Systematic review and meta-analysis of mortality risk prediction models in adult cardiac surgery

Sinha, Shubhra; Dimagli, Arnaldo; Dixon, Lauren; Gaudino, Mario; Caputo, Massimo; Vohra, Hunaid A.; Angelini, Gianni; Benedetto, Umberto

doi:10.1093/icvts/ivab151

Cited by 11 publications

(5 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Today, EuroSCORE II and the Society of Thoracic Surgery Predicted Risk of Mortality (STS-PROM) are the most widely recognized and utilized risk stratification tools [ 4 , 5 ]. EuroSCORE II and STS-PROM have comparable discriminative accuracy and calibration regarding in-hospital and 30-day mortality in coronary artery bypass grafting (CABG) and in aortic valve replacement (AVR) patients [ 5 – 8 ].…”

Section: Introductionmentioning

confidence: 99%

The performance of EuroSCORE II in CABG patients in relation to sex, age, and surgical risk: a nationwide study in 14,118 patients

Silverborn

Nielsen

Karlsson

2023

J Cardiothorac Surg

View full text Add to dashboard Cite

Background To determine the discriminative accuracy and calibration of EuroSCORE II in relation to age, sex, and surgical risk in a large nationwide coronary artery bypass grafting (CABG) cohort. Methods All 14,118 patients undergoing isolated CABG in Sweden during 2012–2017 were included. Individual patient data were taken from the SWEDEHEART registry. Patients were divided by age (< 60, 60–69, 70–79, ≥ 80 years), sex, and surgical risk (low: EuroSCORE < 4%, intermediate: 4–8%, high: > 8%). Discriminative accuracy was determined by the area under the receiver operating characteristic curve (AUC) and calibration by the observed/estimated (O/E) mortality ratio at 30 days. Results AUC and O/E ratio were 0.82 (95% CI 0.79–0.85) and 0.58 (0.50–0.66) overall, 0.82 (0.79–0.86) and 0.57 (0.48–0.66) in men, and 0.79 (0.73–0.85) and 0.60 (0.47–0.75) in women. Regarding age, discriminative accuracy was highest in patients aged 60–69 years (AUC: 0.86 [0.80–0.93]) but was satisfactory in all groups (AUC: 0.74–0.80). O/E ratio varied from 0.26 for patients > 60 years to 0.90 for patients > 80 years. Regarding surgical risk, AUC and O/E ratio were 0.63 (0.44–0.83) and 0.18 (0.09–0.30) in low-risk patients, 0.60 (0.55–0.66) and 0.57 (0.46–0.68) in intermediate-risk patients, and 0.78 (0.73–0.83) and 0.78 (0.64–0.92) in high-risk patients. Conclusions EuroSCORE II had good discriminative accuracy independently of sex and age, but markedly overestimated mortality risk, especially in younger patients. Accuracy and calibration were better in high-risk patients than in low-risk and intermediate-risk patients.

show abstract

Section: Introductionmentioning

confidence: 99%

The performance of EuroSCORE II in CABG patients in relation to sex, age, and surgical risk: a nationwide study in 14,118 patients

Silverborn

Nielsen

Karlsson

2023

J Cardiothorac Surg

View full text Add to dashboard Cite

show abstract

“…Cardiac surgery, a formidable surgical procedure, entails significant potential for complications [1]. Various predictive scales, such as The Society of Thoracic Surgeons (STS) score and Euro score II, have been developed to forecast complications following cardiac surgery [2]. Nevertheless, these scores fall short in capturing the actual occurrence and impact of complications in patients.…”

Section: Introductionmentioning

confidence: 99%

Application of Clavien-Dindo Complications Classification in Cardiac Surgery Practice: A Narrative Review

Thuan

2024

IJCTS

View full text Add to dashboard Cite

Background: Cardiac surgery is a complex medical specialty known for its potential complications, necessitating accurate evaluation and reporting. Current prediction scales have limitations in capturing the full spectrum of complications experienced by patients undergoing cardiac surgery. The Clavien-Dindo Complications Classification (CDCC) and the Comprehensive Complications Index (CCI) have emerged as promising tools for assessing complications in various surgical specialties, including cardiac surgery. Method: This comprehensive review synthesizes the available literature to assess the application of CDCC and CCI in the context of cardiac surgery. The effectiveness of CDCC and CCI in measuring the nature and clinical impact of complications in this specialized field is explored. Additionally, methods from other medical specialties are reviewed to enhance our understanding of the practical implementation of these classification systems in cardiac surgery. Results: The present study, including significant contributions by Mélanie Hébert et al., highlights the potential of CDCC and CCI to quantify both the number and severity of complications in adult cardiac surgery. Their utility in this specialized field presents opportunities for robust data collection and outcome evaluation. Conclusion: While the application of CDCC and CCI in cardiac surgery shows promise, the notable scarcity of comprehensive evaluation studies has hindered the accessibility of these systems to clinicians. This study provides a clear and accessible reference for healthcare professionals seeking to integrate CDCC and CCI into their cardiac surgery practice. Additionally, we propose the need for guideline studies to address this gap in the field.

show abstract

“…The data relevant to its calculation are now routinely gathered, analysed and released for the above purposes. EuroSCORE II improved upon the results of logistic EuroSCORE [ 2 ] but still has a tendency to over-estimate risk, especially in those in the highest risk strata [ 3–8 ] and in those operated on outside Europe [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

Comparison of machine learning techniques in prediction of mortality following cardiac surgery: analysis of over 220 000 patients from a large national database

Sinha

Dong

Dimagli

et al. 2023

European Journal of Cardio-Thoracic Surgery

Self Cite

View full text Add to dashboard Cite

Objectives To perform a systematic comparison of in-hospital mortality risk prediction post-cardiac surgery, between the predominant scoring system-European System for Cardiac Operative Risk Evaluation(EuroSCOREII), logistic regression(LR) retrained on the same variables and alternative machine learning techniques(ML)-random forest(RF), neural networks(NN),XGBoost and weighted support vector machine(SVM). Methods Retrospective analyses of prospectively routinely collected data on adult patients undergoing cardiac surgery in the UK from January 2012-March 2019. Data was temporally split 70:30 into training and validation subsets. Mortality prediction models were created using the 18 variables of EuroSCOREII. Comparisons of discrimination, calibration and clinical utility were then conducted. Changes in model performance, variable-importance over time and hospital/operation-based model performance were also reviewed. Results Of the 227,087 adults who underwent cardiac surgery during the study period there were 6,258 deaths(2.76%). In the testing cohort, there was an improvement in discrimination XGBoost(95% confidence interval(CI) Area Under the Curve(AUC): 0.834-0.834,F1 score:0.276-0.280) and RF(95%CI AUC:0.833-0.834,F1:0.277-0.281) compared with EuroSCOREII(95%CI AUC:0.817-0.818,F1: 0.243-0.245).There was no significant improvement in calibration with ML and retrained-LR compared to EuroSCOREII. However, EuroSCOREII overestimated risk across all deciles of risk and over time. The calibration drift was lowest in NN, XGBoost and RF compared with EuroSCOREII. Decision curve analysis showed XGBoost and RF to have greater net benefit than EuroSCOREII. Conclusions ML techniques showed some statistical improvements over retrained-LR and EuroSCOREII. The clinical impact of this improvement is modest at present. However the incorporation of additional risk factors in future studies may improve upon these findings and warrants further study.

show abstract

Systematic review and meta-analysis of mortality risk prediction models in adult cardiac surgery

Cited by 11 publications

References 77 publications

The performance of EuroSCORE II in CABG patients in relation to sex, age, and surgical risk: a nationwide study in 14,118 patients

The performance of EuroSCORE II in CABG patients in relation to sex, age, and surgical risk: a nationwide study in 14,118 patients

Application of Clavien-Dindo Complications Classification in Cardiac Surgery Practice: A Narrative Review

Comparison of machine learning techniques in prediction of mortality following cardiac surgery: analysis of over 220 000 patients from a large national database

Contact Info

Product

Resources

About