Related Experiment Video
Updated: Aug 7, 2025
Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
Machine learning for prediction of bleeding in acute myocardial infarction patients after percutaneous coronary
Xueyan Zhao1, Junmei Wang2, Jingang Yang1
1National Clinical Research Center for Cardiovascular Diseases, State Key Laboratory of Cardiovascular Disease, Fu Wai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
Insights
Machine learning accurately predicts bleeding in acute myocardial infarction patients after percutaneous coronary intervention. The developed model outperforms existing scores, offering a valuable tool for clinical risk assessment.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Predicting bleeding is crucial for acute myocardial infarction (AMI) patients undergoing percutaneous coronary intervention (PCI).
- Machine learning (ML) offers advanced capabilities for feature selection and relationship learning in predicting clinical outcomes.
Purpose of the Study:
- To assess the predictive performance of ML methods for in-hospital bleeding in AMI patients post-PCI.
- To develop and validate a novel ML-based risk prediction model for this patient cohort.
Main Methods:
- Utilized data from the China Acute Myocardial Infarction (CAMI) registry, randomly partitioning into derivation and validation sets.
- Applied eXtreme Gradient Boosting (XGBoost) to select features from 98 variables and predict Bleeding Academic Research Consortium (BARC) 3 or 5 bleeding.
- Developed an online calculator based on the 12 most important variables.
Main Results:
- The XGBoost model demonstrated strong predictive performance with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.941 (derivation) and 0.837 (validation).
- The model significantly outperformed the CRUSADE (AUROC: 0.741) and ACUITY-HORIZONS (AUROC: 0.731) scores.
- The online calculator achieved an AUROC of 0.809 on the validation set.
Conclusions:
- The CAMI bleeding model, developed using ML, is the first of its kind for predicting bleeding in AMI patients after PCI.
- The model shows superior predictive accuracy compared to existing risk scores, offering a significant advancement in clinical decision-making.
- The online calculator provides a practical tool for real-time risk assessment.
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.
More Related Videos
Related Concept Videos
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:30Acute Coronary Syndrome I: Introduction
01:28Acute Coronary Syndrome IV: Interprofessional Care