基于冠脉造影视频的人工智能算法自动评估左室收缩功能
该横断面研究利用基于视频的深度神经网络(DNN)CathEF,从标准左冠状动脉造影视频中判别左室射血分数(LVEF)≤40%并预测连续LVEF百分比。UCSF测试集(n=813)判别AUROC为0.911,外部验证(n=776)AUROC为0.906;预测连续LVEF的平均绝对误差分别为8.5%和7.0%,提示该方法可早期从造影视频估计LVEF。
要点
- 造影视频DNN判别LVEF≤40%的AUROC在测试集为0.911、外部验证为0.906。
- 预测连续LVEF的平均绝对误差在测试集为8.5%、外部验证为7.0%。
- DNN倾向高估低LVEF、低估高LVEF,性能在多个亚组中一致。
核心结论
- 基于视频的深度神经网络可从标准左冠状动脉造影视频中早期估计LVEF,但准确性仍需进一步研究提高。
研究设计与样本
- 横断面研究,数据来自UCSF 2012年12月12日至2019年12月31日,随机分为训练、开发和测试集,并行外部验证。
- 纳入18岁及以上、在冠脉造影前3个月至后1个月内接受经胸超声心动图(TTE)的患者。
- 分析共纳入3679例UCSF患者的4042份成人造影资料,平均(SD)年龄64.3(13.3)岁,2212例为男性(65%)。
- UCSF测试集n=813,外部验证数据来自University of Ottawa Heart Institute,n=776。
主要发现
- UCSF测试集中,DNN判别LVEF≤40%的AUROC为0.911(95%CI 0.887-0.934),诊断比值比为22.7(95%CI 14.0-37.0)。
- UCSF测试集中,DNN预测连续LVEF与TTE LVEF的平均绝对误差为8.5%(95%CI 8.1%-9.0%)。
- UCSF测试集中,38.0%(309/813)的检查预测LVEF与TTE LVEF差异≤5%,15.2%(124/813)差异>15%。
- 外部验证中,DNN判别LVEF≤40%的AUROC为0.906(95%CI 0.881-0.931),预测连续LVEF的平均绝对误差为7.0%(95%CI 6.6%-7.4%)。
- DNN倾向高估低LVEF、低估高LVEF,其性能在性别、体重指数、低估算肾小球滤过率(≤45)、急性冠脉综合征、阻塞性冠心病及左心室肥厚亚组中一致。
关键数值与推荐
- LVEF降低的二元判别阈值定义为≤40%。
- 性能评估指标包括AUROC、诊断比值比和平均绝对误差(MAE),并按测试集与外部验证分别报告。
临床怎么用
- 可在冠脉造影过程中利用标准左冠状动脉造影视频辅助识别LVEF≤40%的患者,为疾病管理提供参考。
- 结果不能替代TTE等标准LVEF评估,部分检查预测误差较大(>15%),需结合临床判断。
局限性
- 为横断面研究,属于早期验证性演示。
- DNN预测存在高估低LVEF、低估高LVEF的系统性偏差。
- 作者指出需进一步研究提高准确性并减少DNN变异性以最大化临床效用。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
IMPORTANCE: Understanding left ventricular ejection fraction (LVEF) during coronary angiography can assist in disease management. OBJECTIVE: To develop an automated approach to predict LVEF from left coronary angiograms. DESIGN, SETTING, AND PARTICIPANTS: This was a cross-sectional study with external validation using patient data from December 12, 2012, to December 31, 2019, from the University of California, San Francisco (UCSF). Data were randomly split into training, development, and test data sets. External validation data were obtained from the University of Ottawa Heart Institute. Included in the analysis were all patients 18 years or older who received a coronary angiogram and transthoracic echocardiogram (TTE) within 3 months before or 1 month after the angiogram. EXPOSURE: A video-based deep neural network (DNN) called CathEF was used to discriminate (binary) reduced LVEF (≤40%) and to predict (continuous) LVEF percentage from standard angiogram videos of the left coronary artery. Guided class-discriminative gradient class activation mapping (GradCAM) was applied to visualize pixels in angiograms that contributed most to DNN LVEF prediction. RESULTS: A total of 4042 adult angiograms with corresponding TTE LVEF from 3679 UCSF patients were included in the analysis. Mean (SD) patient age was 64.3 (13.3) years, and 2212 patients were male (65%). In the UCSF test data set (n = 813), the video-based DNN discriminated (binary) reduced LVEF (≤40%) with an area under the receiver operating characteristic curve (AUROC) of 0.911 (95% CI, 0.887-0.934); diagnostic odds ratio for reduced LVEF was 22.7 (95% CI, 14.0-37.0). DNN-predicted continuous LVEF had a mean absolute error (MAE) of 8.5% (95% CI, 8.1%-9.0%) compared with TTE LVEF. Although DNN-predicted continuous LVEF differed 5% or less compared with TTE LVEF in 38.0% (309 of 813) of test data set studies, differences greater than 15% were observed in 15.2% (124 of 813). In external validation (n = 776), video-based DNN discriminated (binary) reduced LVEF (≤40%) with an AUROC of 0.906 (95% CI, 0.881-0.931), and DNN-predicted continuous LVEF had an MAE of 7.0% (95% CI, 6.6%-7.4%). Video-based DNN tended to overestimate low LVEFs and underestimate high LVEFs. Video-based DNN performance was consistent across sex, body mass index, low estimated glomerular filtration rate (≤45), presence of acute coronary syndromes, obstructive coronary artery disease, and left ventricular hypertrophy. CONCLUSION AND RELEVANCE: This cross-sectional study represents an early demonstration of estimating LVEF from standard angiogram videos of the left coronary artery using video-based DNNs. Further research can improve accuracy and reduce the variability of DNNs to maximize their clinical utility.
引用
- Avram R, Barrios JP, Abreau S, et al. Automated Assessment of Cardiac Systolic Function From Coronary Angiograms With Video-Based Artificial Intelligence Algorithms. JAMA Cardiol. 2023. PMID: 37163297. doi:10.1001/jamacardio.2023.0968
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。