Performance of the AusSCORE II and STS Score for Coronary Artery Bypass Grafting in a New Zealand Population

Singh, Navneet; Gimpel, Damian; Manikavasagar, V.; Watson, Nicholas; Roberts, Jacque; Conaglen, Paul; Meikle, Felicity; Lin, Zaw; Kejriwal, Nand; Odom, Nicholas; McCormack, David; El‐Gamel, Adam

doi:10.1016/j.hlc.2020.08.021

Cited by 5 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Однако, по мнению ряда авторов, данные шкалы обладают низкой дискриминационной способностью, что снижает эффективность их применения [13]. Также, по мнению исследователей, ПМ, локально реализованные с помощью методов МО, имеют большую эффективность в сравнении с EuroScore II и STS, что делает их более предпочтительными в использовании [6,7,14].…”

Section: Discussionunclassified

Potential of machine learning methods in operational risk stratification in patients with coronary artery disease scheduled for coronary bypass surgery

et al. 2023

View full text Add to dashboard Cite

Aim. To develop and evaluate the effectiveness of models for predicting mortality after coronary bypass surgery, obtained using machine learning analysis of preoperative data.Material and methods. As part of a cohort study, a retrospective prediction of in-hospital mortality after coronary artery bypass grafting (CABG) was performed in 2182 patients with stable coronary artery disease. Patients were divided into 2 following samples: learning (80%, n=1745) and training (20%, n=437). The initial ratio of surviving (n=2153) and deceased (n=29) patients in the total sample indicated a pronounced class imbalance, and therefore the resampling method was used in the training sample. Five machine learning (ML) algorithms were used to build predictive risk models: Logistic regression, Random Forrest, CatBoost, LightGBM, XGBoost. For each of these algorithms, cross-validation and hyperparameter search were performed on the training sample. As a result, five predictive models with the best parameters were obtained. The resulting predictive models were applied to the learning sample, after which their performance was compared in order to determine the most effective model.Results. Predictive models implemented on ensemble classifiers (CatBoost, LightGBM, XGBoost) showed better results compared to models based on logistic regression and random forest. The best quality metrics were obtained for CatBoost and LightGBM based models (Precision — 0,667, Recall — 0,333, F1-score — 0,444, ROC AUC — 0,666 for both models). There were following common high-ranking parameters for deciding on the outcome for both models: creatinine and blood glucose levels, left ventricular ejection fraction, age, critical stenosis (>70%) of carotid arteries and main lower limb arteries.Conclusion. Ensemble machine learning methods demonstrate higher predictive power compared to traditional methods such as logistic regression. The prognostic models obtained in the study for preoperative prediction of in-hospital mortality in patients referred for CABG can serve as a basis for developing systems to support medical decision-making in patients with coronary artery disease.

show abstract

Section: Discussionunclassified

Potential of machine learning methods in operational risk stratification in patients with coronary artery disease scheduled for coronary bypass surgery

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In another investigation by Singh et al [27] in 933 patients from New Zealand who received simple CABG, a validation analysis of STS scores indicated excellent discriminatory ability and calibration of the STS score (AUC = 0.921, HL: P = 0.294). These findings suggest that the STS score has good predictive value for postoperative 30-day mortality in patients in this region.…”

Section: Application Of the Sts Score In Western Countriesmentioning

confidence: 94%

Risk-Predictive Models for Adverse Events in Cardiac Surgery: A Review

Luo

2024

CVIA

View full text Add to dashboard Cite

Risk prediction models are an important part of assessing operative mortality and postoperative complication rates in current cardiac surgery practice. Furthermore, they guide clinical decision-making and perioperative patient management. In recent years, a variety of clinical prediction models have been developed in China and other countries to assess the risk of mortality and complications after cardiac surgery. Currently, the most widely used and mature models are the new version of the European Cardiac Surgery Evaluation System (EuroSCORE II), the American Society of Thoracic Surgeons Cardiac Surgery Risk Model (STS score), and the Chinese Coronary Artery Bypass Graft Surgery Risk Evaluation System (SinoSCORE). This article reviews the application of these three risk prediction models, to identify the optimal model for guiding clinical practice.

show abstract

“…Assessing the risk of perioperative bleeding is important; therefore, many risk score questionnaires, such as the Society of Thoracic Surgeons score and Euro SCORE II score, have been widely used to predict the mortality of patients undergoing cardiac surgery. [36][37][38] Additionally, there are some questionnaires for evaluating the degree of GI bleeding, such as the Rockall score and Glasgow Blatchford score. Additionally, it is necessary to assess the coagulation function.…”

Section: Bleeding Assessment Toolsmentioning

confidence: 99%

Gastrointestinal bleeding during the transcatheter aortic valve replacement perioperative period: A Review

Lü

Zhang

2022

Medicine

View full text Add to dashboard Cite

With the aging of the population, the incidence of senile degenerative valvular heart disease is expected to increase. Transcatheter aortic valve replacement (TAVR) has been used for patients at lower surgical risk with symptomatic severe aortic valve stenosis. Because of the improvements in TAVR technology and increasing experience of the operators, TAVR is regarded as a safe and feasible procedure. Bleeding events during the TAVR perioperative period, especially gastrointestinal (GI) bleeding, have been proven to be related to the long-term prognosis and mortality. Elderly patients with valvular heart disease are susceptible to GI bleeding because of their use of antithrombotic drugs, physical damage of coagulation factors, and GI angiodysplasia. Frequent GI bleeding and low levels of preoperative hemoglobin increase the risk of TAVR, especially for elderly patients. Because of these risks, which are easily overlooked, we should focus more attention on the perioperative management of TAVR. Reasonable screening tools, including blood examinations, risk evaluation scales, and endoscopy, are beneficial to the prevention of complications that can occur during the perioperative period. Additionally, medical therapy can safely help patients at high-risk for bleeding patients throughout the perioperative period. This study aimed to characterize the pathology of TAVR patients and discuss treatment strategies for GI bleeding during the perioperative period.

show abstract

Performance of the AusSCORE II and STS Score for Coronary Artery Bypass Grafting in a New Zealand Population

Cited by 5 publications

References 9 publications

Potential of machine learning methods in operational risk stratification in patients with coronary artery disease scheduled for coronary bypass surgery

Potential of machine learning methods in operational risk stratification in patients with coronary artery disease scheduled for coronary bypass surgery

Risk-Predictive Models for Adverse Events in Cardiac Surgery: A Review

Gastrointestinal bleeding during the transcatheter aortic valve replacement perioperative period: A Review

Contact Info

Product

Resources

About