 1 TR color Doppler video in 5268 of the 5549 studies, resulting in an AUC of 0.999 (95% CI, 0.998-0.999), a sensitivity of 0.949 (95% CI, 0.944-0.955), and a specificity of 0.999 (95% CI, 0.999-0.999). The artificial intelligence model detected moderate or severe TR with an AUC of 0.951 (95% CI, 0.938-0.962) and severe TR with an AUC of 0.980 (95% CI, 0.966-0.988).
In this study, an automated pipeline was developed to identify clinically significant TR with excellent performance. With open-source code and weights, this project can serve as the foundation for future prospective evaluation of artificial intelligence-assisted workflows in echocardiography.
准确评估三尖瓣反流（TR）对于识别和风险分层至关重要。
设计一种深度学习计算机视觉工作流程，用于识别彩色多普勒超声心动图视频并确定TR严重程度。
设计、设置和参与者：使用2011年至2021年期间雪松西奈医疗中心（CSMC）的47312项研究（2079898个视频）开发了一种自动化深度学习工作流程。2024年进行数据分析。该流程在2022年于CSMC获得的2462项研究（108138个视频）的时间上不同的测试集以及来自斯坦福医疗保健（SHC）的5549项研究（278377个视频）的地理上不同的队列上进行了测试。训练和验证队列包含2011年至2021年期间在CSMC接受治疗的31708名患者的数据。根据TR严重程度类别选择患者以保持均衡，不基于其他临床或人口统计学特征设置排除标准。2022年CSMC测试队列和SHC测试队列分别包含来自2170名患者和5014名患者的研究。
深度学习计算机视觉模型。
主要结局是在识别跨三尖瓣的彩色多普勒的心尖四腔心（A4C）视频时的受试者操作特征曲线下面积（AUC）、敏感性和特异性，以及在识别中度至重度或重度TR的研究时的AUC。
在CSMC测试数据集中，视图分类器的AUC为1.000（95%CI，0.999 - 1.000），在2462项研究中的2410项中识别出至少1个跨三尖瓣的彩色多普勒A4C视频，敏感性为0.975（95%CI，0.968 - 0.982），特异性为1.000（95%CI，1.000 - 1.000）。在CSMC测试队列中，检测到中度或重度TR的AUC为0.928（95%CI，0.913 - 0.943），检测到重度TR的AUC为0.956（95%CI，0.940 - 0.969）。在SHC队列中，视图分类器在5549项研究中的5268项中正确识别出至少1个TR彩色多普勒视频，AUC为0.999（95%CI，0.998 - 0.999），敏感性为0.949（95%CI，0.944 - 0.955），特异性为0.999（95%CI，0.999 - 0.999）。人工智能模型检测到中度或重度TR的AUC为0.951（95%CI，0.938 - 0.962），检测到重度TR的AUC为0.980（95%CI，0.966 - 0.988）。
在本研究中，开发了一种自动化流程以识别具有优异性能的具有临床意义的TR。通过开源代码和权重，该项目可作为未来超声心动图中人工智能辅助工作流程前瞻性评估的基础。
