Accuracy of intracoronary ECG parameters for myocardial ischemia detection

Bigler, Marius Reto; Zimmermann, Patrick; Papadis, Athanasios; Seiler, Christian

doi:10.1016/j.jelectrocard.2020.11.018

Cited by 15 publications

(20 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Slightly different from previously published results, icECG ST-segment shift showed a lower diagnostic accuracy (0.903±0.043 for the evaluation data versus 0.963±0.029 [ 4 ]), and was less pronounced during myocardial ischemia in the current analysis (0.915±0.972mV vs. 1.272±0.998mV). This resulted in a lower optimal cut-off level for ischemia detection at 0.279mV (compared to 0.365mV).…”

Section: Discussioncontrasting

confidence: 99%

“…While the duration of coronary artery occlusion was identical in the recent and the present study (i.e., 60 seconds), the other determinants of myocardial ischemia differed. Compared to the previous analysis [ 4 ], where left anterior descending coronary artery was the most frequent study vessel, the right coronary artery currently served as the most frequent study vessel, causing a relevant decrease in the myocardial area at risk.…”

Section: Discussionmentioning

confidence: 86%

“…CNN focuses on distinctive features in the icECG ST-segment and the T-wave. The pathophysiologic basis of these characteristic patterns is the reduced resting potential of the ischemic myocardial cells, caused by a pathologic ion current across the injured cell membrane with subsequent distortion of the normally isoelectric ST-segment [ 4 , 40 ]. In addition, inadequate energy supply during ischemia directly affects the ventricular repolarization and thus, the morphology and duration of the T-wave [ 40 ].…”

Section: Discussionmentioning

confidence: 99%

“…In brief, CFI is a measure of collateral blood supply to a coronary artery proximally balloon-occluded for the duration of 1 minute, and it is defined as mean coronary occlusive pressure relative to mean aortic pressure, both subtracted by PLOS ONE central venous pressure [18]. Hence, the present study employs the same temporal landmarks with non-ischemic (i.e., before coronary occlusion), and controlled ischemic (i.e., at the end of the occlusion) conditions as recently [4]. Of note, the experimental setting of a brief artificial coronary balloon occlusion creates an independent reference essential for the subsequent analysis.…”

Section: Study Design and Patientsmentioning

confidence: 99%

“…Recently, our research group employed an experimental setting with complete coronary artery balloon occlusion during 1 minute, thus creating a brief myocardial ischemia [ 2 , 3 ]. Intracoronary ECG (icECG) was used to assess the diagnostic accuracy of various ECG parameters for ischemia detection [ 4 ], whereby the icECG ST-segment shift measured at the J-point at a threshold of 0.365mV was superior to other parameters for ischemia detection. In the mentioned study, selection of the analyzed parameters was based on a literature search for ECG ischemia parameters.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Detection of myocardial ischemia by intracoronary ECG using convolutional neural networks

Bigler

Seiler

2021

PLoS ONE

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussioncontrasting

confidence: 99%

Section: Discussionmentioning

confidence: 86%