Lots of interesting abstracts and cases were submitted for TCTAP 2023. Below are the accepted ones after a thorough review by our official reviewers. Don’t miss the opportunity to expand your knowledge and interact with authors as well as virtual participants by sharing your opinion in the comment section!
TCTAP A-009
Prognostic Value of Machine-Learning-Based PRAISE Score for Ischemic and Bleeding Events in Patients With Acute Coronary Syndrome Undergoing PCI
By Haoyu Wang, Kefei Dou
Presenter
Haoyu Wang
Authors
Haoyu Wang1, Kefei Dou2
Affiliation
Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, China1, Fuwai Hospital, China2
View Study Report
TCTAP A-009
Acute Coronary Syndromes (STEMI, NSTE-ACS)
Prognostic Value of Machine-Learning-Based PRAISE Score for Ischemic and Bleeding Events in Patients With Acute Coronary Syndrome Undergoing PCI
Haoyu Wang1, Kefei Dou2
Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, China1, Fuwai Hospital, China2
Background
The Prediction of Adverse Events Following an Acute Coronary Syndrome (PRAISE) score is a machine-learning-based model for predicting 1-year all-cause death, myocardial infarction (MI), and Bleeding Academic Research Consortium (BARC) type 3/5 bleeding. Its utility in an unselected Asian population undergoing percutaneous coronary intervention (PCI)for acute coronary syndrome (ACS) remains unknown. We aimed to validate the PRAISE score in a real-world Asian population.
Methods
A total of 5,944 consecutive patients undergoing PCI for ACS were prospectively included. The PRAISE scores were compared with established scoring systems (GRACE 2.0, PRECISE-DAPT, and PARIS) to evaluate their discrimination, calibration, and reclassification. Three outcomes of interest were evaluated: all cause death, recurrent acute myocardial infarction, and major bleeding 1 year after discharge.
Results
By multivariable Cox analysis, the risk of all-cause mortality (HR: 7.16, 95% CI: 4.43–11.60), recurrent acute MI (HR: 7.20, 95% CI:4.36–11.90), and BARC types 3/5 bleeding (HR 7.04, 95% CI: 4.47–8.39) were greater in the high-risk group than in the low-risk group. The C-statistics for death, MI and major bleeding were 0.71 (0.65-0.77), 0.68 (0.61-0.74), and 0.66(0.61-0.72), respectively. The observed to expected (O: E) ratio of death, MI, and major bleeding were 0.767, 0.555, and 0.757, respectively. Based on decision curve analysis, the PRAISE score displayed a slightly greater net benefit between 1% and 22% for 1-year risk of death as well as 2% and 18% for the 1-year risk of MI, compared with the GRACE and PARIS scores, respectively.
Conclusion
In an all-comer real-world cohort with ACS patients treated with PCI, the machine learning-based PRAISE score performed well with high levels of discrimination and calibration in terms of 1-year all-cause death, MI, and major bleeding. The efficacy of the PRAISE score in enhancing the risk stratification of patients with ACS needed be tested in randomized controlled trials.