Biomedical Engineering Research Center, Asan Institute for Life Sciences, Seoul, South Korea.
Department of Cardiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, South Korea.
Atherosclerosis. 2020 Jan;292:171-177. doi: 10.1016/j.atherosclerosis.2019.10.022. Epub 2019 Nov 2.
Intravascular ultrasound (IVUS)-derived morphological criteria are poor predictors of the functional significance of intermediate coronary stenosis. IVUS-based supervised machine learning (ML) algorithms were developed to identify lesions with a fractional flow reserve (FFR) ≤0.80 (vs. >0.80).
A total of 1328 patients with 1328 non-left main coronary lesions were randomized into training and test sets in a 4:1 ratio. Masked IVUS images were generated by an automatic segmentation model, and 99 computed IVUS features and six clinical variables (age, gender, body surface area, vessel type, involved segment, and involvement of the proximal left anterior descending artery) were used for ML training with 5-fold cross-validation. Diagnostic performances of the binary classifiers (L2 penalized logistic regression, artificial neural network, random forest, AdaBoost, CatBoost, and support vector machine) for detecting ischemia-producing lesions were evaluated using the non-overlapping test samples.
In the classification of test set lesions into those with an FFR ≤0.80 vs. >0.80, the overall diagnostic accuracies for predicting an FFR ≤0.80 were 82% with L2 penalized logistic regression, 80% with artificial neural network, 83% with random forest, 83% with AdaBoost, 81% with CatBoost, and 81% with support vector machine (AUCs: 0.84-0.87). With exclusion of the 28 lesions with borderline FFR of 0.75-0.80, the overall accuracies for the test set were 86% with L2 penalized logistic regression, 85% with an artificial neural network, 87% with random forest, 87% with AdaBoost, 85% with CatBoost, and 85% with support vector machine.
The IVUS-based ML algorithms showed good diagnostic performance for identifying ischemia-producing lesions, and may reduce the need for pressure wires.
血管内超声（IVUS）衍生的形态学标准预测中等程度冠状动脉狭窄的功能意义较差。已经开发了基于 IVUS 的监督机器学习（ML）算法来识别血流储备分数（FFR）≤0.80（与>0.80 相比）的病变。
将 1328 名非左主干冠状动脉病变患者随机分为训练集和测试集，比例为 4：1。通过自动分割模型生成蒙版 IVUS 图像，并使用 5 折交叉验证对 99 个计算 IVUS 特征和 6 个临床变量（年龄、性别、体表面积、血管类型、受累节段和前降支近端受累）进行 ML 训练。使用非重叠测试样本评估二元分类器（L2 惩罚逻辑回归、人工神经网络、随机森林、AdaBoost、CatBoost 和支持向量机）检测产生缺血病变的分类性能。
在将测试集病变分为 FFR≤0.80 和>0.80 组的分类中，L2 惩罚逻辑回归预测 FFR≤0.80 的总体诊断准确率为 82%，人工神经网络为 80%，随机森林为 83%，AdaBoost 为 83%，CatBoost 为 81%，支持向量机为 81%（AUC：0.84-0.87）。排除 FFR 为 0.75-0.80 的 28 个边界病变后，测试集的总体准确率分别为 L2 惩罚逻辑回归 86%、人工神经网络 85%、随机森林 87%、AdaBoost 87%、CatBoost 85%和支持向量机 85%。
基于 IVUS 的 ML 算法在识别产生缺血病变方面具有良好的诊断性能，可能减少对压力导丝的需求。
