Machine Learning on High-Dimensional Data to Predict Bleeding Post Percutaneous Coronary Intervention
Corbin Rayfield, Pradyumna Agasthi, Farouk Mookadam
1Senior Consultant Cardiovascular Diseases, Mayo Clinic, 13400 East Shea Boulevard, Scottsdale, AZ 85259 USA. Arsanjani.Reza@mayo.edu.
Insights
A new machine learning model (AI-BR) accurately predicts bleeding after percutaneous coronary intervention (PCI), outperforming the existing American College of Cardiology bleeding risk (ACC-BR) model in patient risk assessment.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Bleeding complications are a significant risk following percutaneous coronary intervention (PCI).
- Accurate prediction of bleeding risk is crucial for patient management and outcomes.
- Existing risk models may have limitations in predicting bleeding post-PCI.
Purpose of the Study:
- To evaluate the accuracy of a machine learning model in predicting bleeding outcomes after PCI.
- To compare the performance of the machine learning model against the American College of Cardiology CathPCI bleeding risk (ACC-BR) model.
Main Methods:
- Retrospective analysis of 15,603 patients from the Mayo Clinic CathPCI registry (2003-2018).
- Development of a boosted classification tree algorithm (AI-BR) using 105 variables to predict major and minor bleeding within 72 hours post-PCI.
- Comparison of AI-BR model performance (ROC-AUC) against the ACC-BR model in a test cohort of 3900 patients.
Main Results:
- The overall rate of major bleeding complications was 1.8%.
- The AI-BR model demonstrated superior performance with an ROC-AUC of 0.873 compared to the ACC-BR model's 0.764 (P=.02).
- The AI-BR model achieved a sensitivity of 77.3% and specificity of 80.9%.
Conclusions:
- The AI-BR machine learning model accurately predicts bleeding events post-PCI.
- The AI-BR model significantly outperforms the ACC-BR model in predicting bleeding risk in patients undergoing PCI.
- This AI-driven approach offers improved risk stratification for patients undergoing PCI.
Introduction:
The purpose of the current study is to determine the accuracy of machine learning in predicting bleeding outcomes post percutaneous coronary intervention (PCI) in comparison with the American College of Cardiology CathPCI bleeding risk (ACC-BR) model.
Methods:
Mayo Clinic CathPCI registry data were retrospectively analyzed from January, 2003 to June, 2018, including 15,603 patients who underwent PCI. The cohort was randomly divided into a training sample of 11,703 patients (75%) and a unique test sample of 3900 patients (25%) prior to model generation. The risk-prediction model was generated utilizing a boosted classification tree algorithm of 105 unique variables to predict the risk of major and minor bleeding complications within 72 hours after PCI or before hospital discharge. The receiver operating characteristic (ROC) curves and areas under the curve (AUC) for the boosted classification tree algorithm (AI-BR) model and ACC-BR model were compared for the test cohort.
Results:
The mean age of the patient cohort was 67 ± 12.7 years, and women constituted 30% of the cohort. The rate of major bleeding complications in the entire cohort was 1.8%. The sensitivity and specificity of the AIBR model were 77.3% and 80.9%, respectively. The ROC-AUC for the AI-BR model (0.873) was superior vs the ACC-BR model (0.764; P=.02) in predicting major bleeding for the test cohort.
Conclusion:
The AI-BR model accurately predicts bleeding post PCI and outperforms the ACC-BR model in predicting the risk of bleeding in patients undergoing PCI.
More Related Videos
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
10:03Coronary Progenitor Cells and Soluble Biomarkers in Cardiovascular Prognosis after Coronary Angioplasty
Published on: January 28, 2020