Agreement between cardiologists and fellows in interpretation of ischemic electrocardiographic changes in acute myocardial infarction

Critical appraisal of artificial intelligence-based prediction models for cardiovascular disease

The medical field has seen a rapid increase in the development of artificial intelligence (AI)-based prediction models. With the introduction of such AI-based prediction model tools and software in cardiovascular patient care, the cardiovascular researcher and healthcare professional are challenged to understand the opportunities as well as the limitations of the AI-based predictions. In this article, we present 12 critical questions for cardiovascular health professionals to ask when confronted with an AI-based prediction model. We aim to support medical professionals to distinguish the AI-based prediction models that can add value to patient care from the AI that does not.

The interobserver agreement of ECG abnormalities using Minnesota codes in people with type 2 diabetes

OBJECTIVES

To assess the interobserver agreement in categories of electrocardiogram (ECG) abnormalities using the Minnesota Code criteria.

METHODS

We used a random sample of 180 ECGs from people with type 2 diabetes. ECG abnormalities were classified and coded using the Minnesota ECG Classification. Each ECG was independently rated on several abnormalities by an experienced rater (rater 1) and by two cardiologists (raters 2 and 3) trained to apply the Minnesota codes on four Minnesota codes; 1-codes as an indication for myocardial infarction, 4 en 5-codes as an indication for ischemic abnormalities, 3-codes as an indication for left ventricle hypertrophy, 7-1-codes as an indication for ventricular conduction abnormalities, and 8-3-codes as an indication for atrial fibrillation / atrial flutter. After all pairwise tables were summed, the overall agreement, the specific positive and negative agreement were calculated with a 95% confidence interval (CI) for each abnormality. Also, Kappa's with a 95% CI were calculated.

RESULTS

The overall agreement (with 95% CI) were for myocardial infarction, ischemic abnormalities, left ventricle hypertrophy, conduction abnormalities and atrial fibrillation/atrial flutter respectively: 0.87 (0.84-0.91), 0.79 (0.74-0.84), 0.81 (0.76-0.85), 0.93 (0.90-0.95), 0.96 (0.93-0.97).

CONCLUSION

This study shows that the overall agreement of the Minnesota code is good to excellent.

Cardiologists appropriately exclude resuscitated out-of-hospital cardiac arrests from emergency coronary angiography

OBJECTIVE

Emergency coronary angiography after resuscitated out-of-hospital cardiac arrest as a selective or non-selective diagnostic procedure with or without intervention continues to be the subject of debate. This study sought to determine if cardiologists reliably select patients using clinical judgement for emergency coronary angiography without missing acutely ischemic cases requiring revascularization.

METHODS

Presenting clinical details and ECGs (within 2 hours) from 52 consecutive out-of-hospital cardiac arrest patients who underwent non-selective coronary angiography were compiled retrospectively. Three out-of-hospital cardiac arrest-experienced interventional cardiologists, blinded to patient outcome, independently determined working diagnosis, and decision for emergency coronary angiography using clinical judgement. Sensitivity of the cardiologists' decision was assessed with respect to the outcome of acute revascularization. Inter-rater differences, consensus in clinical assessment, and influence of working diagnosis were also investigated.

RESULTS

Sensitivity of individual cardiologist's decision for emergency coronary angiography with respect to acute revascularization was very high (adjusted overall sensitivity = 95.8%, 95% CI = 89-100, cardiologist range = 93%-100%), and perfect for the consensus of 2 or more cardiologists (100%, 95% CI = 79.4-100). There was no statistical difference in the sensitivity of this decision between cardiologists (P < 0.05), and inter-rater agreement was moderate (78% overall agreement, Κ = 0.56).

CONCLUSIONS

Experienced cardiologists recommend emergency coronary angiography in all resuscitated out-of-hospital cardiac arrest requiring acute revascularization and appropriately excluded one-third of patients. Rather than advocating a non-selective, or conversely, a restrictive strategy with respect to coronary angiography after out-of-hospital cardiac arrest, the findings support an individualized approach by a multidisciplinary emergency team that includes experienced cardiologists. The results should be confirmed in a larger prospective study.

The high-risk ECG pattern of ST-elevation myocardial infarction: A substudy of the randomized trial of primary PCI with or without routine manual thrombectomy (TOTAL trial)

BACKGROUND

Useful tools for risk assessment in patients with STEMI are needed. We evaluated the prognostic impact of the evolving myocardial infarction (EMI) and the preinfarction syndrome (PIS) ECG patterns and determined their correlation with angiographic findings and treatment strategy.

METHODS

This substudy of the randomized Trial of Routine Aspiration Thrombectomy with PCI versus PCI Alone in Patients with STEMI (TOTAL) included 7860 patients with STEMI and either the EMI or the PIS ECG pattern. The primary outcome was a composite of death from cardiovascular causes, recurrent MI, cardiogenic shock, or New York Heart Association (NYHA) class IV heart failure within one year.

RESULTS

The primary outcome occurred in 271 of 2618 patients (10.4%) in the EMI group vs. 322 of 5242 patients (6.1%) in the PIS group [AdjustedHR, 1.54; 95% CI, 1.30 to 1.82; p < .001]. The primary outcome occurred in the thrombectomy and PCI alone groups in 131 of 1306 (10.0%) and 140 of 1312 (10.7%) patients with EMI [HR 0.94; 95% CI, 0.74-1.19] and 162 of 2633 (6.2%) and 160 of 2609 (6.1%) patients with PIS [HR 1.00; 95% CI, 0.81-1.25], respectively (p_interaction = 0.679).

CONCLUSIONS

Patients with the EMI ECG pattern proved to have an increased rate of the primary outcome within one year compared to the PIS pattern. Routine manual thrombectomy did not reduce the risk of primary outcome within the different dynamic ECG patterns. The PIS/EMI dynamic ECG classification could help to triage patients in case of simultaneous STEMI patients with immediate need for pPCI.