基于面部照片的深度学习检测冠心病可行性研究
在中国9个中心开展多中心横断面研究,纳入行冠状动脉造影或CT血管造影的患者,训练并验证基于面部照片检测冠心病(至少一处狭窄≥50%)的深度卷积神经网络。测试组共1013例,算法敏感度0.80、特异度0.54,AUC为0.730(95%CI 0.699-0.761),高于Diamond-Forrester模型和CAD consortium临床评分。
要点
- 基于面部照片的深度学习算法可用于辅助冠心病检测,测试组AUC为0.730。
- 该算法AUC优于Diamond-Forrester模型和CAD consortium临床评分。
- 高敏感度操作点下敏感度0.80、特异度0.54,可能适合筛查场景。
核心结论
- 基于面部照片的深度学习算法在中国队列中可辅助冠心病检测。
- 该技术有望用于门诊冠心病验前概率评估或社区筛查。
研究设计与样本
- 多中心横断面研究,在中国9个中心招募行冠状动脉造影或CT血管造影的患者。
- 2017年7月至2019年3月,8个中心连续纳入5796例患者,随机分为训练组(90%,n=5216)和验证组(10%,n=580)用于算法开发。
- 2019年4月至2019年7月,9个中心纳入1013例患者进入测试组用于算法测试。
- 以放射科医生诊断为标准,计算敏感度、特异度和受试者工作特征曲线下面积(AUC)。
主要发现
- 测试组中,采用高敏感度操作切点时,CAD检测算法的敏感度为0.80,特异度为0.54。
- 测试组AUC为0.730(95%CI 0.699-0.761)。
- 算法AUC高于Diamond-Forrester模型(0.730 vs. 0.623,P<0.001)。
- 算法AUC高于CAD consortium临床评分(0.730 vs. 0.652,P<0.001)。
关键数值与推荐
- 冠心病定义为至少一处狭窄≥50%。
- 训练组n=5216,验证组n=580,测试组n=1013。
临床怎么用
- 该算法可能用于门诊验前CAD概率评估或社区CAD筛查。
- 需进一步研究开发临床可用工具。
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
AIMS: Facial features were associated with increased risk of coronary artery disease (CAD). We developed and validated a deep learning algorithm for detecting CAD based on facial photos. METHODS AND RESULTS: We conducted a multicentre cross-sectional study of patients undergoing coronary angiography or computed tomography angiography at nine Chinese sites to train and validate a deep convolutional neural network for the detection of CAD (at least one ≥50% stenosis) from patient facial photos. Between July 2017 and March 2019, 5796 patients from eight sites were consecutively enrolled and randomly divided into training (90%, n = 5216) and validation (10%, n = 580) groups for algorithm development. Between April 2019 and July 2019, 1013 patients from nine sites were enrolled in test group for algorithm test. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated using radiologist diagnosis as the reference standard. Using an operating cut point with high sensitivity, the CAD detection algorithm had sensitivity of 0.80 and specificity of 0.54 in the test group; the AUC was 0.730 (95% confidence interval, 0.699-0.761). The AUC for the algorithm was higher than that for the Diamond-Forrester model (0.730 vs. 0.623, P < 0.001) and the CAD consortium clinical score (0.730 vs. 0.652, P < 0.001). CONCLUSION: Our results suggested that a deep learning algorithm based on facial photos can assist in CAD detection in this Chinese cohort. This technique may hold promise for pre-test CAD probability assessment in outpatient clinics or CAD screening in community. Further studies to develop a clinical available tool are warranted.
引用
- Lin S, Li Z, Fu B, et al. Feasibility of using deep learning to detect coronary artery disease based on facial photo. Eur Heart J. 2020. PMID: 32818267. doi:10.1093/eurheartj/ehaa640
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。