PDF(Pubmed)
Abstract：
Identifying patients with left ventricular ejection fraction (EF), either reduced [EF < 40% (rEF)], mid-range [EF 40-50% (mEF)], or preserved [EF > 50% (pEF)], is considered of primary clinical importance. An end-to-end video classification using AutoML in Google Vertex AI was applied to echocardiographic recordings. Datasets balanced by majority undersampling, each corresponding to one out of three possible classifications, were obtained from the Standford EchoNet-Dynamic repository. A train-test split of 75/25 was applied. A binary video classification of rEF vs. not rEF demonstrated good performance (test dataset: ROC AUC score 0.939, accuracy 0.863, sensitivity 0.894, specificity 0.831, positive predicting value 0.842). A second binary classification of not pEF vs. pEF was slightly less performing (test dataset: ROC AUC score 0.917, accuracy 0.829, sensitivity 0.761, specificity 0.891, positive predicting value 0.888). A ternary classification was also explored, and lower performance was observed, mainly for the mEF class. A non-AutoML PyTorch implementation in open access confirmed the feasibility of our approach. With this proof of concept, end-to-end video classification based on transfer learning to categorize EF merits consideration for further evaluation in prospective clinical studies.
摘要：
确定左心室射血分数（EF）的患者，要么降低[EF<40%(rEF)]，中档[EF40-50%(mEF)]，或保留[EF>50%(pEF)]，被认为是首要的临床重要性。使用GoogleVertexAI中的AutoML的端到端视频分类应用于超声心动图记录。通过多数欠采样平衡的数据集，每个对应于三个可能分类中的一个，是从StandfordEchoNet-Dynamic存储库中获得的。应用75/25的列车测试分裂。rEF与rEF的二元视频分类非rEF表现良好（测试数据集：ROCAUC评分0.939，准确性0.863，敏感性0.894，特异性0.831，阳性预测值0.842）。非pEF与pEF的第二个二元分类pEF表现稍差（测试数据集：ROCAUC评分0.917，准确性0.829，敏感性0.761，特异性0.891，阳性预测值0.888）。还探索了三元分类，并且观察到较低的性能，主要是mEF类。开放访问中的非AutoMLPyTorch实现证实了我们方法的可行性。有了这个概念证明，基于迁移学习对EF进行分类的端到端视频分类，以便在前瞻性临床研究中进一步评估。
