Performance of the GRACE Risk Score 2.0 Simplified Algorithm for Predicting 1-Year Death After Hospitalization for an Acute Coronary Syndrome in a Contemporary Multiracial Cohort

Diagnostic and prognostic role of serum interleukin-6 and carotid ultrasonography to detect subclinical atherosclerosis in patients with RA and ANCA-associated vasculitis

ANCA-associated vasculitis (AAV) can affect multiple organs with severe life-threatening manifestations. Disease monitoring is difficult due to a lack of defined biomarkers. We aimed to assess the diagnostic role of serum interleukin-6 and vascular ultrasonography in AAV and subclinical atherosclerosis. The study included 20 AAV patients and two control groups of 34 patients with rheumatoid arthritis (RA) and 35 healthy controls. The levels of Il-6, carotid intima-media thickness test (CIMT), atherosclerotic plaque, and degree of stenosis were investigated. A GRACE-risk score was calculated for AAV and RA patients. The AAV patients had elevated levels of IL-6 (115 ± 23.96) compared to the RA patients (91.25 ± 42.63) and the healthy controls (15.65 ± 3.30), p < 0.001. IL-6 showed a diagnostic accuracy of 73% in distinguishing AAV from RA patients (AUC = 0.730; 95% CI 0.591 to 0834). In the AAV group, CIMT was 1.09, above the upper reference value of 0.90, p < 0.001. The AAV patients had a higher median GRACE risk score, and 60% of them had a high risk of cardiovascular events as compared to 35% of the RA patients. Sonography of extracranial vessels and serum levels of IL-6 can be used in daily clinical practice to diagnose and monitor patients with AAV.

Adding the value of the Charlson Comorbidity Index to the GRACE score for mortality prediction in acute coronary syndromes

BACKGROUND

Scarce and conflicting data still exist about the role of the Charlson Comorbidity Index (CCI) when added to the traditional Global Registry of Acute Coronary Events (GRACE) risk score for outcome prediction in patients with acute coronary syndrome (ACS).

METHODS

All consecutive admissions due to ACS, from 1 January 2018 to 31 December 2020 were retrospectively reviewed from an internal database of a tertiary cardiac center in Salerno (Italy). Logistic and Cox proportional regression analyses were performed in order to assess the contribution of the CCI on 30-day and long-term mortality. The CCI adding value to the GRACE score was analyzed with several measures of improvement in discrimination: increase in the area under the receiver-operating characteristic curve (AUC), the integrated discrimination improvement (IDI), and the categorical and continuous net reclassification improvement (cNRI) more than 0. Robustness of the results was assessed through an internal validation procedure with bootstrapping.

RESULTS

One thousand three hundred and ten patients were identified. The median age was 68 (58-78) years. One hundred and twenty (9.2%) and 113 (9.5%) deaths occurred, respectively, during the first 30 days from admission and during long-term follow-up (median follow-up time: 13 months; interquartile range: 9-24). After multivariate regression analysis, the CCI was not associated with short-term mortality, while it was significantly and independently associated with long-term mortality along with the GRACE score (hazard ratio: 1.34, 95% confidence interval: 1.22-1.47; P  < 0.001). An additive effect of CCI with the GRACE risk score was observed in predicting long-term mortality: AUC from 0.768 to 0.819 ( P  = 0.003), category-based NRI: 0.215, cNRI>0: 0.669 ( P  < 0.001), IDI: 0.066 ( P  < 0.001).

CONCLUSION

The CCI is a predictor of long-term mortality and improves risk stratification of patients with ACS over the GRACE risk score.

A Machine Learning-Based Applied Prediction Model for Identification of Acute Coronary Syndrome (ACS) Outcomes and Mortality in Patients during the Hospital Stay

Nowadays, machine learning (ML) is a revolutionary and cutting-edge technology widely used in the medical domain and health informatics in the diagnosis and prognosis of cardiovascular diseases especially. Therefore, we propose a ML-based soft-voting ensemble classifier (SVEC) for the predictive modeling of acute coronary syndrome (ACS) outcomes such as STEMI and NSTEMI, discharge reasons for the patients admitted in the hospitals, and death types for the affected patients during the hospital stay. We used the Korea Acute Myocardial Infarction Registry (KAMIR-NIH) dataset, which has 13,104 patients' data containing 551 features. After data extraction and preprocessing, we used the 125 useful features and applied the SMOTETomek hybrid sampling technique to oversample the data imbalance of minority classes. Our proposed SVEC applied three ML algorithms, such as random forest, extra tree, and the gradient-boosting machine for predictive modeling of our target variables, and compared with the performances of all base classifiers. The experiments showed that the SVEC outperformed other ML-based predictive models in accuracy (99.0733%), precision (99.0742%), recall (99.0734%), F1-score (99.9719%), and the area under the ROC curve (AUC) (99.9702%). Overall, the performance of the SVEC was better than other applied models, but the AUC was slightly lower than the extra tree classifier for the predictive modeling of ACS outcomes. The proposed predictive model outperformed other ML-based models; hence it can be used practically in hospitals for the diagnosis and prediction of heart problems so that timely detection of proper treatments can be chosen, and the occurrence of disease predicted more accurately.

Diagnostic Model of In-Hospital Mortality in Patients with Acute ST-Segment Elevation Myocardial Infarction Used Artificial Intelligence Methods

Background

Preventing in-hospital mortality in patients with ST-segment elevation myocardial infarction (STEMI) is a crucial step.

Objectives

The objective of our research was to develop and externally validate the diagnostic model of in-hospital mortality in acute STEMI patients used artificial intelligence methods.

Methods

We divided nonrandomly the American population with acute STEMI into a training set, a test set, and a validation set. We converted the unbalanced data into balanced data. We used artificial intelligence methods to develop and externally validate several diagnostic models. We used confusion matrix combined with the area under the receiver operating characteristic curve (AUC) to evaluate the pros and cons of the above models.

Results

The strongest predictors of in-hospital mortality were age, gender, cardiogenic shock, atrial fibrillation (AF), ventricular fibrillation (VF), third degree atrioventricular block, in-hospital bleeding, underwent percutaneous coronary intervention (PCI) during hospitalization, underwent coronary artery bypass grafting (CABG) during hospitalization, hypertension history, diabetes history, and myocardial infarction history. The F2 score of logistic regression in the training set, the test set, and the validation dataset was 0.81, 0.6, and 0.59, respectively. The AUC of logistic regression in the training set, the test set, and the validation data set was 0.77, 0.78, and 0.8, respectively. The diagnostic model built by logistic regression was the best.

Conclusion

The strongest predictors of in-hospital mortality were age, gender, cardiogenic shock, AF, VF, third degree atrioventricular block, in-hospital bleeding, underwent PCI during hospitalization, underwent CABG during hospitalization, hypertension history, diabetes history, and myocardial infarction history. We had used artificial intelligence methods developed and externally validated several diagnostic models of in-hospital mortality in acute STEMI patients. The diagnostic model built by logistic regression was the best. We registered this study with the registration number ChiCTR1900027129 (the WHO International Clinical Trials Registry Platform (ICTRP) on 1 November 2019).

External validation of the GRACE risk score and the risk-treatment paradox in patients with acute coronary syndrome

Objectives

To validate the Global Registry of Acute Coronary Events (GRACE) risk score and examine the extent and impact of the risk–treatment paradox in contemporary patients with acute coronary syndrome (ACS).

Methods

Data from 5015 patients with ACS enrolled in the FORCE-ACS registry between January 2015 and December 2019 were used for model validation. The performance of the GRACE risk score for predicting in-hospital and 1-year mortality was evaluated based on indices of model discrimination and calibration. Differences in the delivery of guideline-recommended care among patients who survived hospitalisation (n=4911) per GRACE risk stratum were assessed and the association with postdischarge mortality was examined.

Results

Discriminative power of the GRACE risk score was good for predicting in-hospital (c-statistic: 0.86; 95% CI: 0.83 to 0.90) and 1-year mortality (c-statistic: 0.82; 95% CI: 0.79 to 0.84). However, the GRACE risk score overestimated the absolute in-hospital and 1-year mortality risk (Hosmer-Lemeshow goodness-of-fit test p<0.01). Intermediate-risk and high-risk patients were 12% and 29% less likely to receive optimal guideline-recommended care compared with low-risk patients, respectively. Optimal guideline-recommended care was associated with lower mortality in intermediate- and high-risk patients.

Conclusions

The GRACE risk score identified patients at higher risk for in-hospital and 1-year mortality, but overestimated absolute risk levels in contemporary patients. Optimal guideline-recommended care was associated with lower mortality in intermediate-risk and high-risk patients, but was less likely to be delivered with increasing mortality risk.

Association of Prolonged Emergency Department Length of Stay with Adverse Events in Patients with Non-ST-Elevation Acute Coronary Syndrome

Objective

To study the association between prolonged emergency department length of stay (EDLOS) and in-hospital adverse events in patients with non-ST-segment elevation acute coronary syndrome (NSTE-ACS).

Methods

In this retrospective cohort study, the medical records of 738 patients diagnosed with NSTE-ACS and admitted to the emergency department (ED) from 1 January 2013 to 31 December 2019 were reviewed. The patients were categorized into groups with EDLOS < 4 hours and EDLOS ≥ 4 hours, and baseline characteristics, clinical presentation, Killip classification, Global Registry of Acute Coronary Events score, investigations, use of the European Society of Cardiology (ESC) 0/1-hour and 0/3-hour algorithms, and treatments in the ED were compared between the groups. The associations of in-hospital adverse events with EDLOS were examined using univariate logistic regression.

Results

Four hundred and twenty-three (57.3%) patients had an EDLOS of ≥ 4 hours, and the median (IQR) EDLOS was 4.48 hours (3.03, 6.20 hours). EDLOS ≥ 4 h was associated with a prolonged time to receive P2Y₁₂ inhibitors and anticoagulants (P < 0.001). However, the two groups showed no significant differences in in-hospital adverse events (congestive heart failure [CHF], shock, stroke or transient ischemic attack [TIA], major bleeding, arrhythmia, recurrent myocardial infarction, death, and one or more adverse events). Nevertheless, a non-significant trend for a higher rate of adverse events (CHF, shock, major bleeding, arrhythmia, recurrent myocardial infarction, death, and one or more adverse events) with longer EDLOS was observed in the subgroup of patients who received diuretic or antiarrhythmic drugs, ventilator or bilevel positive airway pressure support, oxygen support, or inotropic/vasopressor drugs in the ED.

Conclusion

Prolonged EDLOS showed a significant association with longer times to receive P2Y₁₂ inhibitors and anticoagulants. However, the EDLOS < 4 hour and EDLOS ≥ 4 hour groups of patients with NSTE-ACS showed no significant differences in the rates of in-hospital adverse events. Patients who receive cardiovascular medications in the ED or are on respiratory support should be hospitalized as soon as practically possible. Proper use of the 0/1-hour algorithm over the 0/3-hour algorithm without unnecessary repeated cardiac troponin tests in the ED could reduce the EDLOS in patients with NSTE-ACS.

Contemporary Review of Risk Scores in Prediction of Coronary and Cardiovascular Deaths

PURPOSE OF REVIEW

Explore the current literature supporting risk stratification scores for prediction of coronary and cardiovascular disease deaths.

RECENT FINDINGS

Accurate risk prediction remains the foundation of management choice in primary prevention. When applied to new populations, the calibration of a predictive model will deteriorate, although discrimination changes minimally. One of the approaches with better performance and validation is the initial use of pooled cohort equation to identify low and high-risk patients, followed by coronary artery calcium scoring in those with borderline to intermediate risk. It is important to utilize a risk stratification tool that has been validated in a patient population that resembles the one used to develop the original tool to maintain adequate calibration. It is likely that the future of mortality risk prediction will develop in combined clinical risk predictors and cardiovascular imaging, such coronary artery calcium (CAC) scoring that renders the highest predictive accuracy.

Anemia or other comorbidities? using machine learning to reveal deeper insights into the drivers of acute coronary syndromes in hospital admitted patients

Acute coronary syndromes (ACS) are a leading cause of deaths worldwide, yet the diagnosis and treatment of this group of diseases represent a significant challenge for clinicians. The epidemiology of ACS is extremely complex and the relationship between ACS and patient risk factors is typically non-linear and highly variable across patient lifespan. Here, we aim to uncover deeper insights into the factors that shape ACS outcomes in hospitals across four Arabian Gulf countries. Further, because anemia is one of the most observed comorbidities, we explored its role in the prognosis of most prevalent ACS in-hospital outcomes (mortality, heart failure, and bleeding) in the region. We used a robust multi-algorithm interpretable machine learning (ML) pipeline, and 20 relevant risk factors to fit predictive models to 4,044 patients presenting with ACS between 2012 and 2013. We found that in-hospital heart failure followed by anemia was the most important predictor of mortality. However, anemia was the first most important predictor for both in-hospital heart failure, and bleeding. For all in-hospital outcome, anemia had remarkably non-linear relationships with both ACS outcomes and patients' baseline characteristics. With minimal statistical assumptions, our ML models had reasonable predictive performance (AUCs > 0.75) and substantially outperformed commonly used statistical and risk stratification methods. Moreover, our pipeline was able to elucidate ACS risk of individual patients based on their unique risk factors. Fully interpretable ML approaches are rarely used in clinical settings, particularly in the Middle East, but have the potential to improve clinicians' prognostic efforts and guide policymakers in reducing the health and economic burdens of ACS worldwide.

Risk Prediction of Cardiovascular Events by Exploration of Molecular Data with Explainable Artificial Intelligence

Cardiovascular diseases (CVD) annually take almost 18 million lives worldwide. Most lethal events occur months or years after the initial presentation. Indeed, many patients experience repeated complications or require multiple interventions (recurrent events). Apart from affecting the individual, this leads to high medical costs for society. Personalized treatment strategies aiming at prediction and prevention of recurrent events rely on early diagnosis and precise prognosis. Complementing the traditional environmental and clinical risk factors, multi-omics data provide a holistic view of the patient and disease progression, enabling studies to probe novel angles in risk stratification. Specifically, predictive molecular markers allow insights into regulatory networks, pathways, and mechanisms underlying disease. Moreover, artificial intelligence (AI) represents a powerful, yet adaptive, framework able to recognize complex patterns in large-scale clinical and molecular data with the potential to improve risk prediction. Here, we review the most recent advances in risk prediction of recurrent cardiovascular events, and discuss the value of molecular data and biomarkers for understanding patient risk in a systems biology context. Finally, we introduce explainable AI which may improve clinical decision systems by making predictions transparent to the medical practitioner.

Development and validation of a risk prediction model for in-hospital major cardiovascular events in patients hospitalised for acute myocardial infarction

OBJECTIVES

Patients admitted to hospital with acute myocardial infarction (AMI) have considerable variability in in-hospital risks, resulting in higher demands on healthcare resources. Simple risk-assessment tools are important for the identification of patients with higher risk to inform clinical decisions. However, few risk assessment tools have been built that are suitable for populations with AMI in China. We aim to develop and validate a risk prediction model, and further build a risk scoring system.

DESIGN

Data from a nationally representative retrospective study was used to develop the model. Patients from a prospective study and another nationally representative retrospective study were both used for external validation.

SETTING

161 nationally representative hospitals, and 53 and 157 other hospitals were involved in the above three studies, respectively.

PARTICIPANTS

8010 patients hospitalised for AMI were included as development sample, and 4485 and 11 223 other patients were included as validation samples in their corresponding studies.

PRIMARY AND SECONDARY OUTCOME MEASURES

The in-hospital major adverse cardiovascular events (MACE) was defined as death from any cause, recurrent AMI, or ischaemic stroke.

RESULTS

The proportion of in-hospital MACE was 11.7%, 8.8% and 11.4% among the development sample and two external-validation samples, respectively. Nine predictors (ie, age, sex, left ventricular ejection fraction, Killip class, systolic blood pressure, creatinine, white blood cell count, heart rate and blood glucose) were independently associated with in-hospital MACE. The model performed well on both discrimination and calibration capability, with areas under the Receiver Operating Characteristic Curve (ROC) curve of 0.85, 0.74 and 0.80, and calibration slopes of 0.98, 0.84 and 0.97 in the development sample and two external validation samples, respectively. A point-based risk scoring system was built with good discrimination and reclassification ability.

CONCLUSIONS

A prediction model using readily available clinical parameters was developed and externally validated to estimate risks of in-hospital MACE among patients with AMI, thereby better informing decision-making in improving clinical care.

Clinical impact of estimated plasma volume status and its additive effect with the GRACE risk score on in-hospital and long-term mortality for acute myocardial infarction

Background

Estimated plasma volume status (ePVS) is a well-validated prognostic indicator in heart failure. However, it remains unclear whether ePVS has prognostic significance in patients with acute myocardial infarction (AMI). Moreover, there is no available information on its additive effect with the Global Registry of Acute Coronary Events (GRACE) risk score in AMI patients.

Methods

Data were obtained from the Osaka Acute Coronary Insufficiency Study (OACIS) registry database. Patients whose data were available for ePVS derived from Hakim’s formula and the GRACE risk score were studied. The primary endpoints were in-hospital and 5-year mortality.

Results

Of 3930 patients, 206 and 200 patients died during hospitalization and 5 years after discharge, respectively. After adjustment, ePVS remained an independent predictor of in-hospital death (OR:1.02, 95% CI: 1.00–1.04, p = 0.036), and 5-year mortality(HR:1.03, 95% CI: 1.01–1.04, p < 0.001). An additive effect of ePVS with the GRACE risk score was observed in predicting the 5-year mortality with an area under the receiver operating characteristic curve (AUC) from 0.744 to 0.763 (p = 0.026), but not in-hospital mortality (the AUC changed from 0.875 to 0.875, p = 0.529). The incremental predictive value of combining ePVS and the GRACE risk score for 5-year mortality was significantly improved, as shown by the net reclassification improvement (NRI:0.378, p < 0.001) and integrated discrimination improvement (IDI:0.014, p < 0.001).

Conclusions

In patients with AMI, ePVS independently predicted in-hospital and long-term mortality. In addition, ePVS had an additive effect with the GRACE risk score on long-term mortality. Therefore, ePVS may be useful for identifying high-risk subjects for intensive treatment.

Modern NCDR and ACTION risk models outperform the GRACE model for prediction of in-hospital mortality in acute coronary syndrome in a German cohort

BACKGROUND AND PURPOSE

Risk prediction with the Global Registry of Acute Coronary Events (GRACE) risk model is guideline-recommended in acute coronary syndrome (ACS) patients. However, the performance of more contemporary scores derived from ACTION (Acute Coronary Treatment and Intervention Outcomes Network) and National Cardiovascular Data (NCDR) registries remains incompletely understood. We aimed to compare these models in German ACS patients.

METHODS AND RESULTS

A total of 1567 patients with (Non-)ST-segment elevation myocardial infarction (NSTEMI: 1002 patients, STEMI: 565 patients) undergoing invasive management at University Hospital Düsseldorf (Germany) from 2014 to 2018 were included. Overall in-hospital mortality was 7.5% (NSTEMI 3.7%, STEMI 14.5%). Parameters for calculation of GRACE 1.0, GRACE 2.0, ACTION and NCDR risk models and in-hospital mortality were assessed and risk model performance was compared. The GRACE 1.0 risk model for prediction of in-hospital mortality discriminated risk superior (c-index 0.84) to its successor GRACE 2.0 (c-index 0.79, p_{GRACE1.0vsGRACE2.0} = 0.0008). The NCDR model performed best in discrimination of risk in ACS overall (c-index 0.89; p_ACTIONvsNCDR < 0.0001; p_GRACEvsNCDR < 0.0001) and showed superior performance compared to GRACE in NSTEMI and STEMI subgroups (p_GRACEvsNCDR both < 0.02). ACTION and GRACE risk models performed comparable to each other (both c-index 0.84, p_{GRACEvsACTION} = 0.68), with advantages for ACTION in NSTEMI patients (c-index 0.87 vs. 0.84 (GRACE); p_{GRACEvsACTION} = 0.02). ACTION and GRACE 2.0 showed the most accurate calibration of all models.

CONCLUSIONS

In a contemporary German patient population with ACS, modern NCDR and ACTION risk models showed superior performance in prediction of in-hospital mortality compared to the gold-standard GRACE model.

Predicting 1-, 3- and 5-year outcomes in patients with coronary artery disease: A comparison of available risk assessment scores

BACKGROUND AND AIMS

Thromboischemic and bleeding events are rare but life-threatening complications after percutaneous coronary intervention (PCI). Various risk assessment models have been established to predict short- and long-term adverse events in patients with chronic and acute coronary syndromes (CCS, ACS). The aim of the present study was to compare available risk assessment systems based on their performance in identifying high-risk patients with symptomatic coronary artery disease (CAD).

METHODS

We enrolled 1565 consecutive patients with symptomatic CAD (n = 821 CCS, n = 744 ACS). CALIBER, DAPT, GRACE 2.0, PARIS-CTE, PARIS-MB, PRECISE-DAPT and PREDICT-STABLE scores were calculated in appropriate patient subgroups. All patients were followed-up for 1, 3 and 5 years for all-cause death (ACD), myocardial infarction (MI), ischemic stroke (IS) and bleeding. The primary combined ischemic endpoint (CE) consisted of ACD, MI and/or IS. Secondary endpoints were defined as single occurrence of either ACD, MI, IS, or bleeding.

RESULTS

GRACE 2.0 score showed good discrimination performance (AUC>0.7) for CE in a 3- and 5-year follow-up. CALIBER, GRACE 2.0 and PARIS-CTE showed best performance (AUC>0.7) in predicting ACD throughout the follow-up, whereas IS was best predicted by PARIS-CTE and CALIBER scores. None of the scores performed well (AUC>0.7) in predicting MI or bleeding.

CONCLUSIONS

In a consecutive German CAD cohort, CALIBER, GRACE 2.0 and PARIS-CTE scores performed best in predicting CE, ACD and/or IS whereas none of the selected scores could predict MI and bleeding efficiently.

Dual Antiplatelet Therapy Duration in Medically Managed Acute Coronary Syndrome Patients: Sub-Analysis of the OPT-CAD Study

INTRODUCTION

Optimal dual antiplatelet therapy (DAPT) duration for medically managed acute coronary syndrome (ACS) (MMACS) patients is still unknown. We explored the efficacy and safety of ≥ 12-month DAPT among MMACS patients.

METHODS

In this sub-analysis of the optimal antiplatelet therapy for Chinese Patients with Coronary Artery Disease study (NCT01735305), clinical outcomes among MMACS patients were compared between the < 12-month and ≥ 12-month DAPT groups. The primary efficacy endpoint was a composite of cardiac death, myocardial infarction, and stroke. Safety endpoints included the Bleeding Academic Research Consortium (BARC) 2-5, BARC 3-5, and all bleeding events. Propensity score matching (PSM) was used to compare baseline characteristics between the < 12-month and ≥ 12-month DAPT groups.

RESULTS

In this cohort of ACS patients (n = 10,016), MMACS patients (n = 2967) were less likely to use DAPT at 12 (31.64% vs. 67.47%, P < 0.0001) and 24 (13.82% vs. 18.71%, P < 0.0001) months and experienced more ischemic events at 12 (4.55% vs. 3.40%, P = 0.006) and 24 (6.88% vs. 5.08%, P = 0.0004) months than those treated with percutaneous coronary intervention (n = 7049). Among MMACS patients, the rate of primary efficacy endpoint occurring within the second year was significantly higher in the < 12-month DAPT group than in the ≥ 12-month group both before (2.88% vs. 1.60%, P = 0.040) and after (3.19% vs. 1.71%, P = 0.045) PSM. After PSM, no significant differences in all bleeding, BARC 2-5, and BARC 3-5 bleeding were found between the groups.

CONCLUSION

MMACS patients with insufficient DAPT management experienced relatively more ischemic events. DAPT for at least 1 year may be beneficial to this special population without significantly increasing the bleeding risks.

TRIAL REGISTRATION

ClinicalTrials.gov identifier, NCT01735305.

Long-Term Clinical Outcomes for Non-ST Elevation Acute Coronary Syndrome Patients with High-Risk Angiographic Findings Undergoing Percutaneous Coronary Intervention

Objective

We aim to evaluate the long-term prognosis of non-ST elevation acute coronary syndrome (NSTE-ACS) patients with high-risk coronary anatomy (HRCA).

Background

Coronary disease severity is important for therapeutic decision-making and prognostication among patients presenting with NSTE-ACS. However, long-term outcome in patients undergoing percutaneous coronary intervention (PCI) with HRCA is still unknown.

Method

NSTE-ACS patients undergoing PCI in Fuwai Hospital in 2013 were prospectively enrolled and subsequently divided into HRCA and low-risk coronary anatomy (LRCA) groups according to whether angiography complies with the HRCA definition. HRCA was defined as left main disease >50%, proximal LAD lesion >70%, or 2- to 3- vessel disease involving the LAD. Prognosis impact on 2-year and 5-year major adverse cardiovascular and cerebrovascular events (MACCE) is analyzed.

Results

Out of 4,984 enrolled patients with NSTE-ACS, 3,752 patients belonged to the HRCA group, while 1,232 patients belonged to the LRCA group. Compared with the LRCA group, patients in the HRCA group had worse baseline characteristics including higher age, more comorbidities, and worse angiographic findings. Patients in the HRCA group had higher incidence of unplanned revascularization (2 years: 9.7% vs. 5.1%, p < 0.001; 5 years: 15.4% vs. 10.3%, p < 0.001), 2-year MACCE (13.1% vs. 8.8%, p < 0.001), and 5-year death/MI/revascularization/stroke (23.0% vs. 18.4%, p = 0.001). Kaplan–Meier survival analysis showed similar results. After adjusting for confounding factors, HRCA is independently associated with higher risk of revascularization (2 years: HR = 1.636, 95% CI: 1.225–2.186; 5 years: HR = 1.460, 95% CI: 1.186–1.798), 2-year MACCE (HR = 1.275, 95% CI = 1.019–1.596) and 5-year death/MI/revascularization/stroke (HR = 1.183, 95% CI: 1.010–1.385).

Conclusion

In our large cohort of Chinese patients, HRCA is an independent risk factor for long-term unplanned revascularization and MACCE.

Mortality prediction algorithms for patients undergoing primary percutaneous coronary intervention

Mortality risk of ST-segment elevation myocardial infarction (STEMI) patients shows high variability. In order to assess individual risk, a number of scoring systems have been developed and validated. Yet, as treatment approaches evolve over time with improving outcomes, there is a need to build new risk prediction algorithms to maintain/increase prognostic accuracy. One of the most relevant improvements of therapy is primary percutaneous coronary intervention (PCI). We overview the characteristics and discriminative performance of the most studied and some recently constructed mortality risk models that were validated in patients with STEMI who underwent primary PCI.

Machine learning for predicting cardiac events: what does the future hold?

Introduction: With the increase in the number of patients with cardiovascular diseases, better risk-prediction models for cardiovascular events are needed. Statistical-based risk-prediction models for cardiovascular events (CVEs) are available, but they lack the ability to predict individual-level risk. Machine learning (ML) methods are especially equipped to handle complex data and provide accurate risk-prediction models at the individual level.Areas covered: In this review, the authors summarize the literature comparing the performance of machine learning methods to that of traditional, statistical-based models in predicting CVEs. They provide a brief summary of ML methods and then discuss risk-prediction models for CVEs such as major adverse cardiovascular events, heart failure and arrhythmias.Expert opinion: Current evidence supports the superiority of ML methods over statistical-based models in predicting CVEs. Statistical models are applicable at the population level and are subject to overfitting, while ML methods can provide an individualized risk level for CVEs. Further prospective research on ML-guided treatments to prevent CVEs is needed.

Defining and managing patients with non-ST-elevation myocardial infarction: Sorting through type 1 vs other types

Advances in cardiovascular (CV) imaging, redefined electrocardiogram criteria, and high‐sensitivity CV biomarker assays have enabled more differentiated etiological classification of myocardial infarction (MI). Type 1 MI has a different underlying pathophysiology than type 2 through type 5 MI; type 1 MI is characterized primarily by intracoronary atherothrombosis and the other types by a variety of mechanisms, which can occur with or without an atherosclerotic component. In type 2 MI, there is evidence of myocardial oxygen supply‐demand imbalance unrelated to acute coronary atherothrombosis. Types 1 and 2 MI are spontaneous events, while type 4 and type 5 are procedure‐related; type 3 MI is identified only after death. Most type 1 and type 2 MI present as non‐ST‐elevation MI (NSTEMI), although both types can also present as ST‐elevation MI. Because of their different underlying etiologies, type 1 and type 2 NSTEMI have different presentation and prognosis and should be managed differently. In this article, we discuss the epidemiology, prognosis, and management of NSTEMI occurring in the setting of underlying type 1 or type 2 pathophysiology. Most NSTEMI (65%–90%) are type 1 MI. Patients with type 2 MI have multiple comorbidities and causes of in‐hospital mortality among these patients are not always CV‐related. It is important to distinguish between type 1 and type 2 NSTEMI early in the clinical course to allow for the use of the most appropriate treatments that will provide the greatest benefit for these patients.

A machine learning-based 1-year mortality prediction model after hospital discharge for clinical patients with acute coronary syndrome

Cardiovascular disease is the leading cause of death worldwide so, early prediction and diagnosis of cardiovascular disease is essential for patients affected by this fatal disease. The goal of this article is to propose a machine learning-based 1-year mortality prediction model after discharge in clinical patients with acute coronary syndrome. We used the Korea Acute Myocardial Infarction Registry data set, a cardiovascular disease database registered in 52 hospitals in Korea for 1 November 2005-30 January 2008 and selected 10,813 subjects with 1-year follow-up traceability. The ranges of hyperparameters to find the best prediction model were selected from four different machine learning models. Then, we generated each machine learning-based mortality prediction model with hyperparameters completed the range fitness via grid search using training data and was evaluated by fourfold stratified cross-validation. The best prediction model with the highest performance was found, and its hyperparameters were extracted. Finally, we compared the performance of machine learning-based mortality prediction models with GRACE in area under the receiver operating characteristic curve, precision, recall, accuracy, and F-score. The area under the receiver operating characteristic curve in applied machine learning algorithms was averagely improved up to 0.08 than in GRACE, and their major prognostic factors were different. This implementation would be beneficial for prediction and early detection of major adverse cardiovascular events in acute coronary syndrome patients.

Design and rationale for the "Me & My Heart" (eMocial) study: A randomized evaluation of a new smartphone-based support tool to increase therapy adherence of patients with acute coronary syndrome

A novel smartphone‐based patient support tool was developed to increase the adherence to antiplatelet therapy and lifestyle changes in patients after coronary angioplasty for acute coronary syndrome (ACS). The eMocial study (http://clinicaltrials.gov Identifier: NCT02615704) investigates whether an electronic support tool will improve adherence to comedication and lifestyle changes in ACS patients. The primary hypothesis of this trial is that an electronic support tool can increase adherence to comedication (primary endpoint) thereby supporting positive lifestyle changes (secondary endpoints). Patients hospitalized with ACS (ST elevation myocardial infarction [STEMI], non‐ST elevation myocardial infarction [NSTEMI], or unstable angina pectoris) and treated with ticagrelor coadministered with low‐dose acetylsalicylic acid will be randomized 1:1 to an active group receiving the patient support tool via a smartphone‐based application or to a control group without the patient support tool. Patient questionnaires to evaluate lifestyle changes and quality of life will be used at baseline and at the end of the 48‐week observation phase. Patients are asked to fill out questionnaires to determine their adherence, treatment attitudes, health‐care utilization and risk factors on a monthly basis. The study was started in February 2016 and the completion date is scheduled for October 2019. For final analysis 664 patients are expected be available. Preliminary baseline demographics were unstable angina pectoris (13.7%), NSTEMI (49.9%), STEMI (36.4%), male gender (86.3%), and diabetes mellitus (17.6%). Our study could significantly help to understand how inadequate adherence to antiplatelet therapy in ACS patients could be improved with a smartphone‐based application.

Evaluation of the impact of the GRACE risk score on the management and outcome of patients hospitalised with non-ST elevation acute coronary syndrome in the UK: protocol of the UKGRIS cluster-randomised registry-based trial

INTRODUCTION

For non-ST-segment elevation acute coronary syndrome (NSTEACS) there is a gap between the use of class I guideline recommended therapies and clinical practice. The Global Registry of Acute Coronary Events (GRACE) risk score is recommended in international guidelines for the risk stratification of NSTEACS, but its impact on adherence to guideline-indicated treatments and reducing adverse clinical outcomes is unknown. The objective of the UK GRACE Risk Score Intervention Study (UKGRIS) trial is to assess the effectiveness of the GRACE risk score tool and associated treatment recommendations on the use of guideline-indicated care and clinical outcomes.

METHODS AND ANALYSIS

The UKGRIS, a parallel-group cluster randomised registry-based controlled trial, will allocate hospitals in a 1:1 ratio to manage NSTEACS by standard care or according to the GRACE risk score and associated international guidelines. UKGRIS will recruit a minimum of 3000 patients from at least 30 English National Health Service hospitals and collect healthcare data from national electronic health records. The co-primary endpoints are the use of guideline-indicated therapies, and the composite of cardiovascular death, non-fatal myocardial infarction, new onset heart failure hospitalisation or cardiovascular readmission at 12 months. Secondary endpoints include duration of inpatient hospital stay over 12 months, EQ-5D-5L responses and utilities, unscheduled revascularisation and the components of the composite endpoint over 12 months follow-up.

ETHICS AND DISSEMINATION

The study has ethical approval (North East - Tyne & Wear South Research Ethics Committee reference: 14/NE/1180). Findings will be announced at relevant conferences and published in peer-reviewed journals in line with the funder's open access policy.

TRIAL REGISTRATION NUMBER

ISRCTN29731761; Pre-results.

Evaluation of a novel score for predicting 2-year outcomes in patients with acute coronary syndrome after percutaneous coronary intervention

BACKGROUND

A novel risk model to predict long-term mortality in patients with acute coronary syndrome (ACS), derived from the EPICOR (long-term follow-up of antithrombotic management patterns in acute coronary syndrome patients) registry, has been released recently and its performance remains to be assessed. The objective is to evaluate the EPICOR score for 2-year mortality risk in ACS patients after percutaneous coronary intervention (PCI).

METHODS

From January to December in 2013, a total of 6087 consecutive patients presenting with ACS who were scheduled for PCI were enrolled. Use online simplified EPICOR calculator to assess the expected risk of death.

RESULTS

Sixty-eight patients (1.1%) died during 2-year follow-up. The areas under the receiver operating characteristics curve for mortality in the overall population, ST-segment elevation myocardial infarction (STEMI), and non-ST-segment elevation ACS were 0.712 (95% CI, 0.650-0.772; p < 0.001), 0.790 (95% CI, 0.676-0.903; p < 0.001), and 0.683 (95% CI, 0.615-0.751; p < 0.001), respectively. Moreover, it was noninferior to the updated Global Registry of Acute Coronary Events (GRACE) risk score. Patients were stratified into three categories: low-risk (n = 3382), medium-risk (n = 2547), and high-risk (n = 158). Kaplan-Meier curve demonstrated significant ongoing divergence in both mortality (0.6% vs 1.3% vs 9.5%; p < 0.001) and major adverse cardiovascular and cerebrovascular events (MACCEs) (11.8% vs 12.3% vs 19.6%; p = 0.014) among them. Multivariate Cox analysis revealed that medium- and high-risk groups predicted 2- and 12-fold hazards of death comparing to the lowest. Yet, it was not a significant predictor for MACCEs after adjusting confounding factors.

CONCLUSION

The simplified EPICOR score showed fair discriminatory power of 2-year mortality in patients with ACS and an improved performance in the STEMI subgroup. It could aid in risk stratification of ACS patients as an independent predictor.

Comparison of RANKL expression, inflammatory markers, and cardiovascular risk in patients with acute coronary syndrome with and without rheumatoid arthritis

The mechanisms responsible for increased cardiovascular risk in patients with rheumatoid arthritis (RA) involve local and systemic inflammatory processes. We aimed to compare inflammatory markers and mortality risk in patients with acute coronary syndrome (ACS) with and without RA. The study involved 95 ACS patients (46 with RA and 49 without RA) and 40 healthy controls. Serum levels of Receptor Activator of Nuclear Factor Kappa B Ligand (sRANKL), Osteoprotegerin (sOPG), high-sensitivity C-reactive protein (hs-CRP) and high-sensitivity Tropinin I (hs-TnI) were tested in all participants. Additionally, ACS patients were assessed on RANKL expression (exRANKL) on coronary arteries and mortality risk on the Global Registry of Acute Coronary Events scale (GRACE). exRANKL was established in 35 (76%) ACS patients with RA, vs. 19 (39%) patients without RA, p < 0.001. RA patients had significantly higher levels of sRANKL and sOPG at 24 h and 48 h compared to ACS patients without RA and healthy controls (sRANKL 24 h: 121.33 vs. 51.67 vs. 36.94, p = 0.019; sRANKL 48 h: 89.21 vs. 36.95 vs. 36.94, p = 0.004; sOPG 24 h: 207.71 vs. 69.39 vs. 111.91, p < 0.001; sOPG 48 h: 143.36 vs. 69.38 vs. 111.91, p < 0.001). RA patients had significantly higher RANKL:OPG ratio at 48 h (0.062 vs. 0.53 vs. 0.33, p < 0.001), hs-CRP (28.82 vs. 23.67 vs. 2.60, p < 0.001) and hs-TnI (0.90 vs. 0.76 vs. 0.012). GRACE risk score was significantly higher in RA patients vs. those without RA (140.45 vs. 125.50, p = 0.030) and correlated with exRANKL, RANKL:OPG, hs-CRP, and hs-TnI. Our results indicate that exRANKL, inflammatory markers and mortality risk are amplified in ACS patients with RA compared to ACS patients without RA.

Non-Linear Relationship between Anti-Apolipoprotein A-1 IgGs and Cardiovascular Outcomes in Patients with Acute Coronary Syndromes

Autoantibodies against apolipoprotein A-I (anti-apoA-I IgGs) are prevalent in atherosclerosis-related conditions. It remains elusive whether they improve the prognostic accuracy of the Global Registry of Acute Coronary Events (GRACE) score 2.0 (GS) in acute coronary syndromes (ACS). In this prospective multicenter registry, 1713 ACS patients were included and followed for 1 year. The primary endpoint (major adverse cardiovascular events (MACE)) was defined as the composite of myocardial infarction, stroke (including transient ischemic attack), or cardiovascular (CV) death with individual events independently adjudicated. Plasma levels of anti-apoA-I IgGs upon study inclusion were assessed using ELISA. The association between anti-apoA-I IgGs and incident MACE was assessed using Cox models with splines and C-statistics. One-year MACE incidence was 8.4% (144/1713). Anti-apoA-I IgG levels were associated with MACE with a non-linear relationship (p = 0.01), which remained unchanged after adjusting for the GS (p = 0.04). The hazard increased progressively across the two first anti-apoA-I IgG quartiles before decreasing thereafter. Anti-apoA-I IgGs marginally improved the prognostic accuracy of the GS (c-statistics increased from 0.68 to 0.70). In this multicenter study, anti-apoA-I IgGs were predictive of incident MACE in ACS independently of the GS but in a nonlinear manner. The practical implications of these findings remain to be defined.

Predicting long-term ischemic events using routine clinical parameters in patients with coronary artery disease: The OPT-CAD risk score

BACKGROUND

The prognosis of patients with coronary artery disease (CAD) at hospital discharge was constantly varying, and postdischarge risk of ischemic events remain a concern. However, risk prediction tools to identify risk of ischemia for these patients has not yet been reported.

AIMS

We sought to develop a scoring system for predicting long-term ischemic events in CAD patients receiving antiplatelet therapy that would be beneficial in appropriate personalized decision-making for these patients.

METHODS

In this prospective Optimal antiPlatelet Therapy for Chinese patients with Coronary Artery Disease (OPT-CAD, NCT01735305) registry, a total of 14 032 patients with CAD receiving at least one kind of antiplatelet agent were enrolled from 107 centers across China, from January 2012 to March 2014. The risk scoring system was developed in a derivation cohort (enrolled initially 10 000 patients in the database) using a logistic regression model and was subsequently tested in a validation cohort (the last 4032 patients). Points in risk score were assigned based on the multivariable odds ratio of each factor. Ischemic events were defined as the composite of cardiac death, myocardial infarction or stroke.

RESULTS

Ischemic events occurred in 342 (3.4%) patients in the derivation cohort and 160 (4.0%) patients in the validation cohort during 1-year follow-up. The OPT-CAD score, ranging from 0-257 points, consist of 10 independent risk factors, including age (0-71 points), heart rates (0-36 points), hypertension (0-20 points), prior myocardial infarction (16 points), prior stroke (16 points), renal insufficient (21 points), anemia (19 points), low ejection fraction (22 points), positive cardiac troponin (23 points) and ST-segment deviation (13 points). In predicting 1-year ischemic events, the area under receiver operating characteristics curve were 0.73 and 0.72 in derivation and validation cohort, respectively. The incidences of ischemic events in low- (0-90 points), medium- (91-150 points) and high-risk (≥151 points) patients were 1.6%, 5.5%, and 15.0%, respectively. Compared to GRACE score, OPT-CAD score had a better discrimination in predicting ischemic events and all-cause mortality (ischemic events: 0.72 vs 0.65, all-cause mortality: 0.79 vs 0.72, both P < .001).

CONCLUSIONS

Among CAD patients, a risk score based on 10 baseline clinical variables performed better than the GRACE risk score in predicting long-term ischemic events. However, further research is needed to assess the value of the OPT-CAD score in guiding the management of antiplatelet therapy for patients with CAD.

Prognostic Stratification of Patients With ST-Segment-Elevation Myocardial Infarction (PROSPECT): A Cardiac Magnetic Resonance Study

BACKGROUND

Cardiac magnetic resonance (CMR) is a robust tool to evaluate left ventricular ejection fraction (LVEF), myocardial salvage index, microvascular obstruction, and myocardial hemorrhage in patients with ST-segment-elevation myocardial infarction. We evaluated the additional prognostic benefit of a CMR score over standard prognostic stratification with global registry of acute coronary events (GRACE) score and transthoracic echocardiography LVEF measurement.

METHODS AND RESULTS

Two hundred nine consecutive patients with ST-segment-elevation myocardial infarction (age, 61.4±11.4 years; 162 men) underwent transthoracic echocardiography and CMR after succesful primary percutaneous coronary intervention. Major adverse cardiac events (MACE) were assessed at a mean follow-up of 2.5±1.2 years. MACE occurred in 24 (12%) patients who at baseline showed higher GRACE risk score (P<0.01), lower LVEF with both transthoracic echocardiography and CMR, lower myocardial salvage index, and higher per-patient myocardial hemorrhage and microvascular obstruction prevalence and amount as compared with patients without MACE (P<0.01). The best cut-off values of transthoracic echocardiography-LVEF, CMR-LVEF, myocardial salvage index, and microvascular obstruction to predict MACE were 46.7%, 37.5%, 0.4, and 2.6% of left ventricular mass, respectively. Accordingly, a weighted CMR score, including the following 4 variables (CMR-LVEF, myocardial salvage index, microvascular obstruction, and myocardial hemorrhage), with a maximum of 17 points was calculated and included in the multivariable analysis showing that only CMR score (hazard ratio, 1.867 per SD increase [1.311-2.658]; P<0.001) was independently associated with MACE with the highest net reclassification improvement as compared to GRACE score and transthoracic echocardiography-LVEF measurement.

CONCLUSIONS

CMR score provides incremental prognostic stratification as compared with GRACE score and transthoracic echocardiography-LVEF and may impact the management of patients with ST-segment-elevation myocardial infarction.

Importance of Endogenous Fibrinolysis in Platelet Thrombus Formation

The processes of thrombosis and coagulation are finely regulated by endogenous fibrinolysis maintaining healthy equilibrium. When the balance is altered in favour of platelet activation and/or coagulation, or if endogenous fibrinolysis becomes less efficient, pathological thrombosis can occur. Arterial thrombosis remains a major cause of morbidity and mortality in the world despite advances in medical therapies. The role endogenous fibrinolysis in the pathogenesis of arterial thrombosis has gained increasing attention in recent years as it presents novel ways to prevent and treat existing diseases. In this review article, we discuss the role of endogenous fibrinolysis in platelet thrombus formation, methods of measurement of fibrinolytic activity, its role in predicting cardiovascular diseases and clinical outcomes and future directions.