Machine learning derived model for the prediction of bleeding in dual antiplatelet therapy patients
Yang Qian1, Lei Wanlin2, Wang Maofeng2
1Department of Pharmacy, Affiliated Dongyang Hospital, Wenzhou Medical University, Dongyang, Zhejiang, China.
Insights
A new predictive model accurately assesses bleeding risk in patients on dual antiplatelet therapy (DAPT). This tool aids in optimizing treatment and improving patient outcomes.
Area of Science:
- Cardiology
- Medical Informatics
- Clinical Prediction Modeling
Background:
- Dual antiplatelet therapy (DAPT) is crucial for preventing thrombotic events but increases bleeding risk.
- Accurate prediction of bleeding risk in DAPT patients is essential for personalized treatment strategies.
Purpose of the Study:
- To develop and validate a predictive model for assessing bleeding risk in patients undergoing DAPT.
- To identify key clinical variables associated with increased bleeding risk in this population.
Main Methods:
- A large cohort of 18,408 DAPT patients was analyzed.
- Various machine learning models, including XGBoost, were employed for prediction model development.
- Model performance was rigorously evaluated using AUC, calibration curves, and decision curve analysis.
Main Results:
- The XGBoost model achieved the highest predictive performance with an AUC of 0.861 (development) and 0.877 (validation).
- Key predictors identified include HGB, PLT, previous bleeding, cerebral infarction, sex, surgical history, and hypertension.
- A nomogram based on these seven variables demonstrated good discriminative and calibration performance.
Conclusions:
- A robust predictive model for DAPT-associated bleeding risk was successfully developed.
- The model, presented as a nomogram, offers potential for optimizing DAPT treatment plans.
- This tool can contribute to improved patient outcomes and efficient healthcare resource utilization.
Objective:
This study aimed to develop a predictive model for assessing bleeding risk in dual antiplatelet therapy (DAPT) patients.
Methods:
A total of 18,408 DAPT patients were included. Data on patients' demographics, clinical features, underlying diseases, past history, and laboratory examinations were collected from Affiliated Dongyang Hospital of Wenzhou Medical University. The patients were randomly divided into two groups in a proportion of 7:3, with the most used for model development and the remaining for internal validation. LASSO regression, multivariate logistic regression, and six machine learning models, including random forest (RF), k-nearest neighbor imputing (KNN), decision tree (DT), extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), and Support Vector Machine (SVM), were used to develop prediction models. Model prediction performance was evaluated using area under the curve (AUC), calibration curves, decision curve analysis (DCA), clinical impact curve (CIC), and net reduction curve (NRC).
Results:
The XGBoost model demonstrated the highest AUC. The model features were comprised of seven clinical variables, including: HGB, PLT, previous bleeding, cerebral infarction, sex, Surgical history, and hypertension. A nomogram was developed based on seven variables. The AUC of the model was 0.861 (95% CI 0.847-0.875) in the development cohort and 0.877 (95% CI 0.856-0.898) in the validation cohort, indicating that the model had good differential performance. The results of calibration curve analysis showed that the calibration curve of this nomogram model was close to the ideal curve. The clinical decision curve also showed good clinical net benefit of the nomogram model.
Conclusions:
This study successfully developed a predictive model for estimating bleeding risk in DAPT patients. It has the potential to optimize treatment planning, improve patient outcomes, and enhance resource utilization.
Related Concept Videos
01:20Antiplatelet Drugs: Prostaglandin Synthesis, P2Y12 and Glycoprotein IIb/IIIa Inhibitors
Prostaglandin synthesis inhibitors, exemplified by the widely known aspirin, wield their power by irreversibly acetylating...
01:30Venous Thrombosis IV: Nursing Management
01:29Venous Thrombosis III: Interprofessional Care
01:27Coronary Artery Disease V: Surgical Management