Developing a Model to Predict Workers' Risk of Heart Attack Using Regularized Greedy Forests
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study introduces a predictive model using Regularized Greedy Forest (RGF) to identify high-risk heart attack candidates among workers. Heart disease risks are heightened by occupational stressors like stress and sedentary lifestyles. The RGF algorithm effectively handles complex datasets, surpassing traditional models like CART and KNN in prediction accuracy. The model highlights age, cholesterol, and physical activity as key risk factors, achieving an accuracy of 63.7% and an AUC of 65.1%. This research emphasizes machine learning's role in enhancing early intervention strategies in occupational health.
Abstract
This study introduces a predictive model using Regularized Greedy Forest (RGF) to identify high-risk heart attack candidates among workers. Heart disease risks are heightened by occupational stressors like stress and sedentary lifestyles. The RGF algorithm effectively handles complex datasets, surpassing traditional models like CART and KNN in prediction accuracy. The model highlights age, cholesterol, and physical activity as key risk factors, achieving an accuracy of 63.7% and an AUC of 65.1%. This research emphasizes machine learning's role in enhancing early intervention strategies in occupational health.