Related Experiment Video
Updated: Aug 21, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Study on the risk of coronary heart disease in middle-aged and young people based on machine learning methods: a
Jiaoyu Cao1, Lixiang Zhang1, Likun Ma1
1Department of Cardiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.
Insights
Researchers identified key coronary heart disease risk factors in young and middle-aged individuals. The Extreme Gradient Boosting (XGBoost) model demonstrated superior accuracy in predicting heart disease risk for this demographic.
Area of Science:
- Cardiology
- Medical Informatics
- Predictive Analytics
Background:
- Coronary heart disease (CHD) poses a significant health risk, particularly in young and middle-aged populations.
- Accurate risk prediction is crucial for early intervention and management of CHD.
- Existing risk models may not fully capture the nuances of CHD development in younger demographics.
Purpose of the Study:
- To identify significant risk factors for coronary heart disease (CHD) in young and middle-aged individuals.
- To develop and evaluate a tailored risk prediction model for CHD in this specific age group.
- To compare the performance of machine learning models against traditional logistic regression for CHD risk prediction.
Main Methods:
- A retrospective cohort study involving 553 patients (201 with CHD, 352 without) from January 2017 to January 2020.
- Clinical data were analyzed using R software, incorporating 24 statistically significant indexes identified through univariate analysis.
- Four predictive models were constructed: logistic regression, BP neural network, random forest, and Extreme Gradient Boosting (XGBoost).
Main Results:
- Univariate analysis revealed 24 significant differentiating indexes between CHD and non-CHD groups.
- The XGBoost model achieved the highest predictive performance with an Area Under the Curve (AUC) of 0.940 and an F1 score of 0.887.
- Other models showed varying performance: Random Forest (AUC 0.928, F1 0.846), Logistic Regression (AUC 0.829, F1 0.634), and BP Neural Network (AUC 0.795, F1 0.606).
Conclusions:
- The XGBoost model demonstrates high efficiency in predicting coronary heart disease risk in young and middle-aged individuals.
- This advanced model can aid clinicians in effectively screening high-risk patients within this demographic.
- The findings support the clinical utility of machine learning for personalized CHD risk assessment.
Objective:
To identify coronary heart disease risk factors in young and middle-aged persons and develop a tailored risk prediction model.
Methods:
A retrospective cohort study was used in this research. From January 2017 to January 2020, 553 patients in the Department of Cardiology at a tertiary hospital in Anhui Province were chosen as research subjects. The research subjects were separated into two groups based on the results of coronary angiography performed during hospitalization (n = 201) and non-coronary heart disease (n = 352). R software (R 3.6.1) was used to analyze the clinical data of the two groups. A logistic regression prediction model and three machine learning models, including BP neural network, Extreme gradient boosting (XGBoost), and random forest, were built, and the best prediction model was chosen based on the relevant parameters of the different machine learning models.
Results:
Univariate analysis identified a total of 24 indexes with statistically significant differences between coronary heart disease and non-coronary heart disease groups, which were incorporated in the logistic regression model and three machine learning models. The AUCs of the test set in the logistic regression prediction model, BP neural network model, random forest model, and XGBoost model were 0.829, 0.795, 0.928, and 0.940, respectively, and the F1 scores were 0.634, 0.606, 0.846, and 0.887, indicating that the XGBoost model's prediction value was the best.
Conclusion:
The XGBoost model, which is based on coronary heart disease risk factors in young and middle-aged people, has a high risk prediction efficiency for coronary heart disease in young and middle-aged people and can help clinical medical staff screen young and middle-aged people at high risk of coronary heart disease in clinical practice.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Related Concept Videos
01:26Coronary Artery Disease IV: Preventive Measures
01:30Coronary Artery Disease I: Introduction
01:26Coronary Artery Disease II: Pathophysiology
01:20Blood Studies for Cardiovascular System I: Cardiac Biomarkers
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:28Imaging Studies for Cardiovascular System V: CT