Key result
XGBoost model outperforms CRUSADE and ACUITY for predicting in-hospital bleeding with ~0.84 AUROC.
Why the study?
Prediction of bleeding is critical for AMI patients after PCI, and the predictive value of machine learning methods for in-hospital bleeding required evaluation.
Does an XGBoost machine learning model improve the prediction of in-hospital major bleeding (BARC 3 or 5) compared to the CRUSADE and ACUITY-HORIZONS scores in patients with acute myocardial infarction undergoing PCI?
Cohort (n=16,736)
Yes
Does an XGBoost machine learning model improve the prediction of in-hospital major bleeding (BARC 3 or 5) compared to the CRUSADE and ACUITY-HORIZONS scores in patients with acute myocardial infarction undergoing PCI?
An XGBoost machine learning model trained on the CAMI registry significantly improved in-hospital major bleeding risk prediction after PCI for AMI compared to traditional CRUSADE and ACUITY-HORIZONS scores, maintaining good discrimination (AUROC 0.809) even when simplified to 12 variables.
Answers are grounded in this paper and cite their sources.
May aid bleeding risk stratification in AMI-PCI; leaves open prospective validation before clinical adoption.
Background: Prediction of bleeding is critical for acute myocardial infarction (AMI) patients after percutaneous coronary intervention (PCI). Machine learning methods can automatically select the combination of the important features and learn their underlying relationship with the outcome. Objectives: We aimed to evaluate the predictive value of machine learning methods to predict in-hospital bleeding for AMI patients. Design: We used data from the multicenter China Acute Myocardial Infarction (CAMI) registry. The cohort was randomly partitioned into derivation set (50%) and validation set (50%). We applied a state-of-art machine learning algorithm, eXtreme Gradient Boosting (XGBoost), to automatically select features from 98 candidate variables and developed a risk prediction model to predict in-hospital bleeding (Bleeding Academic Research Consortium [BARC] 3 or 5 definition). Results: A total of 16,736 AMI patients who underwent PCI were finally enrolled. 45 features were automatically selected and were used to construct the prediction model. The developed XGBoost model showed ideal prediction results. The area under the receiver-operating characteristic curve (AUROC) on the derivation data set was 0.941 (95% CI = 0.909–0.973, p < 0.001); the AUROC on the validation set was 0.837 (95% CI = 0.772–0.903, p < 0.001), which was better than the CRUSADE score (AUROC: 0.741; 95% CI = 0.654–0.828, p < 0.001) and ACUITY-HORIZONS score (AUROC: 0.731; 95% CI = 0.641–0.820, p < 0.001). We also developed an online calculator with 12 most important variables ( http://101.89.95.81:8260/ ), and AUROC still reached 0.809 on the validation set. Conclusion: For the first time, we developed the CAMI bleeding model using machine learning methods for AMI patients after PCI. Trial registration: NCT01874691. Registered 11 Jun 2013.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2023) conducted a cohort in Acute myocardial infarction undergoing percutaneous coronary intervention (n=16,736). eXtreme Gradient Boosting (XGBoost) machine learning risk prediction model (CAMI bleeding score) vs. CRUSADE score and ACUITY-HORIZONS score was evaluated on In-hospital major bleeding (BARC type 3 or 5 non-CABG-related bleeding) discrimination on validation set (AUROC 0.837, 95% CI 0.772-0.903, p=<0.001). The XGBoost machine learning model achieved an AUROC of 0.837 on the validation set, outperforming CRUSADE and ACUITY-HORIZONS for in-hospital bleeding.
Synapse has enriched 10 related papers. Consider them for comparative context: