Real Time Influenza Monitoring Using Hospital Big Data in Combination with Machine Learning Methods: Comparison Study.
Real Time Influenza Monitoring Using Hospital Big Data in Combination with Machine Learning Methods: Comparison Study.
复制标题
DOI：
10.2196/11361
复制
发表时间：
2018-12-21
影响因子：
8.5
通讯作者：
Bouzille, Guillaume
中科院分区：
文献类型：
--
作者：
Poirier, Canelle;Lavenu, Audrey;Bouzille, Guillaume
背景：传统的监测系统产生流感样疾病（ILI）发病率的估计，但有1- 3周的延迟。流感爆发的准确实时监测系统可能有助于做出公共卫生决策。几项研究调查了使用互联网用户的活动数据和不同的统计模型来近真实的预测流感流行的可能性。然而，很少有研究调查hospital big data.Objective：在这里，我们比较了互联网和电子健康记录（EHRs）数据和不同的统计模型，以确定最佳方法（数据类型和统计模型）ILI估计在真实的time.METHODS：我们使用谷歌数据的互联网数据和临床数据仓库eHOP，其中包括所有的EHRs从雷恩大学医院（法国），医院数据。结果：对于全国ILI发病率，采用随机森林、弹性网络和支持向量机（SVM）3种统计模型进行预测，其相关系数为0.98，均方误差（MSE）为866。对于布列塔尼地区，最好的相关性为0.923和MSE是2364与医院的数据和SVM model.Conclusions：我们发现，EHR数据与历史流行病学信息（法国哨兵网络）允许准确预测ILI发病率为整个法国以及布列塔尼地区，优于互联网数据，无论使用的统计模型。此外，弹性网络和SVM这两种统计模型的性能相当。
BACKGROUND: Traditional surveillance systems produce estimates of influenza-like illness (ILI) incidence rates, but with 1- to 3-week delay. Accurate real-time monitoring systems for influenza outbreaks could be useful for making public health decisions. Several studies have investigated the possibility of using internet users' activity data and different statistical models to predict influenza epidemics in near real time. However, very few studies have investigated hospital big data.OBJECTIVE: Here, we compared internet and electronic health records (EHRs) data and different statistical models to identify the best approach (data type and statistical model) for ILI estimates in real time.METHODS: We used Google data for internet data and the clinical data warehouse eHOP, which included all EHRs from Rennes University Hospital (France), for hospital data. We compared 3 statistical models-random forest, elastic net, and support vector machine (SVM).RESULTS: For national ILI incidence rate, the best correlation was 0.98 and the mean squared error (MSE) was 866 obtained with hospital data and the SVM model. For the Brittany region, the best correlation was 0.923 and MSE was 2364 obtained with hospital data and the SVM model.CONCLUSIONS: We found that EHR data together with historical epidemiological information (French Sentinelles network) allowed for accurately predicting ILI incidence rates for the entire France as well as for the Brittany region and outperformed the internet data whatever was the statistical model used. Moreover, the performance of the two statistical models, elastic net and SVM, was comparable.