Lachmann Mark, Rippen Elena, Rueckert Daniel, Schuster Tibor, Xhepa Erion, von Scheidt Moritz, Pellegrini Costanza, Trenkwalder Teresa, Rheude Tobias, Stundl Anja, Thalmann Ruth, Harmsen Gerhard, Yuasa Shinsuke, Schunkert Heribert, Kastrati Adnan, Joner Michael, Kupatt Christian, Laugwitz Karl Ludwig
First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich, Ismaninger Straße 22, 81675 Munich, Germany.
Institute for AI and Informatics in Medicine, Faculty of Informatics and Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.
Eur Heart J Digit Health. 2022 Apr 22;3(2):153-168. doi: 10.1093/ehjdh/ztac004. eCollection 2022 Jun.
Hypothesizing that aortic outflow velocity profiles contain more valuable information about aortic valve obstruction and left ventricular contractility than can be captured by the human eye, features of the complex geometry of Doppler tracings from patients with severe aortic stenosis (AS) were extracted by a convolutional neural network (CNN).
After pre-training a CNN (VGG-16) on a large data set (ImageNet data set; 14 million images belonging to 1000 classes), the convolutional part was employed to transform Doppler tracings to 1D arrays. Among 366 eligible patients [age: 79.8 ± 6.77 years; 146 (39.9%) women] with pre-procedural echocardiography and right heart catheterization prior to transcatheter aortic valve replacement (TAVR), good quality Doppler tracings from 101 patients were analysed. The convolutional part of the pre-trained VGG-16 model in conjunction with principal component analysis and k-means clustering distinguished two shapes of aortic outflow velocity profiles. Kaplan-Meier analysis revealed that mortality in patients from Cluster 2 ( = 40, 39.6%) was significantly increased [hazard ratio (HR) for 2-year mortality: 3; 95% confidence interval (CI): 1-8.9]. Apart from reduced cardiac output and mean aortic valve gradient, patients from Cluster 2 were also characterized by signs of pulmonary hypertension, impaired right ventricular function, and right atrial enlargement. After training an extreme gradient boosting algorithm on these 101 patients, validation on the remaining 265 patients confirmed that patients assigned to Cluster 2 show increased mortality (HR for 2-year mortality: 2.6; 95% CI: 1.4-5.1, -value: 0.004).
Transfer learning enables sophisticated pattern recognition even in clinical data sets of limited size. Importantly, it is the left ventricular compensation capacity in the face of increased afterload, and not so much the actual obstruction of the aortic valve, that determines fate after TAVR.
假设主动脉流出速度曲线包含比人眼所能捕捉到的更多关于主动脉瓣狭窄和左心室收缩性的有价值信息，通过卷积神经网络（CNN）提取重度主动脉瓣狭窄（AS）患者多普勒描记图复杂几何形状的特征。
在一个大数据集（ImageNet数据集；1400万张属于1000个类别的图像）上对CNN（VGG - 16）进行预训练后，使用卷积部分将多普勒描记图转换为一维数组。在366例符合条件的患者[年龄：79.8±6.77岁；146例（39.9%）为女性]中，这些患者在经导管主动脉瓣置换术（TAVR）前进行了术前超声心动图和右心导管检查，分析了101例患者质量良好的多普勒描记图。预训练的VGG - 16模型的卷积部分结合主成分分析和k均值聚类区分出两种主动脉流出速度曲线形状。Kaplan - Meier分析显示，第2组患者（n = 40，39.6%）的死亡率显著增加[2年死亡率的风险比（HR）：3；95%置信区间（CI）：1 - 8.9]。除了心输出量降低和平均主动脉瓣梯度外，第2组患者还具有肺动脉高压、右心室功能受损和右心房扩大的体征。在对这101例患者训练极端梯度提升算法后，对其余265例患者进行验证，证实分配到第2组的患者死亡率增加（2年死亡率的HR：2.6；95% CI：1.4 - 5.1，P值：0.004）。
迁移学习即使在规模有限的临床数据集中也能实现复杂的模式识别。重要的是，决定TAVR后命运的是面对后负荷增加时左心室的代偿能力，而非主动脉瓣的实际狭窄程度。
