scholarly journals Detection of myocardial ischemia by intracoronary ECG using convolutional neural networks

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
M R Bigler ◽  
C Seiler
Keyword(s):  
Neural Networks ◽  
Coronary Artery ◽  
Myocardial Ischemia ◽  
Convolutional Neural Networks ◽  
Balloon Occlusion ◽  
Operating Characteristics ◽  
Shift Measurement ◽  
Coronary Syndrome ◽  
St Segment ◽  
Significant Difference

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. This study aimed to determine the optimal ischemic parameter as obtained from the highly susceptible intracoronary ECG (icECG) using pre-trained CNN. 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 (893icECGs 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. FUNDunding Acknowledgement Type of funding sources: None.

scholarly journals Detection of myocardial ischemia by intracoronary ECG using convolutional neural networks

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0253200
Author(s):  
Marius Reto Bigler ◽  
Christian Seiler
Keyword(s):  
Neural Networks ◽  
Coronary Artery ◽  
Myocardial Ischemia ◽  
Convolutional Neural Networks ◽  
Balloon Occlusion ◽  
Operating Characteristics ◽  
Shift Measurement ◽  
Coronary Syndrome ◽  
St Segment ◽  
Significant Difference

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.

scholarly journals Vasospasm or Atherosclerotic Lesion of Coronary Arteries: Case Management

2019 ◽  
pp. 87-90
Author(s):  
V. K. Tashchuk ◽  
I. O. Makoviichuk ◽  
M. V. Al Salama ◽  
O. V. Malinevska-Biliichuk ◽  
S. S. Biletskiy ◽  
...  
Keyword(s):  
Coronary Artery ◽  
Coronary Angiography ◽  
Myocardial Ischemia ◽  
Coronary Arteries ◽  
Atherosclerotic Lesion ◽  
Diagnostic Procedures ◽  
Silent Myocardial Ischemia ◽  
St Segment Elevation ◽  
Coronary Syndrome ◽  
St Segment

  Background. Coronary artery vasospasm (CVS) is an important mechanism of myocardial ischemia which can produce any of the manifestations of coronary artery disease from silent myocardial ischemia to acute coronary syndrome including myocardial infarction or sudden cardiac death. One of the main markers of CVS is retrosternal pain not associated with increased myocardial oxygen requirement such as that due to exercise or emotional excitement with frequent attacks in the morning and temporary ST segment elevation. Some patients have variant angina caused by the spasm of coronary arteries (СА) coupled with stable angina provoked by emotional and physical stress. Such patients have decreased exercise tolerance. Aim. To determine the feasibility and subsequence of the appointment of diagnostic procedures such as electrocardiography (ECG), bicycle ergometry (BEM), provocative tests and coronary angiography and left ventriculography (CAG & LVG) in order to visualize СА, to make the choice of patient’s management and to assign an adequate therapeutic program. Materials and methods. The patient who was admitted with complaints about progression of angina and shortness of breath received the full complex of diagnostic manipulations. The purpose was to verify the diagnosis and to prescribe an adequate treatment. Results. This clinical case shows the subsequence of the appointment of diagnostic procedures to the patient who has normal ECG, ST segment elevation on BEM and progression of angina attacks, that is, the necessity of the widespread introduction of coronary angiography. Conclusion. This article shows the necessity of appointment of CAG & LVG. CAG & LVG revealed atherosclerotic lesion of CA which caused chest paint, ST segment elevation, and this result confounded the presence of CVS as a cause of complaints in this patient. The patient underwent stenting of the affected CA which helped to eliminate the cause of pain and is compatible with adequate therapeutic tactics for patients with CA stenosis.

Functional assessment of myocardial ischemia by intracoronary electrocardiogram

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
M.R Bigler ◽  
F Praz ◽  
G.C.M Siontis ◽  
M Stoller ◽  
R Grossenbacher ◽  
...  
Keyword(s):  
Myocardial Ischemia ◽  
Primary Study ◽  
Coronary Perfusion ◽  
Funding Source ◽  
Maximal Heart Rate ◽  
Fractional Flow ◽  
Coronary Syndrome ◽  
Flow Reserve ◽  
St Segment ◽  
Coronary Lesions

Abstract Background In patients with chronic coronary syndrome (CCS), percutaneous coronary intervention (PCI) targets hemodynamically significant stenoses, i.e., those thought to cause ischemia. The hemodynamic severity of a coronary stenosis increases with its tightness and with the myocardial mass of viable myocardium downstream of the stenosis. Besides the structural angiographic approach, assessment of functional relevance by pressure measurements (fractional flow reserve, FFR; instantaneous wave-free ratio, iFR) is recommended. However, visual angiographic assessment continues to dominate the treatment decisions for intermediate coronary lesions. Conversely, intracoronary ECG (icECG) potentially provides an inexpensive, sensitive and direct measure of myocardial ischemia. Purpose The goal of this study was to test the accuracy of intracoronary ECG during pharmacologic inotropic stress to determine coronary lesion severity in comparison to established physiologic indices (FFR/iFR) as well as with quantitatively determined percent diameter stenosis (%S) using biplane coronary angiography. Method This was a prospective, open-label study in patients with CCS. The primary study end point was the maximal change in icECG ST-segment shift during pharmacologic inotropic stress induced by dobutamine plus atropine obtained within 1 minute after the point of maximal heart rate (estimated by the formula 220 - age). IcECG was acquired by attaching an alligator clamp to the angioplasty guidewire positioned downstream of a stenosis. For the pressure-derived ratios, i.e. FFR and iFR, the coronary perfusion pressure downstream of a lesion as well as the aortic pressure were continuously recorded. Results One hundred patients were included in the study. Pearson-Correlation coefficient was significant between icECG and all three comparators (%S p&lt;0.001, iFR p&lt;0.001, FFR p&lt;0.001). Using the FFR threshold of 0.80 defining coronary hemodynamic significance, ROC-analysis of the absolute icECG ST-segment shift showed an area under the curve (AUC) of 0.708±0.053 (p=0.0001, n=100, FFR&lt;0.80 n=41). AUC for iFR was 0.919±0.030 (p&lt;0.0001), for percent diameter stenosis it was 0.867±0.036 (p&lt;0.0001). Conclusions During pharmacologic inotropic stress, intracoronary ECG ST-segment shift provides specific evidence for regional myocardial ischemia irrespective of the etiology and thus, provides an additional (patho-)physiologic information for decision making in borderline coronary lesions. Funding Acknowledgement Type of funding source: Foundation. Main funding source(s): Swiss Heart Foundation

scholarly journals Effect of PCSK9 E670G and R46L Polymorphisms on Major Adverse Cardio-Cerebrovascular Events in Patients with ST-Segment Elevation Myocardial Infarction Undergoing Primary Percutaneous Coronary Intervention

2021 ◽  
Author(s):  
Anwar Santoso ◽  
Yulianto Yulianto ◽  
Hendra Simarmata ◽  
Abhirama Nofandra Putra ◽  
Erlin Listiyaningsih
Keyword(s):  
Myocardial Infarction ◽  
Proportional Hazards Model ◽  
Cox Proportional Hazards ◽  
Cox Proportional Hazards Model ◽  
St Segment Elevation ◽  
Coronary Syndrome ◽  
Segment Elevation Myocardial Infarction ◽  
Cerebrovascular Events ◽  
St Segment ◽  
Significant Difference

AbstractMajor adverse cardio-cerebrovascular events (MACCE) in ST-segment elevation myocardial infarction (STEMI) are still high, although there have been advances in pharmacology and interventional procedures. Proprotein convertase subtilisin/Kexin type 9 (PCSK9) is a serine protease regulating lipid metabolism associated with inflammation in acute coronary syndrome. The MACCE is possibly related to polymorphisms in PCSK9. A prospective cohort observational study was designed to confirm the association between polymorphism of E670G and R46L in the PCSK9 gene with MACCE in STEMI. The Cox proportional hazards model and Spearman correlation were utilized in the study. The Genotyping of PCSK9 and ELISA was assayed.Sixty-five of 423 STEMI patients experienced MACCE in 6 months. The E670G polymorphism in PCSK9 was associated with MACCE (hazard ratio = 45.40; 95% confidence interval: 5.30–390.30; p = 0.00). There was a significant difference of PCSK9 plasma levels in patients with previous statin consumption (310 [220–1,220] pg/mL) versus those free of any statins (280 [190–1,520] pg/mL) (p = 0.001).E670G polymorphism of PCSK9 was associated with MACCE in STEMI within a 6-month follow-up. The plasma PCSK9 level was higher in statin users.

Unstable Angina and Other Acute Coronary Syndromes

2013 ◽  
Author(s):  
R Scott Wright ◽  
Joseph G Murphy
Keyword(s):  
Myocardial Infarction ◽  
Coronary Artery ◽  
Risk Stratification ◽  
Unstable Angina ◽  
The United States ◽  
Cardiac Biomarkers ◽  
St Segment Elevation ◽  
Coronary Syndrome ◽  
Segment Elevation Myocardial Infarction ◽  
St Segment

Patients with coronary artery disease (CAD) present clinically when their disease enters an unstable phase known as an acute coronary syndrome (ACS), in which the cap of a previously stable atheromatous coronary plaque ruptures or erodes, which in turn activates a thrombotic cascade that may lead to coronary artery occlusion, myocardial infarction (MI), cardiogenic shock, and patient death. There are nearly 2 million episodes of ACS in the United States annually; it is the most common reason for hospitalization with CAD and is the leading cause of death in the developed world. ACS patients include those with unstable angina (UA), non–ST segment elevation myocardial infarction (non-STEMI), and ST segment elevation myocardial infarction (STEMI) and patients who die suddenly of an arrhythmia precipitated by coronary occlusion. The distinction among various ACS subgroups reflects varying characteristics of clinical presentation (presence or absence of elevated cardiac biomarkers) and the type of electrocardiographic (ECG) changes manifested on the initial ECG at the time of hospitalization. This chapter focuses on UA and non-STEMI. A graph outlines mortality risks faced by patients with varying degrees of renal insufficiency. An algorithm describes the suggested management of patients admitted with UA or non-STEMI. Tables describe the risk stratification of the patient with chest pain, categories of Killip class, examination findings of a patient with high-risk ACS, diagnosis of MI, causes of troponin elevation other than ischemic heart disease, initial risk stratification of ACS patients, and long-term medical therapies and goals in ACS patients. This review contains 2 highly rendered figures, 11 tables, and 76 references.

scholarly journals Loeffler’s endocarditis and possible coronary spasm secondary to eosinophilic coronary periarteritis with ECG change mimicking acute non-ST-segment elevation myocardial infarction: A case report

2020 ◽  
Author(s):  
Fan-xin Kong ◽  
Meng Li ◽  
Chun-Yan Ma ◽  
Ping-ping Meng ◽  
Yong-huai Wang ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Differential Diagnosis ◽  
Coronary Artery ◽  
Troponin I ◽  
Hypereosinophilic Syndrome ◽  
Coronary Spasm ◽  
St Segment Elevation ◽  
Coronary Syndrome ◽  
Segment Elevation Myocardial Infarction ◽  
St Segment

Abstract Background Loeffler’s endocarditis is an inflammatory cardiac condition of hypereosinophilic syndrome which rarely involves coronary artery. When coronary artery is involved, known as eosinophilic coronary periarteritis, the clinical presentation, electrocardiographic changes and troponin level are extremely nonspecific and may mimic acute coronary syndrome. It is very important to make differential diagnosis for ECPA in order to avoid the unnecessary further invasive coronary angiography. Case presentation We report a case with chest pain, ST-segment depression in electrocardiogram and increased troponin-I mimicking acute non-ST-segment elevation myocardial infarction. However, quick echocardiography showed endomyocardial thickening with normal regional wall motion, which corresponded to the characteristics of Loeffler’s endocarditis. Emergent blood analysis showed marked increase in eosinophils and computed tomography angiography found no significant stenosis of coronary artery. Manifestations of magnetic resonance imaging consisted with findings of echocardiography. Finally, the patient was diagnosed as Loeffler’s endocarditis and possible coronary spasm secondary to eosinophilic coronary periarteritis. Conclusion This case exhibits the crucial use of quick transthoracic echocardiography and the emergent hematological examination for differential diagnosis in such scenarios as often if electrocardiogram change mimicking myocardial infarction.

Sign in / Sign up

Export Citation Format

Share Document