PDF(Pubmed)
Abstract：
UNASSIGNED: Heatstroke is a serious clinical condition caused by exposure to high temperature and high humidity environment, which leads to a rapid increase of the core temperature of the body to more than 40°C, accompanied by skin burning, consciousness disorders and other organ system damage. This study aims to analyze the effect of meteorological factors on the incidence of heatstroke using machine learning, and to construct a heatstroke forecasting model to provide reference for heatstroke prevention.
UNASSIGNED: The data of heatstroke incidence and meteorological factors in a city in South China from May to September 2014-2019 were analyzed in this study. The lagged effect of meteorological factors on heatstroke incidence was analyzed based on the distributed lag non-linear model, and the prediction model was constructed by using regression decision tree, random forest, gradient boosting trees, linear SVRs, LSTMs, and ARIMA algorithm.
UNASSIGNED: The cumulative lagged effect found that heat index, dew-point temperature, daily maximum temperature and relative humidity had the greatest influence on heatstroke. When the heat index, dew-point temperature, and daily maximum temperature exceeded certain thresholds, the risk of heatstroke was significantly increased on the same day and within the following 5 days. The lagged effect of relative humidity on the occurrence of heatstroke was different with the change of relative humidity, and both excessively high and low environmental humidity levels exhibited a longer lagged effect on the occurrence of heatstroke. With regard to the prediction model, random forest model had the best performance of 5.28 on RMSE and dropped to 3.77 after being adjusted.
UNASSIGNED: The incidence of heatstroke in this city is significantly correlated with heat index, heatwave, dew-point temperature, air temperature and zhongfu, among which the heat index and dew-point temperature have a significant lagged effect on heatstroke incidence. Relevant departments need to closely monitor the data of the correlated factors, and adopt heat prevention measures before the temperature peaks, calling on citizens to reduce outdoor activities.
UNASSIGNED: The data of heatstroke incidence and meteorological factors in a city in South China from May to September 2014-2019 were analyzed in this study. The lagged effect of meteorological factors on heatstroke incidence was analyzed based on the distributed lag non-linear model, and the prediction model was constructed by using regression decision tree, random forest, gradient boosting trees, linear SVRs, LSTMs, and ARIMA algorithm.
UNASSIGNED: The cumulative lagged effect found that heat index, dew-point temperature, daily maximum temperature and relative humidity had the greatest influence on heatstroke. When the heat index, dew-point temperature, and daily maximum temperature exceeded certain thresholds, the risk of heatstroke was significantly increased on the same day and within the following 5 days. The lagged effect of relative humidity on the occurrence of heatstroke was different with the change of relative humidity, and both excessively high and low environmental humidity levels exhibited a longer lagged effect on the occurrence of heatstroke. With regard to the prediction model, random forest model had the best performance of 5.28 on RMSE and dropped to 3.77 after being adjusted.
UNASSIGNED: The incidence of heatstroke in this city is significantly correlated with heat index, heatwave, dew-point temperature, air temperature and zhongfu, among which the heat index and dew-point temperature have a significant lagged effect on heatstroke incidence. Relevant departments need to closely monitor the data of the correlated factors, and adopt heat prevention measures before the temperature peaks, calling on citizens to reduce outdoor activities.
摘要：
■中暑是由于暴露于高温和高湿度环境而引起的严重临床状况，这导致身体的核心温度迅速增加到40°C以上，伴随着皮肤灼烧，意识障碍和其他器官系统损害。本研究旨在利用机器学习分析气象因素对中暑发病率的影响,并构建中暑预测模型,为防暑提供参考。
■本研究分析了2014-2019年5月至9月中国南方某市中暑发生率和气象因素的数据。基于分布滞后非线性模型分析了气象因素对中暑发病的滞后效应,利用回归决策树构建预测模型,随机森林,梯度增强树，线性SVRs，LSTMs,和ARIMA算法。
■累积滞后效应发现，热指数，露点温度,日最高温度和相对湿度对中暑的影响最大。当热量指数，露点温度,每日最高温度超过某些阈值，在同一天和随后的5天内，中暑的风险显着增加。相对湿度对中暑发生的滞后效应随相对湿度的变化而不同,过高和过低的环境湿度水平对中暑的发生都表现出更长的滞后作用。关于预测模型，随机森林模型对RMSE的最佳性能为5.28，经调整后降至3.77。
■这个城市中暑的发生率与热量指数显著相关,热浪,露点温度,气温和中福，其中热指数和露点温度对中暑发病率有显著的滞后影响。相关部门需要密切监测相关因素的数据，并在温度达到峰值之前采取防热措施，呼吁市民减少户外活动。
■本研究分析了2014-2019年5月至9月中国南方某市中暑发生率和气象因素的数据。基于分布滞后非线性模型分析了气象因素对中暑发病的滞后效应,利用回归决策树构建预测模型,随机森林,梯度增强树，线性SVRs，LSTMs,和ARIMA算法。
■累积滞后效应发现，热指数，露点温度,日最高温度和相对湿度对中暑的影响最大。当热量指数，露点温度,每日最高温度超过某些阈值，在同一天和随后的5天内，中暑的风险显着增加。相对湿度对中暑发生的滞后效应随相对湿度的变化而不同,过高和过低的环境湿度水平对中暑的发生都表现出更长的滞后作用。关于预测模型，随机森林模型对RMSE的最佳性能为5.28，经调整后降至3.77。
■这个城市中暑的发生率与热量指数显著相关,热浪,露点温度,气温和中福，其中热指数和露点温度对中暑发病率有显著的滞后影响。相关部门需要密切监测相关因素的数据，并在温度达到峰值之前采取防热措施，呼吁市民减少户外活动。
