A novel machine learning model to predict high on-treatment platelet reactivity on clopidogrel in Asian patients
Lan-Ping Ding1, Ping Li2, Li-Rong Yang3
1Department of Pharmacy, Jiangsu Province Hospital, The First Affiliated Hospital with Nanjing Medical University, Nanjing, 210009, China.
Insights
Machine learning, specifically XGBoost, effectively predicts high on-treatment platelet reactivity (HTPR) in Chinese patients undergoing percutaneous coronary intervention (PCI) after clopidogrel treatment. This model aids clinical decisions for improved patient outcomes.
Area of Science:
- Cardiology
- Medical Informatics
- Pharmacogenomics
Background:
- High on-treatment platelet reactivity (HTPR) is influenced by various genetic and non-genetic factors in patients receiving clopidogrel.
- Predicting HTPR is crucial for optimizing antiplatelet therapy after percutaneous coronary intervention (PCI).
Purpose of the Study:
- To develop and validate a novel machine learning (ML) model for predicting HTPR in Chinese patients post-PCI.
- To identify key predictors of HTPR using ML techniques.
Main Methods:
- A cohort study involving 461 patients treated with clopidogrel after PCI.
- Development and comparison of nine ML models and logistic regression (LR) on a training set (90%) and testing set (10%).
- Performance evaluation using AUC, precision, recall, F1 score, and accuracy; model interpretation via variable importance scores.
Main Results:
- The XGBoost model demonstrated superior performance with an AUC of 0.82, accuracy of 0.87, and precision of 0.80.
- XGBoost identified seven key variables predictive of HTPR.
- A user-friendly XGBoost prediction platform was established for clinical application.
Conclusions:
- Machine learning, particularly XGBoost, offers optimal performance for predicting HTPR in clopidogrel-treated patients post-PCI.
- The developed ML model can assist clinicians in decision-making to personalize antiplatelet therapy.
- Further validation studies are recommended to strengthen the clinical utility of the predictive model.
Background:
Various genetic and nongenetic variables influence the high on-treatment platelet reactivity (HTPR) in patients taking clopidogrel.
Aim:
This study aimed to develop a novel machine learning (ML) model to predict HTPR in Chinese patients after percutaneous coronary intervention (PCI).
Method:
This cohort study collected information on 507 patients taking clopidogrel. Data were randomly divided into a training set (90%) and a testing set (10%). Nine candidate Machine learning (ML) models and multiple logistic regression (LR) analysis were developed on the training set. Their performance was assessed according to the area under the receiver operating characteristic curve, precision, recall, F1 score, and accuracy on the test set. Model interpretations were generated using importance scores by transforming model variables into scaled features and representing in radar plots. Finally, we established a prediction platform for the prediction of HTPR.
Results:
A total of 461 patients (HTPR rate: 19.52%) were enrolled in building the prediction model for HTPR. The XGBoost model had an optimized performance, with an AUC of 0.82, a precision of 0.80, a recall of 0.44, an F1 score of 0.57, and an accuracy of 0.87, which was superior to those of LR. Furthermore, the XGBoost method identified 7 main predictive variables. To facilitate the application of the model, we established an XGBoost prediction platform consisting of 7 variables and all variables for the HTPR prediction.
Conclusion:
A ML-based approach, such as XGBoost, showed optimum performance and might help predict HTPR on clopidogrel after PCI and guide clinical decision-making. Further validated studies will strengthen this finding.
