1.Predicting the risk of cardiovascular and cerebrovascular diseases based on meteorological factors and the analysis of its correlation with incidence rates
Yuanyuan SHANG ; Zhengjing DU ; Ying DUAN ; Yanjing TANG
Journal of Public Health and Preventive Medicine 2024;35(5):1-5
Objective Based on meteorological factors, the prediction of the risk of cardiovascular and cerebrovascular diseases(CVD) and the analysis of its correlation with the incidence rate. Methods The research utilizes six years of data on CVD incidence from Xingyi, from 2017 to 2022, as the subject of study. The incidence risk levels are categorized based on the 25%, 50%, 75%, and 95% quantiles of the cumulative probability of the number of cases. The study is conducted based on the relationship between meteorological factors and the risk of incidence of CVD. Results The incidence of CVD shows a significant correlation with temperature, vapor pressure, atmospheric pressure, and relative humidity. It is negatively correlated with temperature and vapor pressure, among which the correlation with the daily minimum temperature is the highest at -0.504 (P < 0.05), and positively correlated with atmospheric pressure and relative humidity. Meteorological factors that have a significant correlation with the incidence rate are selected as input factors for the machine prediction model. It was found that the random forest model performs best in predicting the risk of incidence of CVD, with a comprehensive score of 0.851. Analysis of Relative Risk (RR) values found that there is a lagged association between exposure levels to meteorological factors and the incidence of cardiovascular and cerebrovascular diseases. A temperature drop of more than 11°C and an increase in atmospheric pressure of more than 8 hPa can significantly increase the risk of incidence. Conclusion The study revealed significant correlations between the incidence of CVD and meteorological parameters including temperature, water vapor pressure, atmospheric pressure, and relative humidity. Utilizing machine learning models, the research effectively predicted the risk of these diseases, uncovering that extreme weather conditions significantly elevate the risk of incidence. These findings provide a basis for meteorological risk assessment in public health interventions, emphasizing the importance of taking preventative measures in the context of extreme climate changes.