Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany. Author to whom any correspondence should be addressed.
Physiol Meas. 2019 Jan 15;40(1):015001. doi: 10.1088/1361-6579/aaf34d.
We aim to provide an algorithm for the detection of myocardial infarction that operates directly on ECG data without any preprocessing and to investigate its decision criteria.
We train an ensemble of fully convolutional neural networks on the PTB ECG dataset and apply state-of-the-art attribution methods.
Our classifier reaches 93.3% sensitivity and 89.7% specificity evaluated using 10-fold cross-validation with sampling based on patients. The presented method outperforms state-of-the-art approaches and reaches the performance level of human cardiologists for detection of myocardial infarction. We are able to discriminate channel-specific regions that contribute most significantly to the neural network's decision. Interestingly, the network's decision is influenced by signs also recognized by human cardiologists as indicative of myocardial infarction.
Our results demonstrate the high prospects of algorithmic ECG analysis for future clinical applications considering both its quantitative performance as well as the possibility of assessing decision criteria on a per-example basis, which enhances the comprehensibility of the approach.
我们旨在提供一种直接在心电图数据上运行的心肌梗死检测算法，而无需任何预处理，并研究其决策标准。
我们在 PTB ECG 数据集上训练了一个完全卷积神经网络集成，并应用了最先进的归因方法。
我们的分类器在基于患者抽样的 10 折交叉验证中达到了 93.3%的灵敏度和 89.7%的特异性。所提出的方法优于最先进的方法，达到了人类心脏病专家检测心肌梗死的性能水平。我们能够区分对神经网络决策贡献最大的特定通道区域。有趣的是，该网络的决策受到人类心脏病专家也认为提示心肌梗死的迹象的影响。
我们的结果表明，考虑到算法心电图分析在未来临床应用中的高前景，既要考虑其定量性能，又要考虑在逐个示例的基础上评估决策标准的可能性，这增强了该方法的可理解性。
