Forecasting peak asthma admissions in London: an application of quantile regression models
Forecasting peak asthma admissions in London: an application of quantile regression models
复制标题
DOI：
10.1007/s00484-012-0584-0
复制
发表时间：
2013-07-01
影响因子：
3.2
通讯作者：
Sarran, Christophe
中科院分区：
文献类型：
--
作者：
Soyiri, Ireneous N.;Reidpath, Daniel D.;Sarran, Christophe
哮喘是一种引起全球重大公共卫生关注的慢性疾病。相关的发病率、死亡率和保健利用给保健基础设施和服务带来了巨大负担。本研究展示了一种多阶段分位数回归方法，使用来自医院事件统计、天气和空气质量的回顾性数据，以预测伦敦哮喘每日入院形式的医疗保健服务过度需求。哮喘每日入院的三变量分位数回归模型（QRM）拟合到环境因素滞后的14天范围内，考虑了数据保留样本中的季节性。代表性滞后汇集形成多元预测模型，通过系统的向后逐步约简方法选择。使用保留的数据样本对模型进行交叉验证，并比较其各自的均方根误差测量、灵敏度、特异性和预测值。其中两个预测模型能够以76%和62%的敏感性水平检测每日哮喘入院的极端数量，以及66%和76%的特异性水平。他们的阳性预测值对于保留样本（29%和28%）略高于保留模型开发样本（16%和18%）。qrm可用于多阶段选择合适的变量来预测哮喘极端事件。哮喘与环境因素（包括温度、臭氧和一氧化碳）之间的关联可用于利用qrm预测未来事件。
Asthma is a chronic condition of great public health concern globally. The associated morbidity, mortality and healthcare utilisation place an enormous burden on healthcare infrastructure and services. This study demonstrates a multistage quantile regression approach to predicting excess demand for health care services in the form of asthma daily admissions in London, using retrospective data from the Hospital Episode Statistics, weather and air quality. Trivariate quantile regression models (QRM) of asthma daily admissions were fitted to a 14-day range of lags of environmental factors, accounting for seasonality in a hold-in sample of the data. Representative lags were pooled to form multivariate predictive models, selected through a systematic backward stepwise reduction approach. Models were cross-validated using a hold-out sample of the data, and their respective root mean square error measures, sensitivity, specificity and predictive values compared. Two of the predictive models were able to detect extreme number of daily asthma admissions at sensitivity levels of 76 % and 62 %, as well as specificities of 66 % and 76 %. Their positive predictive values were slightly higher for the hold-out sample (29 % and 28 %) than for the hold-in model development sample (16 % and 18 %). QRMs can be used in multistage to select suitable variables to forecast extreme asthma events. The associations between asthma and environmental factors, including temperature, ozone and carbon monoxide can be exploited in predicting future events using QRMs.