用深度学习分析心电图，提升肺栓塞快速诊断能力
Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms
- 多模型对比实验验证不同神经网络在心电图上识别肺栓塞的效果
- 利用大尺度心电图数据集迁移学习，显著提升小样本下的分类性能
- 为资源有限地区提供快速、低成本的肺栓塞筛查新方法
肺栓塞是院外心脏骤停的主要原因之一，需快速诊断。虽然计算机断层扫描肺动脉造影是标准诊断工具，但并非所有地方都可及。心电图成本低、速度快、应用广泛，是诊断多种心脏异常的重要手段。然而，针对肺栓塞的公开心电图数据集稀缺，且实际数据集规模小，因此优化学习策略至关重要。本研究评估了多种神经网络在肺栓塞识别中的表现，并检验了迁移学习在将大规模心电图数据集（如PTB-XL、CPSC18、MedalCare-XL）中学习到的信息迁移到更小、更具挑战性的肺栓塞数据集时对模型泛化能力的提升效果。通过迁移学习，我们分析了如何在数据有限的情况下提高学习效率和预测性能。代码已公开于 https://github.com/joaodsmarques/Are-ECGs-enough-Deep-Learning-Classifiers。
原文摘要 · Abstract (English)
Pulmonary embolism is a leading cause of out of hospital cardiac arrest that requires fast diagnosis. While computed tomography pulmonary angiography is the standard diagnostic tool, it is not always accessible. Electrocardiography is an essential tool for diagnosing multiple cardiac anomalies, as it is affordable, fast and available in many settings. However, the availability of public ECG datasets, specially for PE, is limited and, in practice, these datasets tend to be small, making it essential to optimize learning strategies. In this study, we investigate the performance of multiple neural networks in order to assess the impact of various approaches. Moreover, we check whether these practices enhance model generalization when transfer learning is used to translate information learned in larger ECG datasets, such as PTB-XL, CPSC18 and MedalCare-XL, to a smaller, more challenging dataset for PE. By leveraging transfer learning, we analyze the extent to which we can improve learning efficiency and predictive performance on limited data. Code available at https://github.com/joaodsmarques/Are-ECGs-enough-Deep-Learning-Classifiers .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。