Designing a machine learning model for predicting cardiovascular events using the triglyceride-glucose index: a
Hedieh Alimi1, Vahid Mahdavizadeh2, Majid Ghayour-Mobarhan3
1Department of Cardiovascular, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran; Vascular and Endovascular Surgery Research Center, Mashhad University of Medical Sciences, Mashhad, Iran.
Insights
The triglyceride-glucose (TyG) index shows promise in predicting cardiovascular disease (CVD) events. Incorporating the TyG index into machine learning models may improve CVD risk assessment, particularly in developing nations.
Area of Science:
- Cardiology
- Biomedical Informatics
- Public Health
Background:
- Cardiovascular diseases (CVD) are a major global health concern, especially in developing countries.
- Current CVD risk prediction models often overlook insulin resistance (IR), a key metabolic factor.
- The triglyceride-glucose (TyG) index offers a novel way to assess IR using readily available data.
Purpose of the Study:
- To evaluate the effectiveness of the triglyceride-glucose (TyG) index in predicting cardiovascular events.
- To explore the utility of machine learning models in conjunction with the TyG index for CVD risk stratification.
- To assess the potential of the TyG index for improving CVD risk prediction in resource-limited settings.
Main Methods:
- Utilized data from the Mashhad Stroke and Heart Atherosclerotic Disorder (MASHAD) cohort, with over ten years of follow-up.
- Applied eleven machine learning models, including Multilayer Perceptron (MLP) and Decision Trees, to analyze predictive performance.
- Assessed the predictive value of the TyG index alongside traditional CVD risk factors.
Main Results:
- Cardiovascular events occurred in 10.9% of the study population.
- Multilayer Perceptron (MLP) and AdaBoost classifier models achieved the highest predictive accuracy (ROC-AUC 0.77 and 0.766, respectively).
- The TyG index emerged as a significant predictor, ranking fourth in the top-performing MLP and AdaBoost models.
Conclusions:
- The triglyceride-glucose (TyG) index demonstrates potential for enhancing cardiovascular disease risk prediction.
- Integrating the TyG index into machine learning models can improve the accuracy and applicability of CVD risk assessment.
- This approach holds particular value for developing countries facing a high burden of cardiovascular diseases.
Introduction:
Cardiovascular diseases (CVD) are the leading cause of death in developing countries, imposing a significant burden on society. Early detection of patients at higher risk of CVD events could reduce mortality. None of the models currently used for this purpose incorporates insulin resistance (IR), which can be measured using triglyceride and glucose levels. This study aims to explore the effectiveness of the triglyceride-glucose (TyG) index in predicting CVD events using machine learning models.
Methods And Materials:
This study utilized data from the Mashhad Stroke and Heart Atherosclerotic Disorder (MASHAD) cohort. Patients were evaluated at baseline and monitored for over ten years for CVD events. Eleven machine learning models, including a multilayer perceptron (MLP) and a decision tree, were used to evaluate the predictive value of the TyG index in conjunction with traditional risk factors.
Results:
The study population had a CVD event prevalence rate of 10.9%. The average age was 48.08 ± 8.26 years, with 60.0% of participants being female. The mean TyG index was 8.59 ± 0.66. The MLP and AdaBoost classifier models demonstrated the highest predictive accuracy with ROC-AUC scores of 0.77 and 0.766, respectively. The TyG index was identified as the fourth most significant predictor in the AdaBoost Classifier and MLP models, although it ranked lower in other models.
Conclusion:
This study highlights the potential benefits of incorporating the TyG index into traditional CVD risk prediction models to enhance accuracy and applicability, especially in developing countries.
