An XGBoost machine learning model incorporating the GRACE score accurately predicted 30-day major adverse cardiac events after TAVI, outperforming conventional logistic regression (AUC 0.98 vs 0.84).
Observational (n=453)
Yes
Does a machine learning model incorporating the GRACE score improve the prediction of 30-day MACE in patients undergoing TAVI compared to conventional regression or ML without GRACE score?
Machine learning techniques, specifically XGBoost incorporating the GRACE score, significantly improve the prediction of 30-day MACE following TAVI compared to conventional regression models.
Effect estimate: AUC 0.98 (95% CI 0.91-0.99)
Absolute Event Rate: 0.98% vs 0.84%
p-value: p=<0.001
Learning Approach with GRACE Score D egenerative aortic stenosis (AS) is the most prevalent valvular heart disease and carries an unfavourable prognosis if left untreated. 1Transcatheter aortic valve implantation (TAVI) is a minimally invasive procedure employed for substituting a damaged aortic valve in patients over the age of 75 or in those who are high risk, or ineligi-ble for surgical aortic valve replacement (sAVR). 2Although TAVI has substantially enhanced the outcomes for patients at high risk, there remains a possibility of experiencing major adverse cardiac events (MACE), including myocardial infarction, stroke, and mortality, after the procedure. 3,4However, the risk factors and preoperative surgical risk scores Objectives: Predictive risk scores have a significant impact on patient selection and assessing the likelihood of complications following interventions in patients with severe aortic stenosis (AS).This study aims to explore the utility of machine learning (ML) techniques in predicting 30-day major adverse cardiac events (MACE) by analyzing parameters, including the Global Registry of Acute Coronary Events (GRACE) score.Methods: This retrospective, multi-center, observational study enrolled 453 consecutive patients diagnosed with severe AS who underwent transcatheter aortic valve implantation (TAVI) from April 2020 to January 2023.The primary outcome was defined as a composition of MACE comprising periprocedural myocardial infarction (MI), cerebrovascular events (CVE), and all-cause mortality during the 1-month follow-up period after the procedure.Conventional binomial logistic regression and ML models were utilized and compared for prediction purposes. Results:The study population had a mean age of 76.1, with 40.8% being male.The primary endpoint was observed in 7.5% of cases.Among the individual components of the primary endpoint, the rates of all-cause mortality, MI, and CVE were reported as 4.2%, 2.4%, and 1.9%, respectively.The ML-based Extreme Gradient Boosting (XGBoost) model with the GRACE score demonstrated superior discriminative performance in predicting the primary endpoint, compared to both the ML model without the GRACE score and the conventional regression model Area Under the Curve (AUC)= 0.98 (0.91-0.99),AUC= 0,87 (0.80-0.98),AUC= 0.84 (0.79-0.96).Conclusion: ML techniques hold the potential to enhance outcomes in clinical practice, especially when utilized alongside established clinical tools such as the GRACE score.
Aslan Erdoğan (Mon,) conducted a observational in Severe aortic stenosis (n=453). XGBoost machine learning model with GRACE score vs. Conventional logistic regression model was evaluated on 30-day major adverse cardiac events (MACE) (AUC 0.98, 95% CI 0.91-0.99, p=<0.001). An XGBoost machine learning model incorporating the GRACE score accurately predicted 30-day major adverse cardiac events after TAVI, outperforming conventional logistic regression (AUC 0.98 vs 0.84).