Total and Cause-Specific Mortality After Percutaneous Coronary Intervention: Observations From the Alberta Provincial Project for Outcome Assessment in Coronary Heart Disease Registry

Machine learning prediction of one-year mortality after percutaneous coronary intervention in acute coronary syndrome patients

BACKGROUND

Machine learning (ML) models have the potential to accurately predict outcomes and offer novel insights into inter-variable correlations. In this study, we aimed to design ML models for the prediction of 1-year mortality after percutaneous coronary intervention (PCI) in patients with acute coronary syndrome.

METHODS

This study was performed on 13,682 patients at Tehran Heart Center from 2015 to 2021. Patients were split into 70:30 for testing and training. Four ML models were designed: a traditional Logistic Regression (LR) model, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Ada Boost models. The importance of features was calculated using the RF feature selector and SHAP based on the XGBoost model. The Area Under the Receiver Operating Characteristic Curve (AUC-ROC) for the prediction on the testing dataset was the main measure of the model's performance.

RESULTS

From a total of 9,073 patients with >1-year follow-up, 340 participants died. Higher age and higher rates of comorbidities were observed in these patients. Body mass index and lipid profile demonstrated a U-shaped correlation with the outcome. Among the models, RF had the best discrimination (AUC 0.866), while the highest sensitivity (80.9%) and specificity (88.3%) were for LR and XGBoost models, respectively. All models had AUCs of >0.8.

CONCLUSION

ML models can predict 1-year mortality after PCI with high performance. A classic LR statistical approach showed comparable results with other ML models. The individual-level assessment of inter-variable correlations provided new insights into the non-linear contribution of risk factors to post-PCI mortality.

Impact of Diabetes in Patients With Acute Myocardial Infarction Undergoing Coronary Artery Bypass Surgery Within 48 Hours

BACKGROUND

Diabetic patients with coronary artery disease may benefit from elective coronary artery bypass graft (CABG) surgery. It is unknown whether this merit is transferable to patients with acute myocardial infarction (AMI) undergoing surgery.

METHOD

A total of 1,427 patients underwent CABG within 48 hours of being diagnosed with AMI at the current institution between 2001 and 2019. Of these patients, 206 (14.4%) had insulin-dependent diabetes mellitus (IDDM) and 148 (10.4%) had non-insulin dependent diabetes mellitus (NIDDM). Retrospective data analysis was performed.

RESULTS

Patients with NIDDM showed the highest perioperative risk profile, with a EuroScore II of 11.6 (±10.3) compared with 7.8 (±8.0) in non-diabetic patients and 8.4 (±7.8) in patients with IDDM (p<0.001). Sub-analysis demonstrated a higher proportion of non-ST-elevation myocardial infarction patients in the NIDDM cohort compared with the IDDM cohort (70.9% vs 56.8%; p=0.005). Postoperatively, NIDDM patients had more sepsis (p<0.01) and longer ventilation times (p<0.001) compared with non-DM and IDDM patients (p<0.01). Wound healing complications were rare, but almost twice as high in NIDDM patients compared with non-DM and IDDM patients (4.7% vs 0.9% vs 2.4%, respectively). The 30-day mortality was highest in the NIDDM cohort (18.3% vs 11.3% vs 7.8%; p=0.012). Analysis of survival for up to 15 years revealed a significantly reduced survival of diabetic patients compared with non-diabetic patients, with lowest survival rates in NIDDM patients (p<0.001).

CONCLUSIONS

Non-insulin dependent diabetes mellitus patients undergoing CABG within 48 hours of being diagnosed with AMI are at increased risk of short-term and long-term complications. Therefore, this particular group should undergo a careful evaluation concerning the expected risks and benefits of CABG in this setting.

Symptomatic HIV infection and in-hospital outcomes for patients with acute myocardial infarction undergoing percutaneous coronary intervention from national inpatient sample

Human immunodeficiency virus (HIV) infection increases the risk of acute myocardial infarction (AMI). However, little is known about its association with in-hospital outcomes and temporal trends in patients with AMI undergoing percutaneous coronary intervention (PCI). We queried patients with AMI who underwent PCI from the National Inpatient Sample Database (2003-2015) and stratified them into three groups: symptomatic, asymptomatic, and HIV-negative. After 1:2 case-control matching (CCM), logistic regression analysis was conducted to determine how HIV infection affected in-hospital outcomes. We also evaluated their recent trends from 2003 to 2015. The total weighted national estimate of 2,191,129 AMI cases included 2,178,995 HIV/AIDS-negative, 4994 asymptomatic, and 7140 symptomatic HIV cases. Symptomatic but not asymptomatic patients with HIV suffered more than triple the in-hospital mortality (adjusted odds ratio (aOR) 3.6, 95% confidence interval (CI) 2.5-5.2), over one-fold incidence of acute kidney injury (aOR 2.6 95% CI 1.9-3.4) and cardiogenic shock risk (aOR 1.9, 95% CI 1.3-2.7), a longer length of hospital stay (beta 1.2, 95% CI 1.0-1.5), and had more procedures (beta 1.3, 95% CI 1.2-1.5). These disparities relating to symptomatic HIV infection persisted from 2003 to 2015. In patients with AMI who underwent PCI, symptomatic HIV infection was associated with higher in-hospital mortality and more severe outcomes.

Development of Comorbidity Index for in-hospital mortality for patients who underwent coronary artery revascularization

BACKGROUND

For myocardial revascularization, coronary artery bypass grafting (CAGB) and percutaneous coronary intervention (PCI) are two common modalities but with high in-hospital mortality. A Comorbidity Index is useful to predict mortality or can be used with other covariates to develop point-scoring systems. This study aimed to develop specific comorbidity indices for patients who underwent coronary artery revascularization.

METHODS

Patients who underwent CABG or PCI were identified in the National Inpatient Sample database between Q4 2015-2020. Patients of age <40 were excluded for congenital heart defects. Patients were randomly sampled into experimental (70%) and validation (30%) groups. Thirty-eight Elixhauser comorbidities were identified and included in multivariable regression to discriminate in-hospital mortality. Weight for each comorbidity was assigned and single indices, Li CABG Mortality Index (LCMI) and Li PCI Mortality Index (LPMI), were developed.

RESULTS

Mortality discrimination by LCMI approached adequacy (c-statistic=0.691, 95% CI=0.682-0.701) and was comparable to multivariable regression with comorbidities (c-statistic=0.685, 95% CI=0.675-0.694). LCMI discrimination performed significantly better than Elixhauser Comorbidity Index (ECI) (c-statistic=0.621, 95% CI=0.611-0.631) and can be further improved by adjusting age (c-statistic=0.721, 95% CI=0.712-0.730). All models were well-calibrated (Brier score=0.021-0.022). LPMI moderately discriminated in-hospital mortality (c-statistic=0.666, 95% CI=0.660-0.672) and performed significantly better than ECI (c-statistic=0.610, 95% CI=0.604-0.616). LPMI performed better than the all-comorbidity multivariable regression (c-statistic=0.658, 95% CI=0.652-0.663). After age adjustment, LPMI discrimination was significantly increased and was approaching adequacy (c-statistic=0.695, 95% CI=0.690-0.701). All models were well-calibrated (Brier score=0.025-0.026).

CONCLUSIONS

LCMI and LPMI effectively discriminated and predicted in-hospital mortality. These indices were validated and performed superior to ECI. These indices can standardize comorbidity measurement as alternatives to ECI to help replicate and compare results across studies.

Development of Comorbidity Index for In-hospital Mortality for Patients Underwent Coronary Artery Revascularization

Background

For myocardial revascularization, coronary artery bypass grafting (CAGB) and percutaneous coronary intervention (PCI) are two common modalities but with high in-hospital mortality. A comorbidity index is useful to predict mortality or can be used with other covariates to develop point-scoring systems. This study aimed to develop specific comorbidity indices for patients who underwent coronary artery revascularization.

Methods

Patients who underwent CABG or PCI were identified in the National Inpatient Sample database between Q4 2015-2020. Patients of age<40 were excluded for congenital heart defects. Patients were randomly sampled into experimental (70%) and validation (30%) groups. Thirty-eight Elixhauser comorbidities were identified and included in multivariable regression to predict in-hospital mortality. Weight for each comorbidity was assigned and single indices, Li CABG Mortality Index (LCMI) and Li PCI Mortality Index (LPMI), were developed.

Results

Mortality prediction by LCMI approached adequacy ( c -statistic=0.691, 95% CI=0.682-0.701) and was comparable to multivariable regression with comorbidities ( c -statistic=0.685, 95% CI=0.675-0.694). LCMI prediction performed significantly better than Elixhauser Comorbidity Index (ECI) ( c -statistic=0.621, 95% CI=0.611-0.631) and can be further improved by adjusting age ( c -statistic=0.721, 95% CI=0.712-0.730). LPMI moderately predicted in-hospital mortality ( c -statistic=0.666, 95% CI=0.660-0.672) and performed significantly better than ECI ( c -statistic=0.610, 95% CI=0.604-0.616). LPMI performed better than the all-comorbidity multivariable regression ( c -statistic=0.658, 95% CI=0.652-0.663). After age adjustment, LPMI prediction was significantly increased and was approaching adequacy ( c -statistic=0.695, 95% CI=0.690-0.701).

Conclusions

LCMI and LPMI effectively predicted in-hospital mortality. These indices were validated and performed superior to ECI. The adjustment of age increased their predictive power to adequacy, implicating potential clinical application.

In-hospital and 1-Year Outcomes of Repeated Percutaneous Coronary Intervention for In-stent Restenosis With Acute Coronary Syndrome Presentation

BACKGROUND

In-stent restenosis (ISR) is the Achilles' heel of percutaneous coronary intervention (PCI). There have been controversial data about outcomes of repeated PCI (redo-PCI) for ISR. This study aims to determine the predictors of major adverse cardiac events (MACE) in patients underwent redo-PCI for ISR.

METHODS

In this retrospective study, all patients with acute coronary syndrome who were underwent successful PCI for ISR at Tehran Herat Center (between 2004 and 2019) were eligible for inclusion. Patients with moderate to severe valvular heart disease and/or hematological disorders were excluded. Participants were divided into 2 groups based on the occurrence of the MACE [composite of cardiovascular death, myocardial infarction (MI), coronary artery bypass grafting, target vessel revascularization, and target lesion revascularization]; then, the study variables were compared between the 2 groups. Finally, the predictors of MACE were identified using Cox regression analysis.

RESULTS

Of 748 redo-PCI patients (mean age: 65.2 ± 10.1; 71.0% males), 631 patients had met the inclusion criteria. Fifty-four patients (9.8%) developed MACE within a 1-year follow-up period. Multivessel disease, primary PCI, Ad-hoc PCI, history of non-ST-segment elevation MI, and diabetes mellitus were independent predictors for MACE. In a subgroup analysis, 30 patients who experienced third PCI (target lesion revascularization/target vessel revascularization) were followed more as 1-year MACE. Among these patients, 14 MACEs were observed during the last follow-up (till June 2020).

CONCLUSIONS

Multivessel disease, primary PCI, and history of non-ST-segment elevation MI were the predictors of higher 1-year MACE, whereas Ad-hoc PCI and diabetes mellitus had a protective effect on MACE.

Ten-year trends of clinical outcomes after percutaneous coronary intervention: a Korean nationwide longitudinal cohort study

OBJECTIVES

Mortality following percutaneous coronary intervention (PCI) is a key quality measurement in clinical practice. This study investigated the 10-year trends of mortality following PCI in an unselected nationwide cohort.

DESIGN

Retrospective cohort study.

SETTING

A nationwide study in South Korea.

PARTICIPANTS

PCI claim data from 2006 to 2015 of the National Health Insurance Service and the Statistics of Korea.

MEASURES

1-year cardiovascular or non-cardiovascular death.

RESULTS

In total, 437 436 patients were included. The annual number of PCI cases increased from 32 098 to 51 990 over the decade studied (p<0.001). Patients were divided into quartile subgroups according to an estimated adjusted probability for predicting 1-year all-cause death. The proportion of patients in the high-risk quartiles increased whereas those in the low-risk quartiles decreased (p<0.001). The 1-year cumulative incidence rate of all-cause death did not change in the population with risk scores in the 1st (0.9% to 0.8%) and 2nd (1.3% to 1.3%) quartiles, whereas it increased in the population with risk scores in the 3rd (3.4% to 5.1%) and 4th (15.5% to 19.4%) quartiles (p<0.001). Compared with year 2006, the mean survival time in year 2015 was shorter by 0, 3.3 and 12.4 days in patients with risk scores in the 1st or 2nd, 3rd and 4th quartiles, respectively. These findings were also consistent for cardiovascular or non-cardiovascular deaths.

CONCLUSION

The number, proportion and the overall risk of patients with a high risk for mortality after PCI increased over the decade in Korea.

Outcomes and regional differences in practice in a worldwide coronary stent registry

OBJECTIVE

The primary objective was to assess the performance of a new generation thin-strut sirolimus-eluting coronary stent with abluminal biodegradable polymer in an all comer population. The secondary objective was to detail differences in contemporary percutaneous coronary intervention (PCI) practice worldwide.

METHODS

e-Ultimaster was an all-comer, prospective, global registry (NCT02188355) with independent event adjudication enrolling patients undergoing PCI with the study stent. The primary outcome measure was target lesion failure (TLF) at 1 year, defined as the composite of cardiac death, target vessel myocardial infarction and clinically driven target lesion revascularisation. Data were stratified according to 4 geographical regions.

RESULTS

A total of 37 198 patients were enrolled (Europe 69.2%, Asia 17.8%, Africa/Middle East 6.6% and South America/Mexico 6.5%) and 1-year follow-up was available for 35 389 patients (95.1%). One-year TLF occurred in 3.2% of the patients, ranging from 2% (Africa/Middle East) to 4.1% (South America/Mexico). In patients with acute coronary syndrome, potent P2Y₁₂ inhibitors were prescribed in 48% of patients at discharge, while at 1 year 72% were on any dual antiplatelet therapy. Lipid-lowering treatment was administered in 80.9% and 75.5% of patients at discharge and 1 year, respectively. Regional differences in the profile of the treated patients as well as in PCI practice were reported.

CONCLUSIONS

In this investigation with worldwide representation, contemporary PCI using a new generation thin-strut sirolimus-eluting coronary stent with abluminal biodegradable polymer was associated with low 1-year TLF across clinical presentations and continents. Suboptimal adherence to current recommendations around antiplatelet and lipid lowering treatments was detected.

The Mid-term Mortality and Mode of Death in Survivors with ST-elevation Myocardial Infarction

Objective The popularity of primary percutaneous coronary intervention (p-PCI) for ST-elevation myocardial infarction (STEMI) has increased over the past decades. Despite improvements in in-hospital mortality rates, it is clinically important to investigate the prognoses after discharge. However, data on the mode of death and prognostic factors are limited. We analyzed these factors in a Japanese cohort in the modern p-PCI era. Methods Between January 2004 and December 2017, a total of 1,222 patients who underwent p-PCI within 24 hours from the onset of STEMI and were alive at discharge (mean age, 67.7 years old; men, 75.5%), were evaluated. The two-year mortality was analyzed using a Cox regression model, and the mode of death was evaluated. Results The rate of mortality at 2 years was 5.7%. Non-cardiac death was more frequent than cardiac death (62.6% vs. 37.4%). A Cox multivariate analysis identified the following as independent predictors of the 2-year mortality: hemoglobin (log-transformed) [adjusted hazard ratio (HR), 0.048; 95% confidence interval (CI), 0.008-0.29; p<0.001], age above 80 years old (adjusted HR, 2.26; 95% CI, 1.30-3.91; p=0.004), Killip class ≥II (adjusted HR, 1.99; 95% CI, 1.17-3.39; p=0.011), brain natriuretic peptide level (log-transformed) (adjusted HR, 1.47; 95% CI, 1.09-2.01; p=0.013), and body mass index (log-transformed) (adjusted HR, 0.16; 95% CI, 0.030-0.84; p=0.030). Conclusion This study demonstrated that the 2-year mortality was 5.7% in STEMI survivors after p-PCI. Non-cardiac death was more frequent than cardiac death. Compared to well-known clinical variables, angiographic findings did not have a significant influence on the mid-term mortality.

Current trends in optimal medical therapy after PCI and its influence on clinical outcomes in China

Background

Limited data were available on the current trends in optimal medical therapy (OMT) after PCI and its influence on clinical outcomes in China. We aimed to evaluate the utilization and impact of OMT on the main adverse cardiovascular and cerebrovascular events (MACCEs) in post-PCI patients and analyzed the factors predictive of OMT after discharge.

Methods

We collected data from 3812 individuals from 2016.10 to 2017.09 at TEDA International Cardiovascular Hospital. They were classified into an OMT group and a non-OMT group according to their OMT status, which was defined as the combination of dual antiplatelet therapy, statins, β-blockers, angiotensin-converting enzyme inhibitors or angiotensin receptor blockers after PCI. Multivariable Cox regression models were developed to assess the association between OMT and MACCEs, defined as all-cause mortality, nonfatal myocardial infarction, stroke, and target vessel revascularization. A logistic regression model was established to analyze the factors predictive of OMT.

Results

Our results revealed that the proportion of patients receiving OMT and its component drugs decreased over time. A total of 36.0% of patients were still adherent to OMT at the end of follow-up. Binary logistic regression analysis revealed that baseline OMT (P < 0.001, OR = 52.868) was the strongest predictor of OMT after PCI. The Cox hazard model suggested that smoking after PCI was associated with the 1-year risk of MACCE (P = 0.001, HR = 2.060, 95% CI 1.346–3.151), while OMT (P = 0.001, HR = 0.486, 95% CI 0.312–0.756) was an independent protective factor against postoperative MACCEs.

Conclusions

There was still a gap between OMT utilization after PCI and the recommendations in the evidence-based guidelines. Sociodemographic and clinical factors influence the application of OMT. The management of OMT and smoking cessation after PCI should be emphasized.

Sympathetic Activation and Arrhythmogenesis after Myocardial Infarction: Where Do We Stand?

Myocardial infarction often leads to progressive structural and electrophysiologic remodeling of the left ventricle. Despite the widespread use of β-adrenergic blockade and implantable defibrillators, morbidity and mortality from chronic-phase ventricular tachyarrhythmias remains high, calling for further investigation on the underlying pathophysiology. Histological and functional studies have demonstrated extensive alterations of sympathetic nerve endings at the peri-infarct area and flow-innervation mismatches that create a highly arrhythmogenic milieu. Such accumulated evidence, along with the previously well-documented autonomic dysfunction as an important contributing factor, has stirred intense research interest for pharmacologic and non-pharmacologic neuromodulation in post-infarction heart failure. In this regard, aldosterone inhibitors, sacubitril/valsartan and sodium-glucose cotransporter type 2 inhibitors have shown antiarrhythmic effects. Non-pharmacologic modalities, currently tested in pre-clinical and clinical trials, include transcutaneous vagal stimulation, stellate ganglion modulation and renal sympathetic denervation. In this review, we provide insights on the pathophysiology of ventricular arrhythmogenesis post-myocardial infarction, focusing on sympathetic activation.

Retrospective cohort analysis of Spanish national trends of coronary artery bypass grafting and percutaneous coronary intervention from 1998 to 2017

INTRODUCTION

Spain is one of the countries with the lowest rates of revascularisation and highest ratio of percutaneous coronary intervention (PCI) to coronary artery bypass grafting (CABG).

OBJECTIVES

To investigate the changes and trends in the two revascularisation procedures between 1998 and 2017 in Spain.

DESIGN

Retrospective cohort study. Analysis of in-hospital outcomes.

SETTING

Minimum basic data set from the Spanish National Department of Health: mandatory database collecting information of patients who are attended in the Spanish public National Health System.

PARTICIPANTS

603 976 patients who underwent isolated CABG or PCI in the Spanish National Health System. The study period was divided in four 5-year intervals. Patients with acute myocardial infarction on admission were excluded.

PRIMARY AND SECONDARY OUTCOMES

We investigated the volume of procedures nationwide, the changes of the risk profile of patients and in-hospital mortality of both techniques.

RESULTS

We observed a 2.2-fold increase in the rate of any type of myocardial revascularisation per million inhabitants-year: 357 (1998) to 776 (2017). 93 682 (15.5%) had a coronary surgery. PCI to CABG ratio rose from 2.2 (1998-2002) to 8.1 (2013-2017). Charlson's index increased by 0.8 for CABG and 1 for PCI. The median annual volume of PCI/hospital augmented from 136 to 232, while the volume of CABG was reduced from 137 to 74. In the two decades, we detected a significant reduction of CABG in-hospital mortality (6.5% vs 2.6%, p<0.001) and a small increase in PCI (1.2% vs 1.5%, p<0.001). Risk adjusted mortality rate was reduced for both CABG (1.51 vs 0.48, p<0.001), and PCI (1.42 vs 1.05, p<0.001).

CONCLUSION

We detected a significant increase in the volume of revascularisations (particularly PCI) in Spain. Risk-adjusted in-hospital mortality was significantly reduced.