38
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Forecasting influenza activity using self-adaptive AI model and multi-source data in Chongqing, China

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          Early detection of influenza activity followed by timely response is a critical component of preparedness for seasonal influenza epidemic and influenza pandemic. However, most relevant studies were conducted at the regional or national level with regular seasonal influenza trends. There are few feasible strategies to forecast influenza activity at the local level with irregular trends.

          Methods

          Multi-source electronic data, including historical percentage of influenza-like illness (ILI%), weather data, Baidu search index and Sina Weibo data of Chongqing, China, were collected and integrated into an innovative Self-adaptive AI Model (SAAIM), which was constructed by integrating Seasonal Autoregressive Integrated Moving Average model and XGBoost model using a self-adaptive weight adjustment mechanism. SAAIM was applied to ILI% forecast in Chongqing from 2017 to 2018, of which the performance was compared with three previously available models on forecasting.

          Findings

          ILI% showed an irregular seasonal trend from 2012 to 2018 in Chongqing. Compared with three reference models, SAAIM achieved the best performance on forecasting ILI% of Chongqing with the mean absolute percentage error (MAPE) of 11·9%, 7·5%, and 11·9% during the periods of the year 2014–2016, 2017, and 2018 respectively. Among the three categories of source data, historical influenza activity contributed the most to the forecast accuracy by decreasing the MAPE by 19·6%, 43·1%, and 11·1%, followed by weather information (MAPE reduced by 3·3%, 17·1%, and 2·2%), and Internet-related public sentiment data (MAPE reduced by 1·1%, 0·9%, and 1·3%).

          Interpretation

          Accurate influenza forecast in areas with irregular seasonal influenza trends can be made by SAAIM with multi-source electronic data.

          Related collections

          Most cited references33

          • Record: found
          • Abstract: found
          • Article: not found

          Forecasting seasonal outbreaks of influenza.

          Influenza recurs seasonally in temperate regions of the world; however, our ability to predict the timing, duration, and magnitude of local seasonal outbreaks of influenza remains limited. Here we develop a framework for initializing real-time forecasts of seasonal influenza outbreaks, using a data assimilation technique commonly applied in numerical weather prediction. The availability of real-time, web-based estimates of local influenza infection rates makes this type of quantitative forecasting possible. Retrospective ensemble forecasts are generated on a weekly basis following assimilation of these web-based estimates for the 2003-2008 influenza seasons in New York City. The findings indicate that real-time skillful predictions of peak timing can be made more than 7 wk in advance of the actual peak. In addition, confidence in those predictions can be inferred from the spread of the forecast ensemble. This work represents an initial step in the development of a statistically rigorous system for real-time forecast of seasonal influenza.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Role of social networks in shaping disease transmission during a community outbreak of 2009 H1N1 pandemic influenza.

            Evaluating the impact of different social networks on the spread of respiratory diseases has been limited by a lack of detailed data on transmission outside the household setting as well as appropriate statistical methods. Here, from data collected during a H1N1 pandemic (pdm) influenza outbreak that started in an elementary school and spread in a semirural community in Pennsylvania, we quantify how transmission of influenza is affected by social networks. We set up a transmission model for which parameters are estimated from the data via Markov chain Monte Carlo sampling. Sitting next to a case or being the playmate of a case did not significantly increase the risk of infection; but the structuring of the school into classes and grades strongly affected spread. There was evidence that boys were more likely to transmit influenza to other boys than to girls (and vice versa), which mimicked the observed assortative mixing among playmates. We also investigated the presence of abnormally high transmission occurring on specific days of the outbreak. Late closure of the school (i.e., when 27% of students already had symptoms) had no significant impact on spread. School-aged individuals (6-18 y) facilitated the introduction and spread of influenza in households, but only about one in five cases aged >18 y was infected by a school-aged household member. This analysis shows the extent to which clearly defined social networks affect influenza transmission, revealing strong between-place interactions with back-and-forth waves of transmission between the school, the community, and the household.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Real-Time Influenza Forecasts during the 2012–2013 Season

              Recently, we developed a seasonal influenza prediction system that uses an advanced data assimilation technique and real-time estimates of influenza incidence to optimize and initialize a population-based mathematical model of influenza transmission dynamics. This system was used to generate and evaluate retrospective forecasts of influenza peak timing in New York City. Here we present weekly forecasts of seasonal influenza developed and run in real time for 108 cites in the United States during the recent 2012–2013 season. Reliable ensemble forecasts of influenza outbreak peak timing with leads of up to 9 weeks were produced. Forecast accuracy increased as the season progressed, and the forecasts significantly outperformed alternate, analog prediction methods. By Week 52, prior to peak for the majority of cities, 63% of all ensemble forecasts were accurate. To our knowledge, this is the first time predictions of seasonal influenza have been made in real time and with demonstrated accuracy.
                Bookmark

                Author and article information

                Contributors
                Journal
                EBioMedicine
                EBioMedicine
                EBioMedicine
                Elsevier
                2352-3964
                30 August 2019
                September 2019
                30 August 2019
                : 47
                : 284-292
                Affiliations
                [a ]Department of Epidemiology, College of Preventive Medicine, Army Medical University (Third Military Medical University), Chongqing, People's Republic of China
                [b ]Chongqing Municipal Center for Disease Control and Prevention, Chongqing, People's Republic of China
                [c ]Ping An Technology (Shenzhen) Co., Ltd, Shenzhen, People's Republic of China
                [d ]Comprehensive AIDS Research Center and Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, School of Medicine, Tsinghua University, Beijing, People's Republic of China
                [e ]Meinian Institute of Health, Beijing, People's Republic of China
                Author notes
                [* ]Correspondence to: Y. Li, Department of Epidemiology, College of Preventive Medicine, Army Medical University (Third Military Medical University), Chongqing 400038, China. liyafei2008@ 123456hotmail.com liyafei2008@ 123456tmmu.edu.cn
                [** ]Correspondence to: J. Xiao, Ping An Technology (Shenzhen) Co., Ltd, Shenzhen 518000, China. xiaojing661@ 123456pingan.com.cn
                [*** ]Correspondence to: L. Zhang, Comprehensive AIDS Research Center and Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, School of Medicine, Tsinghua University, Beijing 100084, China. zhanglinqi@ 123456mail.tsinghua.edu.cn
                [1]

                These authors contributed equally.

                [2]

                These authors jointly directed the project and share the corresponding authorship.

                Article
                S2352-3964(19)30546-8
                10.1016/j.ebiom.2019.08.024
                6796527
                31477561
                5bff90c4-f84b-453f-bb5d-eebdfc4f5dcb
                © 2019 The Authors

                This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

                History
                : 24 May 2019
                : 9 August 2019
                : 9 August 2019
                Categories
                Research paper

                influenza,influenza-like illness,forecast,ai,multi-source electronic data

                Comments

                Comment on this article