The wisdom of crowds in action: Forecasting epidemic diseases with a web-based prediction market system

BACKGROUND The quest for an effective system capable of monitoring and predicting the trends of epidemic diseases is a critical issue for communities worldwide. With the prevalence of Internet access, more and more researchers today are using data from both search engines and social media to improve the prediction accuracy. In particular, a prediction market system (PMS) exploits the wisdom of crowds on the Internet to effectively accomplish relatively high accuracy. OBJECTIVE This study presents the architecture of a PMS and demonstrates the matching mechanism of logarithmic market scoring rules. The system was implemented to predict infectious diseases in Taiwan with the wisdom of crowds in order to improve the accuracy of epidemic forecasting. METHODS The PMS architecture contains three design components: database clusters, market engine, and Web applications. The system accumulated knowledge from 126 health professionals for 31 weeks to predict five disease indicators: the confirmed cases of dengue fever, the confirmed cases of severe and complicated influenza, the rate of enterovirus infections, the rate of influenza-like illnesses, and the confirmed cases of severe and complicated enterovirus infection. RESULTS Based on the winning ratio, the PMS predicts the trends of three out of five disease indicators more accurately than does the existing system that uses the five-year average values of historical data for the same weeks. In addition, the PMS with the matching mechanism of logarithmic market scoring rules is easy to understand for health professionals and applicable to predict all the five disease indicators. CONCLUSIONS The PMS architecture of this study affords organizations and individuals to implement it for various purposes in our society. The system can continuously update the data and improve prediction accuracy in monitoring and forecasting the trends of epidemic diseases. Future researchers could replicate and apply the PMS demonstrated in this study to more infectious diseases and wider geographical areas, especially the under-developed countries across Asia and Africa.

[1]  Ben Y. Reis,et al.  Surveillance Sans Frontières: Internet-Based Emerging Infectious Disease Intelligence and the HealthMap Project , 2008, PLoS medicine.

[2]  Yasushi Ohkusa,et al.  Development of a Web-Based Survey for Monitoring Daily Health and its Application in an Epidemiological Survey , 2011, Journal of medical Internet research.

[3]  David M. Pennock,et al.  Prediction Markets: Does Money Matter? , 2004, Electron. Mark..

[4]  Chen-yuan Tung,et al.  Using prediction markets of market scoring rule to forecast infectious diseases: a case study in Taiwan , 2015, BMC Public Health.

[5]  William B. Lober,et al.  Implementing Syndromic Surveillance , 2004 .

[6]  T. Bernardo,et al.  Scoping Review on Search Queries and Social Media for Disease Surveillance: A Chronology of Innovation , 2013, Journal of medical Internet research.

[7]  Panagiotis Takis Metaxas,et al.  The power of prediction with social media , 2013, Internet Res..

[8]  Lawrence M. Wein,et al.  Dynamic Allocation of Kidneys to Candidates on the Transplant Waiting List , 2000, Oper. Res..

[9]  Jeffrey W. Herrmann,et al.  Montgomery County's Public Health Service Uses Operations Research to Plan Emergency Mass Dispensing and Vaccination Clinics , 2006, Interfaces.

[10]  Gregoris Mentzas,et al.  Collective intelligence for idea management with Internet-based information aggregation markets , 2009, Internet Res..

[11]  R. Hanson.  LOGARITHMIC MARKETS CORING RULES FOR MODULAR COMBINATORIAL INFORMATION AGGREGATION , 2012 .

[12]  David M. Pennock,et al.  Using internet searches for influenza surveillance. , 2008, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[13]  Mark C Thurmond,et al.  Description of an epidemic simulation model for use in evaluating strategies to control an outbreak of foot-and-mouth disease. , 2003, American journal of veterinary research.

[14]  Andrew Leigh,et al.  Three Tools for Forecasting Federal Elections: Lessons from 2001 , 2001 .

[15]  Salaheddin M. Mahmud,et al.  Flu Trends ” and Emergency Department Triage Data Predicted the 2009 Pandemic H 1 N 1 Waves in Manitoba , 2011 .

[16]  L. V. Williams,et al.  Prediction Markets , 2003 .

[17]  E. Nsoesie,et al.  Forecasting Peaks of Seasonal Influenza Epidemics , 2013, PLoS currents.

[18]  Mark Dredze,et al.  Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance , 2015, PLoS Comput. Biol..

[19]  Massimo Bernaschi,et al.  Optimization of HAART with genetic algorithms and agent-based models of HIV infection , 2007, Bioinform..

[20]  D. Newbery,et al.  Futures Markets, Hedging and Speculation , 1989 .

[21]  Christina Ann LaComb,et al.  The imagination market , 2007, Inf. Syst. Frontiers.

[22]  A. R. Gallant,et al.  Noise and Nonlinearity in Measles Epidemics: Combining Mechanistic and Statistical Approaches to Population Modeling , 1998, The American Naturalist.

[23]  D. Focks,et al.  A simulation model of the epidemiology of urban dengue fever: literature analysis, model development, preliminary validation, and samples of simulation results. , 1995, The American journal of tropical medicine and hygiene.

[24]  Christl A. Donnelly,et al.  Predicted vCJD mortality in Great Britain , 2000, Nature.

[25]  Kenneth D. Mandl,et al.  Time series modeling for syndromic surveillance , 2003, BMC Medical Informatics Decis. Mak..

[26]  Kenneth D. Mandl,et al.  HealthMap: Global Infectious Disease Monitoring through Automated Classification and Visualization of Internet Media Reports , 2008, Journal of the American Medical Informatics Association.

[27]  Mark H. Whitworth,et al.  Designing the Response to an Anthrax Attack , 2006, Interfaces.

[28]  Jon Parker,et al.  A Distributed Platform for Global-Scale Agent-Based Models of Disease Transmission , 2011, TOMC.

[29]  Elad Yom-Tov,et al.  Detecting Disease Outbreaks in Mass Gatherings Using Internet Data Monitoring , 2015 .

[30]  L. J. Savage.  Elicitation of Personal Probabilities and Expectations , 1971 .

[31]  Trevor Strome,et al.  “Google Flu Trends” and Emergency Department Triage Data Predicted the 2009 Pandemic H1N1 Waves in Manitoba , 2011, Canadian journal of public health = Revue canadienne de sante publique.

[32]  Robert L. Winkler,et al.  The accuracy of extrapolation (time series) methods: Results of a forecasting competition , 1982 .

[33]  Gregor Brüggelambert,et al.  Information and efficiency in political stock markets: using computerized markets to predict election results , 2004 .

[34]  Yanping Bai,et al.  Prediction of SARS epidemic by BP neural networks with online prediction strategy , 2005 .

[35]  D. Kirschner,et al.  A hybrid multi-compartment model of granuloma formation and T cell priming in tuberculosis. , 2011, Journal of theoretical biology.

[36]  R. G. Will,et al.  Predicting the CJD epidemic in humans , 1997, Nature.

[37]  Robert S. Erikson,et al.  Are Political Markets Really Superior to Polls as Election Predictors , 2008 .

[38]  Eva K. Lee,et al.  Large-Scale Dispensing for Emergency Response to Bioterrorism and Infectious-Disease Outbreak , 2006, Interfaces.

[39]  D. Dunstan,et al.  Providing NHS staff with height-adjustable workstations and behaviour change strategies to reduce workplace sitting time: protocol for the Stand More AT (SMArT) Work cluster randomised controlled trial , 2015, BMC Public Health.

[40]  Koleman Strumpf,et al.  Historical presidential betting markets , 2004 .

[41]  F. Nelson,et al.  Use of prediction markets to forecast infectious disease activity. , 2007, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[42]  Robin Hanson,et al.  Combinatorial Information Market Design , 2003, Inf. Syst. Frontiers.

[43]  Vincent Conitzer,et al.  Making decisions based on the preferences of multiple agents , 2010, CACM.

[44]  Eldon Y. Li,et al.  User adoption of wisdom of crowd: usage and performance of prediction market system , 2015, Int. J. Electron. Bus..

[45]  Lawrence M Wein,et al.  Analyzing bioterror response logistics: the case of smallpox. , 2003, Mathematical biosciences.

[46]  Thomas A. Rietz,et al.  Prediction market accuracy in the long run , 2008 .

[47]  Kurt Matzler,et al.  Predicting New Product Success with Prediction Markets in Online Communities , 2013 .

[48]  Robert Forsythe,et al.  Anatomy of an Experimental Political Stock Market , 1992 .

[49]  Charles R. Plott,et al.  Information Aggregation Mechanisms: Concept, Design and Implementation for a Sales Forecasting Problem , 2002 .

[50]  E. Nsoesie,et al.  A systematic review of studies on forecasting the dynamics of influenza outbreaks , 2013, Influenza and other respiratory viruses.

[51]  Madhav V. Marathe,et al.  Computational epidemiology , 2013, CACM.

[52]  Jose L. Segovia-Juarez,et al.  Identifying control mechanisms of granuloma formation during M. tuberculosis infection using an agent-based model. , 2004, Journal of theoretical biology.

[53]  R. Ariano,et al.  Antibiotic combinations significantly more active than monotherapy in an in vitro infection model of Stenotrophomonas maltophilia. , 2005, Diagnostic microbiology and infectious disease.

[54]  John S. Brownstein,et al.  Evaluation of Internet-Based Dengue Query Data: Google Dengue Trends , 2014, PLoS neglected tropical diseases.

[55]  A. Langworthy,et al.  An influenza simulation model for immunization studies. , 1976, American journal of epidemiology.

[56]  Umar Saif,et al.  FluBreaks: early epidemic detection from Google flu trends. , 2012, Journal of medical Internet research.

[57]  F. Nelson,et al.  Using Prediction Markets to Forecast Trends in Infectious Diseases , 2006 .

[58]  George Miller,et al.  Responding to Bioterrorist Smallpox in San Antonio , 2006, Interfaces.

[59]  A. Valleron,et al.  Estimation of Epidemic Size and Incubation Time Based on Age Characteristics of vCJD in the United Kingdom , 2001, Science.

[60]  Mevlut Ture,et al.  Comparison of four different time series methods to forecast hepatitis A virus infection , 2006, Expert Syst. Appl..

[61]  Jeremy Ginsberg,et al.  Detecting influenza epidemics using search engine query data , 2009, Nature.

[62]  Richard C. Larson,et al.  Simple Models of Influenza Progression Within a Heterogeneous Population , 2007, Oper. Res..

[63]  K. Schulte,et al.  Castleman's disease—a two compartment model of HHV8 infection , 2010, Nature Reviews Clinical Oncology.

[64]  Sowmya R. Rao,et al.  Electronic health records in ambulatory care--a national survey of physicians. , 2008, The New England journal of medicine.

[65]  PengGuan,et al.  Forecasting model for the incidence of hepatitis A based on artificial neural network , 2004 .