Detection of culprit coronary lesion location in pre-hospital 12-lead ECG

Calcium signaling from sarcoplasmic reticulum and mitochondria contact sites in acute myocardial infarction

Acute myocardial infarction (AMI) is a serious condition that occurs when part of the heart is subjected to ischemia episodes, following partial or complete occlusion of the epicardial coronary arteries. The resulting damage to heart muscle cells have a significant impact on patient's health and quality of life. About that, recent research focused on the role of the sarcoplasmic reticulum (SR) and mitochondria in the physiopathology of AMI. Moreover, SR and mitochondria get in touch each other through multiple membrane contact sites giving rise to the subcellular region called mitochondria-associated membranes (MAMs). MAMs are essential for, but not limited to, bioenergetics and cell fate. Disruption of the architecture of these regions occurs during AMI although it is still unclear the cause-consequence connection and a complete overview of the pathological changes; for sure this concurs to further damage to heart muscle. The calcium ion (Ca2+) plays a pivotal role in the pathophysiology of AMI and its dynamic signaling between the SR and mitochondria holds significant importance. In this review, we tried to summarize and update the knowledge about the roles of these organelles in AMI from a Ca2+ signaling point of view. Accordingly, we also reported some possible cardioprotective targets which are directly or indirectly related at limiting the dysfunctions caused by the deregulation of the Ca2+ signaling.

Identification of Coronary Culprit Lesion in ST Elevation Myocardial Infarction by Using Deep Learning

OBJECTIVE

Early revascularization of the occluded coronary artery in patients with ST elevation myocardial infarction (STEMI) has been demonstrated to decrease mortality and morbidity. Currently, physicians rely on features of electrocardiograms (ECGs) to identify the most likely location of coronary arteries related to an infarct. We sought to predict these culprit arteries more accurately by using deep learning.

METHODS

A deep learning model with a convolutional neural network (CNN) that incorporated ECG signals was trained on 384 patients with STEMI who underwent primary percutaneous coronary intervention (PCI) at a medical center. The performances of various signal preprocessing methods (short-time Fourier transform [STFT] and continuous wavelet transform [CWT]) with different lengths of input ECG signals were compared. The sensitivity and specificity for predicting each infarct-related artery and the overall accuracy were evaluated.

RESULTS

ECG signal preprocessing with STFT achieved fair overall prediction accuracy (79.3%). The sensitivity and specificity for predicting the left anterior descending artery (LAD) as the culprit vessel were 85.7% and 88.4%, respectively. The sensitivity and specificity for predicting the left circumflex artery (LCX) were 37% and 99%, respectively, and the sensitivity and specificity for predicting the right coronary artery (RCA) were 88.4% and 82.4%, respectively. Using CWT (Morlet wavelet) for signal preprocessing resulted in better overall accuracy (83.7%) compared with STFT preprocessing. The sensitivity and specificity were 93.46% and 80.39% for LAD, 56% and 99.7% for LCX, and 85.9% and 92.9% for RCA, respectively.

CONCLUSION

Our study demonstrated that deep learning with a CNN could facilitate the identification of the culprit coronary artery in patients with STEMI. Preprocessing ECG signals with CWT was demonstrated to be superior to doing so with STFT.

LASSO Regression-Based Diagnosis of Acute ST-Segment Elevation Myocardial Infarction (STEMI) on Electrocardiogram (ECG)

Electrocardiogram (ECG) is an important tool for the detection of acute ST-segment elevation myocardial infarction (STEMI). However, machine learning (ML) for the diagnosis of STEMI complicated with arrhythmia and infarct-related arteries is still underdeveloped based on real-world data. Therefore, we aimed to develop an ML model using the Least Absolute Shrinkage and Selection Operator (LASSO) to automatically diagnose acute STEMI based on ECG features. A total of 318 patients with STEMI and 502 control subjects were enrolled from Jan 2017 to Jun 2019. Coronary angiography was performed. A total of 180 automatic ECG features of 12-lead ECG were input into the model. The LASSO regression model was trained and validated by the internal training dataset and tested by the internal and external testing datasets. A comparative test was performed between the LASSO regression model and different levels of doctors. To identify the STEMI and non-STEMI, the LASSO model retained 14 variables with AUCs of 0.94 and 0.93 in the internal and external testing datasets, respectively. The performance of LASSO regression was similar to that of experienced cardiologists (AUC: 0.92) but superior (p < 0.05) to internal medicine residents, medical interns, and emergency physicians. Furthermore, in terms of identifying left anterior descending (LAD) or non-LAD, LASSO regression achieved AUCs of 0.92 and 0.98 in the internal and external testing datasets, respectively. This LASSO regression model can achieve high accuracy in diagnosing STEMI and LAD vessel disease, thus providing an assisting diagnostic tool based on ECG, which may improve the early diagnosis of STEMI.

Deep Learning Networks Accurately Detect ST-Segment Elevation Myocardial Infarction and Culprit Vessel

Early diagnosis of acute ST-segment elevation myocardial infarction (STEMI) and early determination of the culprit vessel are associated with a better clinical outcome. We developed three deep learning (DL) models for detecting STEMIs and culprit vessels based on 12-lead electrocardiography (ECG) and compared them with conclusions of experienced doctors, including cardiologists, emergency physicians, and internists. After screening the coronary angiography (CAG) results, 883 cases (506 control and 377 STEMI) from internal and external datasets were enrolled for testing DL models. Convolutional neural network-long short-term memory (CNN-LSTM) (AUC: 0.99) performed better than CNN, LSTM, and doctors in detecting STEMI. Deep learning models (AUC: 0.96) performed similarly to experienced cardiologists and emergency physicians in discriminating the left anterior descending (LAD) artery. Regarding distinguishing RCA from LCX, DL models were comparable to doctors (AUC: 0.81). In summary, we developed ECG-based DL diagnosis systems to detect STEMI and predict culprit vessel occlusion, thus enhancing the accuracy and effectiveness of STEMI diagnosis.

Culprit lesion detection in patients presenting with non-ST elevation acute coronary syndrome and multivessel disease

BACKGROUND/PURPOSE

Identification of the culprit lesion in patients with non-ST elevation acute coronary syndrome (NSTE-ACS) allows appropriate coronary revascularization but may be unclear in patients with multivessel coronary disease (MVD). Therefore, we investigated the rate of culprit lesion identification during coronary angiography in NSTE-ACS and multivessel disease.

METHODS/MATERIALS

Consecutive patients presenting with NSTE-ACS and MVD, between January 2012 and December 2016 were evaluated. Coronary angiograms, intravascular imaging, and ECGs were analyzed for culprit lesion identification. Long-term clinical outcomes in terms of major adverse cardiac events (MACE) and mortality were reported in patients with or without culprit identification.

RESULTS

A total of 1107 patients with NSTE-ACS and MVD were included in the analysis, 310 (28.0%) with unstable angina and 797 (72.0%) with non-ST elevation myocardial infarction. The culprit lesion was angiographically identified in 952 (86.0%) patients, while no clear culprit lesion was found in 155 (14.0%) patients. ECG analysis allowed to predict the location of the culprit vessel with low sensitivity (range 28.4%-36.7%) and high specificity (range 90.6%-96.5%). Higher lesion complexity was associated with inability to identify the culprit. Intravascular imaging was applied in 55 patients and helped to identify the culprit lesion in 53 patients (96.4%). There was no difference in all-cause mortality (21.4% vs. 25.8%, p = 0.24) and MACE (39.2% vs. 47.6%, p = 0.07) between the cohorts with or without culprit lesion identification by angiography.

CONCLUSIONS

The culprit lesion appeared unclear by coronary angiography in >10% of patients with NSTE-ACS and MVD. Complementary invasive imaging substantially enhanced the diagnostic accuracy of culprit lesion detection.

An evaluation of pre-hospital emergency medical systems for suspected ST-elevation myocardial infarction in Colorado

OBJECTIVES

Patients presenting with ST-elevation myocardial infarction (STEMI) benefit from rapid cardiac reperfusion therapy. Emergency medical service (EMS) agencies can improve patient outcomes by calling STEMI alerts to the receiving facility. The aim of this study was to evaluate the use of pre-hospital activation systems for suspected ST-elevation myocardial infarctions (STEMI) throughout Colorado.

METHODS

A cross sectional, survey design was utilized to collect all data from EMS agencies in Colorado. A univariable logistic regression model was used to identify factors predictive of an agency reporting that they utilize a STEMI activation protocol.

RESULTS

84.5% [95% CI: 78.3 to 90.7%] of agencies included indicate that they utilize a STEMI activation protocol. Based on the logistic regression analysis, the number of EMT employees was significantly associated with whether or not an agency indicates that they utilize a STEMI activation protocol. For every 10% increase in the number of EMTs employed by an EMS agency, there was a 3.0 [95% CI: 1.5 to 6.0, p = 0.0012] fold increase in the odds of the agency indicating they utilize a STEMI activation protocol.

CONCLUSIONS

Our study provides evidence that larger agencies are more likely to utilize a STEMI activation protocol. In areas without a STEMI system of care, improvements in smaller agencies that cover more ground (with longer transport times) should be the focus for protocol implementation. Based on the current prevalence of such training, competency based training in reading ST-elevations on ECG should be considered by EMS agencies.

A patient with non-ST-segment elevation acute coronary syndrome: Is it possible to predict the culprit coronary artery?

In acute coronary syndromes without ST-segment elevation (NSTE-ACS), identification of the culprit artery is, most often, not possible. In this case report, we elaborate on the likelihood of different culprit arteries in a patient with NSTE-ACS. While her symptoms were progressing, typical ECG findings of ischemia in the left coronary territories were diminishing. Instead, dynamic T-wave changes in the inferior leads were present and were most likely postischemic and "reischemic." Although the culprit artery could not be identified with certainty by means of these subtle changes, they correlated well with the findings on angiography and the ECG recorded afterward. This case report demonstrates the importance of analyzing ECG and its temporal changes in conjunction with evolving symptoms.