Multifactor Analysis Revealing Key Factors of Chronic NCDS Based on Random Forest Models

• DOI: 10.54097/194ejw55
• Publication Date: 2024-01-26T15:35:50Z
• Authors: Jinzhu Cai; Ziying Zhao; Xinzhe Zheng; Qiulin Feng; Jie Deng; Yu Zhang

This article investigates chronic non-communicable diseases with a focus on lifestyle and dietary habits. By establishing separate models, eliminating the influence of highly correlated variables, addressing data imbalance using SMOTE algorithm, seven independent variables were identified, including basic information, lifestyle, Random forest algorithm analysis revealed that smoking alcohol consumption significantly impact occurrence diseases, different factors associated specific diseases. Occupational type, work intensity, stress also have notable risk Furthermore, increasing daily physical activity is lower disease risk. These findings contribute to better understanding management providing valuable information for prevention treatment.