Related Experiment Video
Updated: Jul 1, 2026
Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
Published on: September 26, 2018
Risk prediction for cardiovascular related diseases using PRS and EHR in the Framingham Heart Study
Taegun Kim1, Jaeseung Song2, Jong Wha J Joo1,3
1Department of Computer Science and Engineering, Dongguk University-Seoul, Seoul, South Korea.
Insights
Combining genetic risk scores with clinical data significantly improves cardiovascular disease prediction. This approach offers a more comprehensive understanding of disease risk factors for better forecasting.
Area of Science:
- Cardiovascular Medicine
- Genetics
- Epidemiology
Background:
- Cardiovascular disease (CVD) is a major global health concern, driving mortality and healthcare expenses.
- Polygenic risk scores (PRS) integrated with clinical data show promise for CVD prediction.
- Previous studies often focused on single CVD events, limiting comprehensive risk assessment.
Purpose of the Study:
- To investigate the combined predictive power of genetic and clinical factors for multiple cardiovascular diseases.
- To compare the performance of various prediction models using Framingham Heart Study data.
- To identify key genetic and clinical predictors for different cardiovascular conditions.
Main Methods:
- Utilized data from the Framingham Heart Study cohort.
- Compared prediction performance of different models across various scenarios.
- Assessed model performance using multiple evaluation metrics.
- Analyzed feature importance for genetic and clinical variables.
Main Results:
- Integrating PRS with clinical data generally enhanced prediction performance for cardiovascular diseases.
- Solely PRS-based models showed variable performance, effective for heritable conditions.
- Feature importance analysis revealed differential impacts of genetic and clinical variables across diseases.
Conclusions:
- Combining PRS with clinical variables offers a valuable strategy for comprehensive cardiovascular disease risk prediction.
- The findings support tailored study designs leveraging both genetic and clinical data for specific cardiovascular conditions.
- This integrated approach can inform personalized prevention and management strategies for cardiovascular health.
Abstract:
Cardiovascular disease is a leading cause of mortality and rising healthcare costs worldwide. Fortunately, the disease is preventable, and addressing risk factors can significantly reduce its effects. Over the past decade, risk prediction models have advanced significantly, with polygenic risk scoring analysis, which is often used in combination with clinical health information for prediction. However, most previous cardiovascular disease prediction studies based on polygenic risk scores have focused on a single specific disease or event, such as cardiac events. Given the complex nature of the cardiovascular disease, which involves a combination of genetic and environmental factors, a comprehensive analysis of the disease prediction results is essential. In this study, we investigate the genetic and environmental factors contributing to cardiovascular disease by utilizing data from the Framingham Heart Study, a leading cardiovascular cohort. We compared the prediction performance of different methods across various scenarios and assessed performance using various evaluation metrics to identify the best-fitting model for six cardiovascular related diseases. We also analyzed the feature importance of genetic and clinical variables, noting that different variables had varying effects on each disease. Our findings demonstrated the performance of prediction algorithms in forecasting cardiovascular disease by utilizing genetic and clinical factors, as well as highlighting the importance of each feature in the disease prediction. While models relying solely on polygenic risk score showed relatively low prediction performance for some diseases, integrating genetic information with clinical data improved prediction performance in most cases. For certain diseases, particularly those known to be heritable, polygenic risk scores demonstrated predictive ability, suggesting that they may serve as standalone predictive tools. We believe our study reveals the value of combining polygenic risk scores with clinical variables and expect that our thorough analysis can inform study designs tailored to specific diseases and research objectives.
