Age and diabetes mellitus associated with worse outcomes after percutaneous coronary intervention in a multi-ethnic Asian dialysis patient population

Machine Learning for Early Prediction of Major Adverse Cardiovascular Events After First Percutaneous Coronary Intervention in Patients With Acute Myocardial Infarction: Retrospective Cohort Study

BACKGROUND

The incidence of major adverse cardiovascular events (MACEs) remains high in patients with acute myocardial infarction (AMI) who undergo percutaneous coronary intervention (PCI), and early prediction models to guide their clinical management are lacking.

OBJECTIVE

This study aimed to develop machine learning-based early prediction models for MACEs in patients with newly diagnosed AMI who underwent PCI.

METHODS

A total of 1531 patients with AMI who underwent PCI from January 2018 to December 2019 were enrolled in this consecutive cohort. The data comprised demographic characteristics, clinical investigations, laboratory tests, and disease-related events. Four machine learning models-artificial neural network (ANN), k-nearest neighbors, support vector machine, and random forest-were developed and compared with the logistic regression model. Our primary outcome was the model performance that predicted the MACEs, which was determined by accuracy, area under the receiver operating characteristic curve, and F1-score.

RESULTS

In total, 1362 patients were successfully followed up. With a median follow-up of 25.9 months, the incidence of MACEs was 18.5% (252/1362). The area under the receiver operating characteristic curve of the ANN, random forest, k-nearest neighbors, support vector machine, and logistic regression models were 80.49%, 72.67%, 79.80%, 77.20%, and 71.77%, respectively. The top 5 predictors in the ANN model were left ventricular ejection fraction, the number of implanted stents, age, diabetes, and the number of vessels with coronary artery disease.

CONCLUSIONS

The ANN model showed good MACE prediction after PCI for patients with AMI. The use of machine learning-based prediction models may improve patient management and outcomes in clinical practice.

A nomogramic model for predicting the left ventricular ejection fraction of STEMI patients after thrombolysis-transfer PCI

Background

The prognosis of ST-segment elevation myocardial infarction (STEMI) is closely linked to left ventricular ejection fraction (LVEF). In contrast to primary percutaneous coronary intervention (PPCI), thrombolysis-transfer PCI (TTPCI) is influenced by multiple factors that lead to heterogeneity in cardiac function and prognosis. The aim of this study is to develop a nomogram model for predicting early LVEF in STEMI patients with TTPCI, based on routine indicators at admission.

Method

We retrospectively reviewed data from patients diagnosed with STEMI at five network hospitals of our PCI center who performed TTPCI as door-to-balloon time (the interval between arrival at the hospital and intracoronary balloon inflation) over 120 min, from February 2018 to April 2022. Categorical variables were analyzed using Pearson χ2 tests or Fisher exact tests, while Student's t-test or Mann-Whitney U-test was used to compare continuous variables. Subsequently, independent risk factors associated with reduced LVEF one week after TTPCI were identified through comprehensive analysis by combining All-Subsets Regression with Logistic Regression. Based on these indicators, a nomogram model was developed, and validated using the area under the receiver operating characteristic (ROC) curve and the Bootstrap method.

Results

A total of 288 patients were analyzed, including 60 with LVEF < 50% and 228 with LVEF ≥ 50%. The nomogram model based on six independent risk factors including age, heart rate (HR), hypertension, smoking history, Alanine aminotransferase (ALT), and Killip class, demonstrated excellent discrimination with an AUC of 0.84 (95% CI: 0.78-0.89), predicted C-index of 0.84 and curve fit of 0.713.

Conclusions

The nomogram model incorporating age, HR, hypertension, smoking history, ALT and Killip class could accurately predict the early LVEF ≥ 50% probability of STEMI patients undergoing TTPCI, and enable clinicians' early evaluation of cardiac function in STEMI patients with TTPCI and early optimization of treatment.

Comparison of revascularization with conservative medical treatment in maintenance dialysis patient with coronary artery disease: a systemic review and meta-analysis

Background

The primary cause of death among maintenance dialysis patients is coronary artery disease (CAD). However, the best treatment plan has not yet been identified.

Methods

The relevant articles were retrieved from various online databases and references from their inception to October 12, 2022. The studies that compared revascularization [percutaneous coronary intervention (PCI) or coronary artery bypass grafting (CABG)] with medical treatment (MT) among maintenance dialysis patients with CAD were selected. The outcomes evaluated were long-term (with a follow-up of at least 1 year) all-cause mortality, long-term cardiac mortality, and the incidence rate of bleeding events. Bleeding events are defined according to TIMI hemorrhage criteria: (1) major hemorrhage, intracranial hemorrhage or clinically visible hemorrhage (including imaging diagnosis) with decrease of hemoglobin concentration ≥5 g/dl; (2) minor hemorrhage, clinically visible bleeding (including imaging diagnosis) with a drop in hemoglobin of 3-5 g/dl; (3) minimal hemorrhage, clinically visible bleeding with hemoglobin drop <3 g/dl. In addition, revascularization strategy, CAD type, and the number of diseased vessels were considered in subgroup analyses.

Results

A total of eight studies with 1,685 patients were selected for this meta-analysis. The current findings suggested that revascularization was associated with low long-term all-cause mortality and long-term cardiac mortality but a similar incidence rate of bleeding events compared to MT. However, subgroup analyses indicated that PCI is linked to decreased long-term all-cause mortality compared to MT but CABG did not significantly differ from MT in terms of long-term all-cause mortality. Revascularization also showed lower long-term all-cause mortality compared to MT among patients with stable CAD, single-vessel disease, and multivessel disease but did not reduce long-term all-cause mortality among patients with ACS.

Conclusion

Long-term all-cause mortality and long-term cardiac mortality were reduced by revascularization in comparison to MT alone in patients undergoing dialysis. Larger randomized studies are needed to confirm the conclusion of this meta-analysis.

Serum VCAM-1 and ICAM-1 measurement assists for MACE risk estimation in ST-segment elevation myocardial infarction patients

Background

Vascular cell adhesion molecule‐1 (VCAM‐1) and intercellular adhesion molecule‐1 (ICAM‐1) modulate atherosclerosis by promoting leukocyte infiltration, neutrophil recruitment, endothelial cell proliferation, etc., which may directly or indirectly facilitate the occurrence of major adverse cardiac events (MACE). This study intended to investigate the value of VCAM‐1 and ICAM‐1 for predicting MACE in ST‐segment elevation myocardial infarction (STEMI) patients.

Methods

Totally, 373 STEMI patients receiving the percutaneous coronary intervention and 50 health controls (HCs) were included. Serum VCAM‐1 and ICAM‐1 were detected by ELISA. Meanwhile, MACE was recorded during a median follow‐up of 18 (range: 1–46) months in STEMI patients.

Results

Vascular cell adhesion molecule‐1 and ICAM‐1 were raised in STEMI patients compared with HCs (both p < 0.001). VCAM‐1 (p = 0.002) and ICAM‐1 (p = 0.012) high were linked with raised accumulating MACE rate in STEMI patients. Notably, VCAM‐1 high (hazard ratio [HR] = 2.339, p = 0.031), age ≥ 65 years (HR = 2.019, p = 0.039), history of diabetes mellitus (DM) (HR = 2.395, p = 0.011), C‐reactive protein (CRP) ≥ 5 mg/L (HR = 2.550, p = 0.012), multivessel disease (HR = 2.561, p = 0.007) independently predicted MACE risk in STEMI patients. Furthermore, a nomogram‐based prediction model combining these factors was established, exhibiting an acceptable value for estimating 1, 2, and 3‐year MACE risk, with AUC of 0.764, 0.716, and 0.778, respectively, in STEMI patients.

Conclusion

This study confirms the value of VCAM‐1 and ICAM‐1 measurement in predicting MACE risk in STEMI patients. Moreover, VCAM‐1 plus other traditional prognostic factors (such as age, history of DM, CRP, and multivessel disease) cloud further improve the predictive accuracy of MACE risk in STEMI patients.