Related Experiment Videos
Development and validation of a machine learning-based model for assessing coronary artery disease risk in
Yifan Deng1,2, Junmei Pan2,3, Shenghu He1,2
1Department of Cardiology, Northern Jiangsu People's Hospital Affiliated to Yangzhou University/Northern Jiangsu People's Hospital, Yangzhou 225001, China.
Insights
This study identified key risk factors for coronary heart disease (CHD) in postmenopausal women, developing an accurate risk assessment model for early detection. The XGBoost model showed superior performance in predicting CHD risk.
Area of Science:
- Cardiology
- Public Health
- Medical Informatics
Background:
- Coronary heart disease (CHD) poses a significant health risk to postmenopausal women.
- Early identification of individuals at high risk is crucial for effective prevention and management strategies.
Purpose of the Study:
- To investigate risk factors associated with CHD in postmenopausal women.
- To develop and validate a robust risk assessment model for CHD in this demographic.
Main Methods:
- Data from 1197 postmenopausal women with CHD were analyzed, split into training (n=821) and validation (n=376) cohorts.
- Lasso regression, logistic regression, and machine learning algorithms (including XGBoost) were employed to identify risk factors and build predictive models.
- Model performance was assessed using ROC curves, decision curve analysis (DCA), and calibration curves.
Main Results:
- Body mass index (BMI) classification and glycated hemoglobin were identified as independent risk factors for CHD.
- Age at menopause and high-density lipoprotein cholesterol (HDL-C) emerged as protective factors.
- The XGBoost model achieved high accuracy, with an AUC of 0.912 in the training set and 0.891 in the validation set.
Conclusions:
- The developed risk assessment model for CHD in Chinese postmenopausal women demonstrates strong accuracy and clinical applicability.
- This model facilitates the early identification of high-risk individuals, enabling timely intervention.
- Machine learning, particularly XGBoost, offers a powerful approach for CHD risk prediction in postmenopausal women.
Objectives:
To investigate the risk factors of coronary heart disease (CHD) and develop a risk assessment model for CHD in postmenopausal women.
Methods:
General information, medical history, and laboratory test results of the patients were collected from postmenopausal women with CHD admitted to two medical centers in Yangzhou (Jiangsu Province, China) from November, 2018 to November, 2023. After excluding cases with incomplete medical records, 1197 patients were included, who were divided into the training cohort (n=821) and validation cohort (n=376) based on the hospital of admission. In the training cohort, the risk factors for CHD in postmenopausal women were identified using Lasso regression, multivariate logistic regression analysis, and machine learning algorithms including Light GradientBoosting Machine (LGBM), Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), and Naive Bayes (NB). Risk assessment models were constructed using these algorithms, and their performance was evaluated using ROC curves, decision curve analysis (DCA), and calibration curves.
Results:
Lasso regression suggested body mass index (BMI) classification and glycated hemoglobin were independent risk factors for CHD in postmenopausal women, whereas age at menopause and high-density lipoprotein cholesterol (HDL-C) were independent protective factors (P<0.05). Among the machine learning models, XGBoost demonstrated the best assessment performance in both the training set (AUC: 0.912; sensitivity: 0.892; specificity: 0.766; recall: 0.892; F1-score: 0.899) and the validation set (AUC: 0.891; sensitivity: 0.836; specificity: 0.921; recall: 0.837; F1-score: 0.877). Calibration curve and DCA curve analyses indicated good consistency between the predicted and actual outcomes. A nomogram and SHAP summary plot were used to visualize and interpret the logistic regression model and the XGBoost model, respectively.
Conclusions:
The risk assessment model for CHD in Chinese postmenopausal women established in this study demonstrates good accuracy and applicability to allow early identification of high-risk patients.
Related Concept Videos
01:30Coronary Artery Disease I: Introduction
01:26Coronary Artery Disease IV: Preventive Measures
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:26Coronary Artery Disease II: Pathophysiology