Assessment of the EuroSCORE risk scoring system for patients undergoing coronary artery bypass graft surgery in a group of Iranian patients

Is preoperative IABP insertion significantly reducing postoperative complication in augmented high-risk coronary artery bypass grafting patients?

BACKGROUND

The aim of this study was to determine whether pre-operative intra-aortic balloon pump (IABP) insertion improves surgical outcomes in high-risk coronary artery bypass grafting (CABG) patients.

METHODS

Patients with a EuroSCORE II greater than 1.2% who underwent CABG from 2009 to 2016 were included in the study, while those who utilized intra-operative or post-operative IABP were excluded. The analysis included a total of 2907 patients, with 377 patients undergoing preoperative IABP insertion (EuroSCORE II > 5.018%) and 1198 patients in the non-IABP group before matching; after propensity score matching (PSM), both groups consisted of a matched cohort of 250 patients.

RESULTS

30-day mortality events occurred in 9 (3.6%) non-IABP group and in 12 (4.8%) IABP patients (OR: 1.33 95%CI: 0.52-3.58). Kaplan-Meier survival curve analysis showed no significant differences between the two groups in mortality up to one year after the operation (p = 0.72). On multivariate analysis, IABP usage among the PSM patients was associated with lower 30-day mortality (OR: 0.28, 95%CI: 0.07-0.92, P-value = 0.043), 90-day mortality (OR: 0.26, 95%CI: 0.08-0.78, P-value = 0.022) and reduced risk of developing severe respiratory disorders (OR: 0.10, 95%CI:0.01-0.50, P-value = 0.011).

CONCLUSION

Pre-operative IABP use in high-risk patients reduces 30- and 90-day mortality rates, along with a notable decrease in rates of severe respiratory disorders.

Comparative analysis of machine learning vs. traditional modeling approaches for predicting in-hospital mortality after cardiac surgery: temporal and spatial external validation based on a nationwide cardiac surgery registry

AIMS

Preoperative risk assessment is crucial for cardiac surgery. Although previous studies suggested machine learning (ML) may improve in-hospital mortality predictions after cardiac surgery compared to traditional modeling approaches, the validity is doubted due to lacking external validation, limited sample sizes, and inadequate modeling considerations. We aimed to assess predictive performance between ML and traditional modelling approaches, while addressing these major limitations.

METHODS AND RESULTS

Adult cardiac surgery cases (n = 168 565) between 2013 and 2018 in the Chinese Cardiac Surgery Registry were used to develop, validate, and compare various ML vs. logistic regression (LR) models. The dataset was split for temporal (2013-2017 for training, 2018 for testing) and spatial (geographically-stratified random selection of 83 centers for training, 22 for testing) experiments, respectively. Model performances were evaluated in testing sets for discrimination and calibration. The overall in-hospital mortality was 1.9%. In the temporal testing set (n = 32 184), the best-performing ML model demonstrated a similar area under the receiver operating characteristic curve (AUC) of 0.797 (95% CI 0.779-0.815) to the LR model (AUC 0.791 [95% CI 0.775-0.808]; P = 0.12). In the spatial experiment (n = 28 323), the best ML model showed a statistically better but modest performance improvement (AUC 0.732 [95% CI 0.710-0.754]) than LR (AUC 0.713 [95% CI 0.691-0.737]; P = 0.002). Varying feature selection methods had relatively smaller effects on ML models. Most ML and LR models were significantly miscalibrated.

CONCLUSION

ML provided only marginal improvements over traditional modelling approaches in predicting cardiac surgery mortality with routine preoperative variables, which calls for more judicious use of ML in practice.

Institutional case-volume-incorporated mortality risk prediction model after cardiac surgery

BACKGROUND

Most risk prediction models predicting short-term mortality after cardiac surgery incorporate patient characteristics, laboratory data, and type of surgery, but do not account for surgical experience. Considering the impact of case volume on patient outcome after high-risk procedures, we attempted to develop a risk prediction model for mortality after cardiac surgery that incorporates institutional case volume.

METHODS

Adult patients who underwent cardiac surgery from 2009 to 2016 were identified. Patients who underwent cardiac surgery (n = 57,804) were randomly divided into the derivation cohort (n = 28,902) or the validation cohorts (n = 28,902). A risk prediction model for in-hospital mortality and 1-year mortality was developed from the derivation cohort and the performance of the model was evaluated in the validation cohort.

RESULTS

The model demonstrated fair discrimination (c-statistics, 0.76 for in-hospital mortality in both cohorts; 0.74 for 1-year mortality in both cohorts) and acceptable calibration. Hospitals were classified based on case volume into 50 or less, 50-100, 100-200, or more than 200 average cardiac surgery cases per year and case volume was a significant variable in the prediction model.

CONCLUSIONS

A new risk prediction model that incorporates institutional case volume and accurately predicts in-hospital and 1-year mortality after cardiac surgery was developed and validated.

Machine learning improves mortality risk prediction after cardiac surgery: Systematic review and meta-analysis

BACKGROUND

Interest in the usefulness of machine learning (ML) methods for outcomes prediction has continued to increase in recent years. However, the advantage of advanced ML model over traditional logistic regression (LR) remains controversial. We performed a systematic review and meta-analysis of studies comparing the discrimination accuracy between ML models versus LR in predicting operative mortality following cardiac surgery.

METHODS

The present systematic review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis statement. Discrimination ability was assessed using the C-statistic. Pooled C-statistics and its 95% credibility interval for ML models and LR were obtained were obtained using a Bayesian framework. Pooled estimates for ML models and LR were compared to inform on difference between the 2 approaches.

RESULTS

We identified 459 published citations of which 15 studies met inclusion criteria and were used for the quantitative and qualitative analysis. When the best ML model from individual study was used, meta-analytic estimates showed that ML were associated with a significantly higher C-statistic (ML, 0.88; 95% credibility interval, 0.83-0.93 vs LR, 0.81; 95% credibility interval, 0.77-0.85; P = .03). When individual ML algorithms were instead selected, we found a nonsignificant trend toward better prediction with each of ML algorithms. We found no evidence of publication bias (P = .70).

CONCLUSIONS

The present findings suggest that when compared with LR, ML models provide better discrimination in mortality prediction after cardiac surgery. However, the magnitude and clinical influence of such an improvement remains uncertain.

Comparison of Patient's Kidney Function Based on Kidney Disease Improving Global Outcomes (KDIGO) Criteria and Clinical Parameters in Isolated Coronary Artery Bypass Graft (CABG) Surgery in On-Pump and Off-pump Methods in Patients with Low Cardiac Output Syndrome (LCOS) After Surgery

Background

Acute kidney injury (AKI) is one of the serious complications of cardiac surgery. It is worsened when accompanied by low cardiac output syndrome.

Objectives

In this study, we compared kidney function based on the KDIGO criteria in isolated on-pump and off-pump coronary artery bypass graft (CABG) surgery.

Methods

In this cohort study, 52 patients with LCOS were enrolled after on-pump (28 patients) and off-pump (24 patients) CABG. In the first six hours after ICU entrance, blood samples were taken for serum creatinine based on routine. For determining AKI after surgery, we used the KDIGO criteria as a primary endpoint. Also, some clinical parameters were recorded before, during, and after surgery. The data were analyzed by SPSS software, version 24, using paired and independent t-test, ANOVA, and Pearson correlation test and non-parametric tests such as Mann-Whitney and Kruskal-Wallis tests at a significance level of P < 0.05.

Results

There was no significant difference in age (P = 0.3) and gender (P = 0.57) between the two groups. Among cardiac disease risk factors, only hypertension (P = 0.02) had a significant difference between the two groups, but AKI in patients with hypertension did not show a significant difference (P = 0.09). In paraclinical parameters, serum creatinine showed a significant difference before and after surgery in on-pump (P < 0.001) and off-pump (P = 0.007) groups. Also, this parameter had a significant difference at 6 h, 12 h, 24 h, and 48 h after surgery between the on-pump and on-pump groups. The AKI incidence showed a significant difference between the two groups (P < 0.001).

Conclusions

The incidence of AKI was more in on-pump patients than in off-pump patients. Also, a significant difference was observed between their clinical parameters. Thus, to improve the patients’ clinical outcomes and lower the health costs, we suggest that patients with a high risk of LCOS be followed up after CABG, especially on-pump CABG.

External Validation of European System for Cardiac Operative Risk Evaluation II (EuroSCORE II) for Risk Prioritization in an Iranian Population

INTRODUCTION

The European System for Cardiac Operative Risk Evaluation II (EuroSCORE II) is a prediction model which maps 18 predictors to a 30-day post-operative risk of death concentrating on accurate stratification of candidate patients for cardiac surgery.

OBJECTIVE

The objective of this study was to determine the performance of the EuroSCORE II risk-analysis predictions among patients who underwent heart surgeries in one area of Iran.

METHODS

A retrospective cohort study was conducted to collect the required variables for all consecutive patients who underwent heart surgeries at Emam Reza hospital, Northeast Iran between 2014 and 2015. Univariate and multivariate analysis were performed to identify covariates which significantly contribute to higher EuroSCORE II in our population. External validation was performed by comparing the real and expected mortality using area under the receiver operating characteristic curve (AUC) for discrimination assessment. Also, Brier Score and Hosmer-Lemeshow goodness-of-fit test were used to show the overall performance and calibration level, respectively.

RESULTS

Two thousand five hundred eight one (59.6% males) were included. The observed mortality rate was 3.3%, but EuroSCORE II had a prediction of 4.7%. Although the overall performance was acceptable (Brier score=0.047), the model showed poor discriminatory power by AUC=0.667 (sensitivity=61.90, and specificity=66.24) and calibration (Hosmer-Lemeshow test, P<0.01).

CONCLUSION

Our study showed that the EuroSCORE II discrimination power is less than optimal for outcome prediction and less accurate for resource allocation programs. It highlights the need for recalibration of this risk stratification tool aiming to improve post cardiac surgery outcome predictions in Iran.