October 3, 2025 Newswires

Researchers from University of Pennsylvania Describe Findings in Cardiovascular Diseases and Conditions (Application of a data mining approach to predict cardiovascular disease risk in the Republic of Korea: The National Health Insurance …): Cardiovascular Diseases and Conditions

Information Technology Business Daily

2025 OCT 03 (NewsRx) -- By a News Reporter-Staff News Editor at Information Technology Business Daily -- Current study results on Cardiovascular Diseases and Conditions have been published. According to news reporting originating from Philadelphia, Pennsylvania, by NewsRx correspondents, research stated, “Risk prediction is critical for cardiovascular disease (CVD) prevention and management. Existing CVD risk prediction models, including the Framingham Risk Score (FRS), are based on the Cox proportional hazard ratio regression.”

Our news editors obtained a quote from the research from the University of Pennsylvania, “Adaptation of a data mining approach could improve the accuracy of CVD risk prediction by being free from the linearity assumption. This study aimed to construct Korean population-based CVD risk prediction models using random survival forest and to compare their predictive accuracy to the FRS in a 14-year Korean cohort. This was a secondary data analysis using a Korean population-based cohort. Out of 463,783 eligible participants, 70 % were selected for training dataset using stratified random sampling, the remaining 30 % served as test dataset. Random survival forest was adopted to build risk prediction models using the training dataset and the test dataset was used to test the validity of the new models and the FRS. Three random forest-based models were developed. The random forest-based models were good in discrimination, with c statistics ranging from 0.698 to 0.747, while c statistics for the FRS were 0.692 and 0.733 in men and women, respectively. All random forest-based models showed good calibration, whereas the FRS tended to overestimate the CVD risk for men. The random survival forest-based models showed better performance with the FRS in a Korean population-based cohort.”

According to the news editors, the research concluded: “Continuous efforts are needed to improve the accuracy of CVD risk prediction for the Korean population and to utilize CVD risk prediction in clinical practice.”

This research has been peer-reviewed.

For more information on this research see: Application of a data mining approach to predict cardiovascular disease risk in the Republic of Korea: The National Health Insurance Service-National Health Screening Cohort. Heart & Lung, 2025;74:111-120. Heart & Lung can be contacted at: Mosby-elsevier, 360 Park Avenue South, New York, NY 10010-1710, USA.

The news editors report that additional information may be obtained by contacting Kathryn H. Bowles, School of Nursing, University of Pennsylvania, Philadelphia, PA, United States. Additional authors for this research include Sooyoung Park, Sarah J. Ratcliffe and Connie M. Ulrich.