Dataset Information

Forecasting influenza epidemics from multi-stream surveillance data in a subtropical city of China.

ABSTRACT:

Background

Influenza has been associated with heavy burden of mortality and morbidity in subtropical regions. However, timely forecast of influenza epidemic in these regions has been hindered by unclear seasonality of influenza viruses. In this study, we developed a forecasting model by integrating multiple sentinel surveillance data to predict influenza epidemics in a subtropical city Shenzhen, China.

Methods

Dynamic linear models with the predictors of single or multiple surveillance data for influenza-like illness (ILI) were adopted to forecast influenza epidemics from 2006 to 2012 in Shenzhen. Temporal coherence of these surveillance data with laboratory-confirmed influenza cases was evaluated by wavelet analysis and only the coherent data streams were entered into the model. Timeliness, sensitivity and specificity of these models were also evaluated to compare their performance.

Results

Both influenza virology data and ILI consultation rates in Shenzhen demonstrated a significant annual seasonal cycle (p<0.05) during the entire study period, with occasional deviations observed in some data streams. The forecasting models that combined multi-stream ILI surveillance data generally outperformed the models with single-stream ILI data, by providing more timely, sensitive and specific alerts.

Conclusions

Forecasting models that combine multiple sentinel surveillance data can be considered to generate timely alerts for influenza epidemics in subtropical regions like Shenzhen.

SUBMITTER: Cao PH

PROVIDER: S-EPMC3968046 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Forecasting influenza epidemics from multi-stream surveillance data in a subtropical city of China.

Cao Pei-Hua PH Wang Xin X Fang Shi-Song SS Cheng Xiao-Wen XW Chan King-Pan KP Wang Xi-Ling XL Lu Xing X Wu Chun-Li CL Tang Xiu-Juan XJ Zhang Ren-Li RL Ma Han-Wu HW Cheng Jin-Quan JQ Wong Chit-Ming CM Yang Lin L

PloS one 20140327 3

<h4>Background</h4>Influenza has been associated with heavy burden of mortality and morbidity in subtropical regions. However, timely forecast of influenza epidemic in these regions has been hindered by unclear seasonality of influenza viruses. In this study, we developed a forecasting model by integrating multiple sentinel surveillance data to predict influenza epidemics in a subtropical city Shenzhen, China.<h4>Methods</h4>Dynamic linear models with the predictors of single or multiple surveil ...[more]

PMID: 24676091

Similar Datasets

Project description:BackgroundThe impact of influenza on morbidity and hospitalization in the tropics and subtropics is poorly quantified. Uniquely, the Hong Kong Special Administrative Region has computerized hospital discharge diagnoses on 95% of total bed days, allowing disease burden for a well-defined population to be accurately assessed.Methods and findingsInfluenza-associated morbidity and hospitalization was assessed by Poisson regression models for weekly counts of hospitalizations in Hong Kong during 1996 to 2000, using proportions of positive influenza types A (H1N1 and H3N2) and B isolations in specimens sent for laboratory diagnosis as measures of influenza virus circulation. We adjusted for annual trend, seasonality, temperature, and relative humidity, as well as respiratory syncytial virus circulation. We found that influenza was significantly associated with hospitalization for acute respiratory disease (International Classification of Diseases version 9 codes [ICD9] 460-466 and 480-487) and its subcategory pneumonia and influenza (ICD9 480-487) for all age groups. The annual rates of excess hospitalization per 100,000 population for acute respiratory diseases for the age groups 0-14, 15-39, 40-64, 65-74, and 75+ were 163.3 (95% confidence interval [CI], 135-190), 6.0 (95% CI, 2.7-8.9), 14.9 (95% CI, 10.7-18.8), 83.8 (95% CI, 61.2-104.2), and 266 (95% CI, 198.7-330.2), respectively. Influenza was also associated with hospitalization for cerebrovascular disease (ICD9 430-438) for those aged over 75 y (55.4; 95% CI, 23.1-87.8); ischemic heart disease (ICD9 410-414) for the age group 40-64 y (5.3; 95% CI, 0.5-9.5) and over 75 y (56.4; 95% CI, 21.1-93.4); and diabetes mellitus (ICD9 250) for all age groups older than 40 y.ConclusionsInfluenza has a major impact on hospitalization due to cardio-respiratory diseases as well as on cerebrovascular disease, ischemic heart disease, and diabetes mellitus in the tropics and subtropics. Better utilization of influenza vaccine during annual epidemics in the tropics will enhance global vaccine production capacity and allow for better preparedness to meet the surge in demand that is inevitable in confronting a pandemic.

Project description:BackgroundInfluenza epidemics pose significant social and economic challenges in China. Internet search query data have been identified as a valuable source for the detection of emerging influenza epidemics. However, the selection of the search queries and the adoption of prediction methods are crucial challenges when it comes to improving predictions. The purpose of this study was to explore the application of the Support Vector Machine (SVM) regression model in merging search engine query data and traditional influenza data.MethodsThe official monthly reported number of influenza cases in Liaoning province in China was acquired from the China National Scientific Data Center for Public Health from January 2011 to December 2015. Based on Baidu Index, a publicly available search engine database, search queries potentially related to influenza over the corresponding period were identified. An SVM regression model was built to be used for predictions, and the choice of three parameters (C, γ, ε) in the SVM regression model was determined by leave-one-out cross-validation (LOOCV) during the model construction process. The model's performance was evaluated by the evaluation metrics including Root Mean Square Error, Root Mean Square Percentage Error and Mean Absolute Percentage Error.ResultsIn total, 17 search queries related to influenza were generated through the initial query selection approach and were adopted to construct the SVM regression model, including nine queries in the same month, three queries at a lag of one month, one query at a lag of two months and four queries at a lag of three months. The SVM model performed well when with the parameters (C = 2, γ = 0.005, ɛ = 0.0001), based on the ensemble data integrating the influenza surveillance data and Baidu search query data.ConclusionsThe results demonstrated the feasibility of using internet search engine query data as the complementary data source for influenza surveillance and the efficiency of SVM regression model in tracking the influenza epidemics in Liaoning.

Dataset Information

Forecasting influenza epidemics from multi-stream surveillance data in a subtropical city of China.

Background

Methods

Results

Conclusions

Publications

Forecasting influenza epidemics from multi-stream surveillance data in a subtropical city of China.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets