Detection of myocardial ischemia by intracoronary ECG using convolutional neural networks

Abstract

Introduction: The electrocardiogram (ECG) is a valuable tool for the diagnosis of myocardial ischemia as it presents distinctive ischemic patterns. Deep learning methods such as convolutional neural networks (CNN) are employed to extract data-derived features and to recognize natural patterns. Hence, CNN enable an unbiased view on well-known clinical phenomenon, e.g., myocardial ischemia. This study tested a novel, hypothesis-generating approach using pre-trained CNN to determine the optimal ischemic parameter as obtained from the highly susceptible intracoronary ECG (icECG).

Method: This was a retrospective observational study in 228 patients with chronic coronary syndrome. Each patient had participated in clinical trials with icECG recording and ST-segment shift measurement at the beginning (i.e., non-ischemic) and the end (i.e., ischemic) of a one-minute proximal coronary artery balloon occlusion establishing the reference. Using these data (893 icECGs in total), two pre-trained, open-access CNN (GoogLeNet/ResNet101) were trained to recognize ischemia. The best performing CNN during training were compared with the icECG ST-segment shift for diagnostic accuracy in the detection of artificially induced myocardial ischemia.

Results: Using coronary patency or occlusion as reference for absent or present myocardial ischemia, receiver-operating-characteristics (ROC)-analysis of manually obtained icECG ST-segment shift (mV) showed an area under the ROC-curve (AUC) of 0.903±0.043 (p<0.0001, sensitivity 80%, specificity 92% at a cut-off of 0.279mV). The best performing CNN showed an AUC of 0.924 (sensitivity 93%, specificity 92%). DeLong-Test of the ROC-curves showed no significant difference between the AUCs. The underlying morphology responsible for the network prediction differed between the trained networks but was focused on the ST-segment and the T-wave for myocardial ischemia detection.

Conclusions: When tested in an experimental setting with artificially induced coronary artery occlusion, quantitative icECG ST-segment shift and CNN using pathophysiologic prediction criteria detect myocardial ischemia with similarly high accuracy.

Fig 1. Comparison of the standard scientific method and the deep–learning based approach.

Starting from a question/problem to be solved, the standard scientific method is based on a thorough literature research resulting in the construction of a hypothesis. Conversely, the deep–learning based approach uses already available data to train a neural network to solve the defined task as good as possible. Assessment of its performance requires comparison with previously established methods. The best performing networks are then analyzed by class activation mapping to visualize the underlying morphology triggering the network. Based on these visualizations, a hypothesis is constructed and tested in an appropriate experiment. Light–grey: shared processes; dark–grey: standard scientific method; white: deep–learning based, hypothesis–generating approach.

Fig 2. Input data for the neural networks.

The input data were taken from the original study analysis and converted into jpgs with a predefined image size (224x224x3 pixels). Each image contained either the illustration of a non–ischemic (i.e., recorded directly before the coronary balloon occlusion) or an ischemic (i.e., recorded at the end of the balloon occlusion) intracoronary ECG as well as the corresponding label (non–ischemic respectively ischemic). In this example, both icECGs are from the same vessel (left anterior descending coronary artery) from the same patient. IcECG ST–segment shift was 0.056mV respectively 0.858mV.

Fig 3. IcECG ST–segment shift grouped according to the state of absent or present coronary artery balloon occlusion.

Combination of the validation and the examination data (n = 225) was used for the performance analysis. Black circles: Non–ischemic prediction of ResNet5, black crosses: Ischemic prediction of ResNet5. Red signals: wrong predictions of ResNet5. Error bars indicate mean values and SD.

Fig 4. Nonparametric receiver–operating characteristic curve of the icECG ST–segment shift and the network predictions using coronary artery patency or occlusion as dichotomic reference for absent or present myocardial ischemia.

Of note, network prediction provides a dichotomous output (non–ischemic respectively ischemic), resulting in a triangular ROC–curve. Hence, there is only one combination of sensitivity and specificity possible for each CNN. Dashed black line = reference line.

Fig 5. Visualization of network activation patterns of the three best performing CNN.

Red regions contributed most to the network class prediction. ResNet5 bases its prediction on the area under the ST–segment and the T–wave. GoogLeNet10 is activated by the QRS–complex and the J–point for the non–ischemic state, and by the ST–segment and the T–wave for the ischemic state. ResNet6 bases its prediction on the ST–segment for the non–ischemic state, and on the end of the T–wave for the ischemic state. Please note the rather uncertain prediction of ResNet6 on the ischemic ECG.