Contemporary Clinical and Coronary Anatomic Risk Model for 30-Day Mortality After Percutaneous Coronary Intervention

Critical appraisal and assessment of bias among studies evaluating risk prediction models for in-hospital and 30-day mortality after percutaneous coronary intervention: a systematic review

OBJECTIVE

We systematically assessed prediction models for the risk of in-hospital and 30-day mortality in post-percutaneous coronary intervention (PCI) patients.

DESIGN

Systematic review and narrative synthesis.

DATA SOURCES

Searched PubMed, Web of Science, Embase, Cochrane Library, CINAHL, CNKI, Wanfang Database, VIP Database and SinoMed for literature up to 31 August 2023.

ELIGIBILITY CRITERIA

The included literature consists of studies in Chinese or English involving PCI patients aged ≥18 years. These studies aim to develop risk prediction models and include designs such as cohort studies, case-control studies, cross-sectional studies or randomised controlled trials. Each prediction model must contain at least two predictors. Exclusion criteria encompass models that include outcomes other than death post-PCI, literature lacking essential details on study design, model construction and statistical analysis, models based on virtual datasets, and publications such as conference abstracts, grey literature, informal publications, duplicate publications, dissertations, reviews or case reports. We also exclude studies focusing on the localisation applicability of the model or comparative effectiveness.

DATA EXTRACTION AND SYNTHESIS

Two independent teams of researchers developed standardised data extraction forms based on CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies to extract and cross-verify data. They used Prediction model Risk Of Bias Assessment Tool (PROBAST) to assess the risk of bias and applicability of the model development or validation studies included in this review.

RESULTS

This review included 28 studies with 38 prediction models, showing area under the curve values ranging from 0.81 to 0.987. One study had an unclear risk of bias, while 27 studies had a high risk of bias, primarily in the area of statistical analysis. The models constructed in 25 studies lacked clinical applicability, with 21 of these studies including intraoperative or postoperative predictors.

CONCLUSION

The development of in-hospital and 30-day mortality prediction models for post-PCI patients is in its early stages. Emphasising clinical applicability and predictive stability is vital. Future research should follow PROBAST's low risk-of-bias guidelines, prioritising external validation for existing models to ensure reliable and widely applicable clinical predictions.

PROSPERO REGISTRATION NUMBER

CRD42023477272.

Contemporary Risk Models for In-Hospital and 30-Day Mortality After Percutaneous Coronary Intervention

PURPOSE OF REVIEW

Risk models for mortality after percutaneous coronary intervention (PCI) are underutilized in clinical practice though they may be useful during informed consent, risk mitigation planning, and risk adjustment of hospital and operator outcomes. This review analyzed contemporary risk models for in-hospital and 30-day mortality after PCI.

RECENT FINDINGS

We reviewed eight contemporary risk models. Age, sex, hemodynamic status, acute coronary syndrome type, heart failure, and kidney disease were consistently found to be independent risk factors for mortality. These models provided good discrimination (C-statistic 0.85-0.95) for both pre-catheterization and comprehensive risk models that included anatomic variables. There are several excellent models for PCI mortality risk prediction. Choice of the model will depend on the use case and population, though the CathPCI model should be the default for in-hospital mortality risk prediction in the United States. Future interventions should focus on the integration of risk prediction into clinical care.

Using the Super Learner algorithm to predict risk of major adverse cardiovascular events after percutaneous coronary intervention in patients with myocardial infarction

BACKGROUND

The primary treatment for patients with myocardial infarction (MI) is percutaneous coronary intervention (PCI). Despite this, the incidence of major adverse cardiovascular events (MACEs) remains a significant concern. Our study seeks to optimize PCI predictive modeling by employing an ensemble learning approach to identify the most effective combination of predictive variables.

METHODS AND RESULTS

We conducted a retrospective, non-interventional analysis of MI patient data from 2018 to 2021, focusing on those who underwent PCI. Our principal metric was the occurrence of 1-year postoperative MACEs. Variable selection was performed using lasso regression, and predictive models were developed using the Super Learner (SL) algorithm. Model performance was appraised by the area under the receiver operating characteristic curve (AUC) and the average precision (AP) score. Our cohort included 3,880 PCI patients, with 475 (12.2%) experiencing MACEs within one year. The SL model exhibited superior discriminative performance, achieving a validated AUC of 0.982 and an AP of 0.971, which markedly surpassed the traditional logistic regression models (AUC: 0.826, AP: 0.626) in the test cohort. Thirteen variables were significantly associated with the occurrence of 1-year MACEs.

CONCLUSION

Implementing the Super Learner algorithm has substantially enhanced the predictive accuracy for the risk of MACEs in MI patients. This advancement presents a promising tool for clinicians to craft individualized, data-driven interventions to better patient outcomes.

Merging machine learning and patient preference: a novel tool for risk prediction of percutaneous coronary interventions

BACKGROUND AND AIMS

Predicting personalized risk for adverse events following percutaneous coronary intervention (PCI) remains critical in weighing treatment options, employing risk mitigation strategies, and enhancing shared decision-making. This study aimed to employ machine learning models using pre-procedural variables to accurately predict common post-PCI complications.

METHODS

A group of 66 adults underwent a semiquantitative survey assessing a preferred list of outcomes and model display. The machine learning cohort included 107 793 patients undergoing PCI procedures performed at 48 hospitals in Michigan between 1 April 2018 and 31 December 2021 in the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) registry separated into training and validation cohorts. External validation was conducted in the Cardiac Care Outcomes Assessment Program database of 56 583 procedures in 33 hospitals in Washington.

RESULTS

Overall rate of in-hospital mortality was 1.85% (n = 1999), acute kidney injury 2.51% (n = 2519), new-onset dialysis 0.44% (n = 462), stroke 0.41% (n = 447), major bleeding 0.89% (n = 942), and transfusion 2.41% (n = 2592). The model demonstrated robust discrimination and calibration for mortality {area under the receiver-operating characteristic curve [AUC]: 0.930 [95% confidence interval (CI) 0.920-0.940]}, acute kidney injury [AUC: 0.893 (95% CI 0.883-0.903)], dialysis [AUC: 0.951 (95% CI 0.939-0.964)], stroke [AUC: 0.751 (95%CI 0.714-0.787)], transfusion [AUC: 0.917 (95% CI 0.907-0.925)], and major bleeding [AUC: 0.887 (95% CI 0.870-0.905)]. Similar discrimination was noted in the external validation population. Survey subjects preferred a comprehensive list of individually reported post-procedure outcomes.

CONCLUSIONS

Using common pre-procedural risk factors, the BMC2 machine learning models accurately predict post-PCI outcomes. Utilizing patient feedback, the BMC2 models employ a patient-centred tool to clearly display risks to patients and providers (https://shiny.bmc2.org/pci-prediction/). Enhanced risk prediction prior to PCI could help inform treatment selection and shared decision-making discussions.

Efficient sensitivity analysis for biomechanical models with correlated inputs

In most variance-based sensitivity analysis (SA) approaches applied to biomechanical models, statistical independence of the model input is assumed. However, often the model inputs are correlated. This might alter the interpretation of the SA results, which may severely impact the guidance provided during model development and personalization. Potential reasons for the infrequent usage of SA techniques that account for input correlation are the associated high computational costs, especially for models with many parameters, and the fact that the input correlation structure is often unknown. The aim of this study was to propose an efficient correlated global sensitivity analysis method by applying a surrogate model-based approach. Furthermore, this article demonstrates how correlated SA should be interpreted and how the applied method can guide the modeler during model development and personalization, even when the correlation structure is not entirely known beforehand. The proposed methodology was applied to a typical example of a pulse wave propagation model and resulted in accurate SA results that could be obtained at a theoretically 27,000× lower computational cost compared to the correlated SA approach without employing a surrogate model. Furthermore, our results demonstrate that input correlations can significantly affect SA results, which emphasizes the need to thoroughly investigate the effect of input correlations during model development. We conclude that our proposed surrogate-based SA approach allows modelers to efficiently perform correlated SA to complex biomechanical models and allows modelers to focus on input prioritization, input fixing and model reduction, or assessing the dependency structure between parameters.

New York Risk Model and Simplified Risk Score for In-Hospital/30-Day Mortality for Percutaneous Coronary Intervention

Risk models and risk scores derived from those models require periodic updating to account for changes in procedural performance, patient mix, and new risk factors added to existing systems. No risk model or risk score exists for predicting in-hospital/30-day mortality for percutaneous coronary interventions (PCIs) using contemporary data. This study develops an updated risk model and simplified risk score for in-hospital/30-day mortality following PCI. To accomplish this, New York's Percutaneous Coronary Intervention Reporting System was used to develop a logistic regression model and a simplified risk score model for predicting in-hospital/30-day mortality and to validate both models based on New York data from the previous year. A total of 54,770 PCI patients from 2019 were used to develop the models. Twelve different risk factors and 27 risk factor categories were used in the models. Both models displayed excellent discrimination for the development and validation samples (range from 0.894 to 0.896) and acceptable calibration, but the full logistic model had superior calibration, particularly among higher-risk patients. In conclusion, both the PCI risk model and its simplified risk score model provide excellent discrimination and although the full risk model requires the use of a hand-held device for estimating individual patient risk, it provides somewhat better calibration, especially among higher-risk patients.

Association of Residual Ischemic Disease With Clinical Outcomes After Percutaneous Coronary Intervention

BACKGROUND

Anatomical scoring systems have been used to assess completeness of revascularization but are challenging to apply to large real-world datasets.

OBJECTIVES

The aim of this study was to assess the prevalence of complete revascularization and its association with longitudinal clinical outcomes in the U.S. Department of Veterans Affairs (VA) health care system using an automatically computed anatomic complexity score.

METHODS

Patients undergoing percutaneous coronary intervention (PCI) between October 1, 2007, and September 30, 2020, were identified, and the burden of prerevascularization and postrevascularization ischemic disease was quantified using the VA SYNTAX (Synergy Between PCI With Taxus and Cardiac Surgery) score. The association between residual VA SYNTAX score and long-term major adverse cardiovascular events (MACE; death, myocardial infarction, repeat revascularization, and stroke) was assessed.

RESULTS

A total of 57,476 veterans underwent PCI during the study period. After adjustment, the highest tertile of residual VA SYNTAX score was associated with increased hazard of MACE (HR: 2.06; 95% CI: 1.98-2.15) and death (HR: 1.50; 95% CI: 1.41-1.59) at 3 years compared to complete revascularization (residual VA SYNTAX score = 0). Hazard of 1- and 3-year MACE increased as a function of residual disease, regardless of baseline disease severity or initial presentation with acute or chronic coronary syndrome.

CONCLUSIONS

Residual ischemic disease was strongly associated with long-term clinical outcomes in a contemporary national cohort of PCI patients. Automatically computed anatomic complexity scores can be used to assess the longitudinal risk for residual ischemic disease after PCI and may be implemented to improve interventional quality.

Influence of Major Adverse Events on Procedural Selection for Percutaneous Coronary Intervention: Insights From the Veterans Affairs Clinical Assessment Reporting and Tracking Program

Background

Public reporting of percutaneous coronary intervention (PCI) outcomes has been associated with risk-averse attitudes, and pressure to avoid negative outcomes may hinder the care of high-risk patients referred for PCI in public reporting environments. It is unknown whether the occurrence of PCI-related major adverse events (MAEs) influences future case selection in nonpublic reporting environments. Here, we describe trends in PCI case selection among patients undergoing coronary angiography following MAEs in Veterans Affairs (VA) cardiac catheterization laboratories participating in a mandatory internal quality improvement program without public reporting of outcomes.

Methods

Patients who underwent coronary angiography between October 1, 2010, and September 30, 2018, were identified and stratified by VA 30-day PCI mortality risk. The association between MAEs and changes in the proportion of patients proceeding from coronary angiography to PCI within 14 days was assessed.

Results

A total of 251,526 patients and 913 MAEs were included in the analysis. For each prespecified time period of 1, 2, and 4 weeks following an MAE, there were no significant changes in the proportion of patients undergoing coronary angiography who proceeded to PCI within 14 days for the overall cohort and for each tercile of VA 30-day PCI mortality risk.

Conclusions

There were no deviations from routine PCI referral practices following MAEs in this analysis of VA cardiac catheterization laboratories. Nonpublic reporting environments and quality improvement programs may be influential in mitigating PCI risk-aversion behaviors.

Prediction of microvascular obstruction by coronary artery angiography score after acute ST-segment elevation myocardial infarction: a single-center retrospective observational study

Background

Some coronary artery angiography (CAG) scores are associated with the no-reflow phenomenon after percutaneous coronary intervention (PCI) in patients with acute ST-segment elevation myocardial infarction (STEMI). However, quality evidence regarding the association between the CAG scores and microvascular injury is still needed. Our study aimed to validate the ability of the CAG scores in predicting microvascular obstruction (MVO) detected by cardiac magnetic resonance (CMR) imaging.

Methods

From October 2020 to October 2021, 141 consecutive patients with acute STEMI who underwent primary PCI and CMR were retrospectively reviewed. CMR imaging was performed between 3 and 7 days after PCI. The patients were divided into MVO and non-MVO group based on the CMR results. Three CAG scores (SYNTAX score, SYNTAX II score and Gensini score) were used to assess the severity of coronary artery atherosclerotic burden.

Results

A total of 122 patients were included (mean age 60.6 ± 12.8 years). MVO occurred in 51 patients (41.8%). Patients with MVO had higher SYNTAX scores, SYNTAX II scores and Gensini scores than those without MVO (all p < 0.001). The Gensini score (r = 0.567, p < 0.001) showed the strongest correlation with infarction size than SYNTAX score (r = 0.521, p < 0.001) and SYNTAX II score (r = 0.509, p < 0.001). The areas under the receiver operator characteristic curves of SYNTAX score, SYNTAX II score and Gensini score for predicting MVO patients were 0.726, 0.774 and 0.807. In multivariable regression analysis, peak troponin I (odd ratio [OR] = 1.236, p = 0.001) and SYNTAX II score (OR = 11.636, p = 0.010) were identified as independent predictors of MVO.

Conclusions

In patients with acute STEMI undergoing primary PCI treatment, the peak troponin I and SYNTAX II score may be an independent predictor of MVO.