Development and validation of a machine learning-based explainable predictive model for long-term net adverse
Junyan Zhang1, Yuting Lei2, Ran Liu3
1Department of Cardiology, West China Hospital of Sichuan University, Chengdu, China.
Insights
A new machine learning model accurately predicts long-term net adverse clinical events (NACEs) in high bleeding risk (HBR) patients undergoing percutaneous coronary intervention (PCI). This tool enhances clinical decision-making for improved patient outcomes in this vulnerable population.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning in Healthcare
Background:
- High bleeding risk (HBR) patients undergoing percutaneous coronary intervention (PCI) experience more adverse events.
- Current risk models inadequately assess HBR patients undergoing PCI.
- There is a critical need for improved risk prediction in PCI-HBR patients.
Purpose of the Study:
- To develop and validate a machine learning (ML) model for predicting long-term net adverse clinical events (NACEs) in patients with high bleeding risk undergoing PCI.
- To identify key predictors of NACEs in this specific patient cohort.
Main Methods:
- Utilized data from the Prognostic Analysis and an Appropriate Antiplatelet Strategy for Patients with Percutaneous Coronary Intervention and High Bleeding Risk (PPP-PCI) registry.
- Employed recursive feature elimination (RFE) and SHapley Additive exPlanations (SHAP) for feature selection and interpretation.
- Developed and compared four ML algorithms: logistic regression, random forest, gradient boosting, and XGBoost.
Main Results:
- Included 1512 patients classified as high bleeding risk (HBR) undergoing percutaneous coronary intervention (PCI).
- The XGBoost model achieved the highest predictive performance with an Area Under the Curve (AUC) of 0.85.
- SHAP analysis identified 24 significant predictors of NACEs, encompassing clinical, laboratory, and echocardiographic data.
Conclusions:
- The developed ML model demonstrates high accuracy and interpretability for predicting long-term NACEs in PCI-HBR patients.
- This model shows potential to improve clinical decision-making and patient care for HBR patients undergoing PCI.
- Further validation in diverse and larger populations is recommended.
Background:
Patients classified as having a high bleeding risk (HBR) and undergoing percutaneous coronary intervention (PCI) face a significantly greater incidence of net adverse clinical events (NACEs) than non-HBR patients do. Existing risk assessment models, such as the CRUSADE and TIMI scores, do not adequately address the unique risks faced by the HBR population. There is an urgent need for a precise and comprehensive predictive model tailored to PCI-HBR patients to guide clinical decision-making and improve patient outcomes.
Methods:
This study aimed to develop a machine learning-based predictive model for long-term NACE in PCI-HBR patients. We utilized data from the Prognostic Analysis and an Appropriate Antiplatelet Strategy for Patients with Percutaneous Coronary Intervention and High Bleeding Risk registry database. Feature selection and interpretation were performed via a SHapley Additive exPlanations (SHAP) model based on recursive feature elimination. Model construction and evaluation were conducted via four algorithms: logistic regression, random forest, gradient boosting, and XGBoost.
Results:
A total of 1512 PCI-HBR patients were included in the study. The XGBoost model demonstrated the highest predictive performance, achieving an area under the receiver operating characteristic curve of 0.85. The SHAP model identified 24 significant variables contributing to the prediction of NACE, including clinical parameters, laboratory findings, and echocardiographic data.
Conclusions:
Our machine learning-based model offers a promising tool for predicting long-term NACE in PCI-HBR patients. The model's high predictive accuracy and interpretability have the potential to enhance clinical decision-making and improve patient care. Further validation in larger, diverse populations is warranted to confirm these findings.
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
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020