Risk stratification for ST segment elevation myocardial infarction in the era of primary percutaneous coronary intervention

Machine learning based model for risk prediction after ST-Elevation myocardial infarction: Insights from the North India ST elevation myocardial infarction (NORIN-STEMI) registry

BACKGROUND

Risk prediction following ST-Elevation Myocardial Infarction (STEMI) in resource limited countries is critical to identify patients at an increased risk of mortality who might benefit from intensive management.

METHODS

North India ST-Elevation Myocardial Infarction (NORIN-STEMI) is an ongoing registry that has prospectively enrolled 3,635 STEMI patients. Of these, 3191 patients with first STEMI were included. Patients were divided into two groups: development (n=2668) and validation (unseen) dataset (n=523). Various ML strategies were used to train and tune the model based on validation dataset results that included 31 clinical characteristics. These models were compared in sensitivity, specificity, F1-score, receiver operating characteristic area under the curve (AUC), and overall accuracy to predict mortality at 30 days. ML model decision making was analyzed using the Shapley Additive exPlanations (ShAP) summary plot.

RESULTS

At 30 days, the mortality was 7.7%. On the validation dataset, Extra Tree ML model had the best predictive ability with sensitivity: 85%, AUC: 79.7%, and Accuracy: 75%. ShAP interpretable summary plot determined delay in time to revascularization, baseline cardiogenic shock, left ventricular ejection fraction <30%, age, serum creatinine, heart failure on presentation, female sex, and moderate-severe mitral regurgitation to be major predictors of all-cause mortality at 30 days (P<0.001 for all).

CONCLUSION

ML models lead to an improved mortality prediction following STEMI. ShAP summary plot for the interpretability of the AI model helps to understand the model's decision in identifying high-risk individuals who may benefit from intensified follow-up and close monitoring.

The Difference in Accuracy Between Global Registry of Acute Coronary Events Score and Thrombolysis in Myocardial Infarction Score in Predicting In-Hospital Mortality of Acute ST-Elevation Myocardial Infarction Patients

BACKGROUND

In-hospital mortality of ST-elevation myocardial infarction (STEMI) patients varies between 1% and 19% in Asia. Global Registry of Acute Coronary Events (GRACE) score and Thrombolysis in Myocardial Infarction (TIMI) score are the most frequently used risk scores for predicting in-hospital mortality. These two scores have different accuracy depending on the risk profiles of each region. This study aimed to identify the difference in accuracy between GRACE and TIMI scores.

METHODS

This was an observational cohort retrospective study on consecutive patients with STEMI admitted to Dr. Hasan Sadikin General Hospital Bandung between July 2018 and June 2019.

RESULTS

The risk scores were evaluated in 255 patients with STEMI, whose data were collected from medical records. Patients in this study were 58 ± 11 years old, more often male (78.8%) and have smoking (65.5%), dyslipidemia (61%), hypertension (56.5%) and diabetes mellitus (21.6 %) as their risk factors. Forty-five patients died in hospitalization (17%). The TIMI and GRACE scores revealed a significant graded increase in mortality with a rising score. There was a statistically significant difference in accuracy between the scores of 0.082 (95% confidence interval (CI): 0.040 - 0.125; P < 0.001) with the GRACE score (C statistics of 0.91; P < 0.001) having better accuracy compared to TIMI score (C statistics of 0.83; P < 0.001). This might be due to the fact that the GRACE scoring system has more detail and complete variables than the TIMI score.

CONCLUSION

There is a significant difference between the accuracy of GRACE and TIMI scores in predicting in-hospital mortality in STEMI patients. The accuracy of the GRACE score is better than the TIMI score for predicting in-hospital mortality in STEMI patients.

Differential Network Analysis Reveals Metabolic Determinants Associated with Mortality in Acute Myocardial Infarction Patients and Suggests Potential Mechanisms Underlying Different Clinical Scores Used To Predict Death

We present here the differential analysis of metabolite–metabolite association networks constructed from an array of 24 serum metabolites identified and quantified via nuclear magnetic resonance spectroscopy in a cohort of 825 patients of which 123 died within 2 years from acute myocardial infarction (AMI). We investigated differences in metabolite connectivity of patients who survived, at 2 years, the AMI event, and we characterized metabolite–metabolite association networks specific to high and low risks of death according to four different risk parameters, namely, acute coronary syndrome classification, Killip, Global Registry of Acute Coronary Events risk score, and metabolomics NOESY RF risk score. We show significant differences in the connectivity patterns of several low-molecular-weight molecules, implying variations in the regulation of several metabolic pathways regarding branched-chain amino acids, alanine, creatinine, mannose, ketone bodies, and energetic metabolism. Our results demonstrate that the characterization of metabolite–metabolite association networks is a promising and powerful tool to investigate AMI patients according to their outcomes at a molecular level.

Predictors of acute kidney injury (AKI) in high-risk ST-elevation myocardial infarction (STEMI) patients: A single-center retrospective observational study

Acute kidney injury (AKI) is a frequent complication in ST-elevation myocardial infarction (STEMI) patients. Factors other than contrast exposure have been suggested as major contributors to renal dysfunction in patients undergoing primary percutaneous coronary intervention (PPCI). Our aim was to assess the incidence and risk factors of AKI in high-risk STEMI patients, mostly treated by PPCI with implemented measures to prevent contrast-induced AKI. We retrospectively analyzed data of 245 STEMI patients (165 men, mean age 63.9 ± 11.9 years) admitted to the Department of Medical Intensive Care Unit. Demographic, clinical, and mortality data were compared between AKI and non-AKI group. AKI was defined as a 1.5-fold increase in serum creatinine from baseline level within 24-48 hours. AKI developed in 34/245 (13.9%) patients. PPCI was performed in 226/245 (92.2%) of all STEMI cases, with no difference between AKI and non-AKI group. There were significant differences between AKI and non-AKI group in diabetes mellitus (41.2% vs. 20.9%), prior MI (26.5% vs. 11.8%), prior resuscitation (38.2% vs. 12.4%), admission acute heart failure [AHF] (44.1% vs. 12.8%), in-hospital AHF (70.6% vs. 17.5%), and hospital-acquired infection [HAI] (79.4% vs. 18.0%). Significantly more AKI patients had increased admission CRP ≥25 mg/L (38.2% vs. 11.8%), peak CRP ≥50 mg/L (91.2% vs. 36%), admission troponin I ≥10 mg/L (44.1% vs. 24.6%), peak troponin I ≥50 mg/L (64.7% vs. 44.1%), peak NT-proBNP ≥400 pmol/L (82.4% vs. 27.5%), and ejection fraction <45% (76.5% vs. 33.6%). Mortality was significantly increased in AKI group, including in-hospital (52.9% vs. 7.1%), 30-day (64.7% vs. 10.7%) and 6-month mortality (70.6% vs. 13.7%). Significant independent predictors of AKI were prior resuscitation (OR 4.171, 95% CI 1.088-15.998), HAI (OR 7.974, 95% CI 1.992-31.912), and peak NT-proBNP (OR 21.261, 95% CI 2.357-191.795). To reduce the risk of AKI in STEMI patients, early diagnosis and treatment of AHF and HAIs are advisable.

Comparative effectiveness of primary PCI versus fibrinolytic therapy for ST elevation myocardial infarction: a review of the literature

Aim: To compare the effectiveness of primary percutaneous coronary intervention (pPCI) and fibrinolytic therapy (FL) for the acute management of ST elevation myocardial infarction (STEMI). Methods: A review of guidelines and PubMed literature comparing clinical outcomes of patients with STEMI treated with pPCI or FL. Results: Earlier trials reported reduced mortality and reinfarction with pPCI. Recent randomized data suggest similar outcomes for delayed pPCI compared with FL, especially in geographically remote areas. Guidelines recommend pPCI as the preferred reperfusion strategy for STEMI, if available within 120 mins of first medical contact. Conclusion: pPCI is the preferred treatment strategy for STEMI. However, FL with subsequent percutaneous coronary intervention remains a viable option for those in rural areas.