Predictive Dynamics: Modeling for Virological Surveillance and Clinical Management of Dengue

  • V. Sree Hari Rao
  • M. Naresh Kumar


Dengue fever is a flu-like illness spread by the bite of an infected mosquito and is fast emerging as a major public health concern. Timely and cost-effective diagnosis would reduce the mortality rates besides providing better grounds for clinical management and disease surveillance. Identifying the clinical features for early diagnosis of dengue would be useful in reducing the virus transmission in a community. In addition to the clinical features, obtaining the influential laboratory attributes and their range would aid in quick identification of disease severity in the suspected individuals. In this chapter a new alternating decision tree methodology which generates more accurate and simplified decision tree structures with simplified classification rules is discussed. This approach helps one to obtain the influential clinical and laboratory features which would aid in identifying the suspected dengue individuals and assess the severity of infection in them.


Dengue Virus Dengue Fever Dengue Hemorrhagic Fever Severe Acute Respiratory Syndrome Decision Node 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This research is supported by the Foundation for Scientific Research and Technological Innovation (FSRTI)—A Constituent Division of Sri Vadrevu Seshagiri Rao Memorial Charitable Trust, Hyderabad 500 035, India.


  1. Allison P (2002) Missing data. Sage, Thousand OaksGoogle Scholar
  2. CDC (2000) Centers for disease control and prevention. World distribution of dengue 2000.
  3. CDC (2011) Centers for disease control and prevention.
  4. Chadwick D, Arch B, Wilder-Smith A, Paton N (2006) Distinguishing dengue fever from other infections on the basis of simple clinical and laboratory features: application of logistic regression analysis. J Clin Virol 35(2):147–153PubMedCrossRefGoogle Scholar
  5. Cios KJ, Mooree W (2002) Uniqueness of medical data mining. Artif Intell Med 26:1–24PubMedCrossRefGoogle Scholar
  6. Crichton N (2002) Receiver operating characteristic (roc) curves. J Clin Nurs 11:134–136CrossRefGoogle Scholar
  7. Dash M, Liu H (1997) Feature selection for classification, intelligent data analysis. Intell Data Anal 1:131–156CrossRefGoogle Scholar
  8. De Paula S, Fonseca B (2004) Dengue: a review of the laboratory tests a clinician must know to achieve a correct diagnosis. Braz J Infect Dis 8(6):390–398PubMedGoogle Scholar
  9. Derouich M, Boutayeb A, Twizell E (2003) A model of dengue fever. Biomed Eng Online 2:4PubMedCrossRefGoogle Scholar
  10. Dixon J (1979) Pattern recognition with partly missing data. IEEE Trans Syst Man Cybern 9(10):617–621CrossRefGoogle Scholar
  11. Esteva L, Vargas C (1998) Analysis of a dengue disease transmission model. Math Biosci 15(2):131–151CrossRefGoogle Scholar
  12. Esteva L, Vargas C (1999) A model for dengue disease with variable human population. J Math Biol 38(3):220–240PubMedCrossRefGoogle Scholar
  13. Freund Y, Mason L (1999) The alternating decision tree learning algorithm. In: Proceeding of the sixteenth international conference on machine learning bled. ACM, SloveniaGoogle Scholar
  14. Friedman N, Geiger D, Goldszmidt M (1997) Bayesian network classifiers. Mach Learn 29:131–163CrossRefGoogle Scholar
  15. George R, Lum L (1997) Clinical spectrum of dengue infection. Dengue and dengue hemorrhagic fever. CAB International, OxfordGoogle Scholar
  16. George HJ, Pat L (1995) Estimating continuous distributions in Bayesian classifiers. In: Eleventh conference on uncertainty in artificial intelligence, San Mateo, pp 338–345Google Scholar
  17. Gibbons RV (2002) Dengue: an escalating problem. BMJ 324(7353):1563–1566PubMedCrossRefGoogle Scholar
  18. Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison-Wesley, ReadingGoogle Scholar
  19. Grassly N, Fraser C (2008) Mathematical models of infectious disease transmission. Nat Rev Microbiol 6(6):477–487PubMedGoogle Scholar
  20. Gubler D (1998) Dengue and dengue hemorrhagic fever. Clin Microbiol Rev 11:480–496PubMedGoogle Scholar
  21. Guzman M, Kouri G (2002) Dengue: an update. Lancet Infect Dis 2:33–42PubMedCrossRefGoogle Scholar
  22. Halstead S (1998) Pathogenesis of dengue: challenges to molecular biology. Science 239(4839):476–481CrossRefGoogle Scholar
  23. Halstead SB (2007) Dengue. Lancet 370(9599):1644–1652PubMedCrossRefGoogle Scholar
  24. Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (roc) curve. Radiology 143:29–36PubMedGoogle Scholar
  25. Harris E, Videa E, Perez L, Sandoval E, Tellez Y (2000) Clinical, epidemiologic, and virologic features of dengue in the 1998 epidemic in nicaragua. Am J Trop Med Hyg 63:5–11PubMedGoogle Scholar
  26. Haykins S (1994) Neural network: a comprehensive foundation. Prentice Hall, Upper Saddle RiverGoogle Scholar
  27. Heijden G, Donders A, Stijnen T, Moons K (2006) Imputation of missing values is superior to complete case analysis and the missing-indicator method in multivariable diagnostic research: a clinical example. J Clin Epidemiol 59(10):1102–1109. doi: 10.1016/j.jclinepi.2006.01.015 PubMedCrossRefGoogle Scholar
  28. Horton N, Lipsitz S (2001) Multiple imputation in practise: comparison of software packages for regression models with missing variables. Am Stat 55(3):244–254CrossRefGoogle Scholar
  29. Huang J, Ling C (2005) Using AUC and accuracy in evaluating learning algorithms. IEEE Trans Knowledge Data Eng 17(3):299–310CrossRefGoogle Scholar
  30. Kalayanarooj S, Vaughn D, Nimmannitya S, Green S, Suntayakorn S (1997) Early clinical and laboratory indicators of acute dengue illness. J Infect Dis 176(2):313–321PubMedCrossRefGoogle Scholar
  31. Kim JO, Curry J (1977) The treatment of missing data in multivariate analysis. Sociol Methods Res 6(2):215–240. doi: 10.1177/004912417700600206 CrossRefGoogle Scholar
  32. Kohavi R, John GH (1998) The wrapper approach. In: Feature extraction, construction and selection: a data mining perspective. Kluwer, New York, pp 33–49Google Scholar
  33. Kothari R, Dong M (2000) Decision trees for classification: a review and some new results. World Scientific, SingaporeGoogle Scholar
  34. Little R, Rubin D (1987) Statistical analysis with missing data. Wiley, New York. doi: 10.1007/BF02925480
  35. Liu H, Wu T (2003) Estimating the area under a receiver operating characteristic curve for repeated measures design. J Stat Softw 8:1–18Google Scholar
  36. Medeiros CCAR, Braga C, de Souza WV, Regis L, Monteiro AMV (2011) Modeling the dynamic transmission of dengue fever: investigating disease persistence. PLoS Negl Trop Dis 5(1)Google Scholar
  37. Metz C (1978) Basic principles of roc analysis. Sem Nucl Med 8:283–298CrossRefGoogle Scholar
  38. Middendorf M (2004) Predicting genetic regulatory response using classification. Bioinformatics 20:232–240CrossRefGoogle Scholar
  39. Monath TP (1994) Dengue: the risk to developed and developing countries. Proc Natl Acad Sci USA 91(7):2395–2400PubMedCrossRefGoogle Scholar
  40. Mussa A, Tshilidzi M (2006) The use of genetic algorithms and neural networks to approximate missing data in database. Comput Inform 24:1001–1013Google Scholar
  41. Nimmannitya S (1997) Dengue hemorrhagic fever: diagnosis and management. Dengue and dengue hemorrhagic fever. CAB International, OxfordGoogle Scholar
  42. Ooi E, Gubler D, Nam V (2007) Dengue research needs related to surveillance and emergency response. Tech. rep., World Health Organization, GenevaGoogle Scholar
  43. PAHO (2007) PAHO. Number of reported cases of dengue and dengue hemorrhagic fever (DHF) in the Americas, by country: figures for 2007 [database on the Internet]. Pan American PAHO, WashingtonGoogle Scholar
  44. Paula ML, Claudia TC, Eduardo M, Jose SC (2003) Uncertainties regarding dengue modeling in Rio de Janeiro, Brazil. Mem Inst Oswaldo Cruz 98(7):871–878CrossRefGoogle Scholar
  45. Pearson R (2005) Mining imperfect data: dealing with contamination and incomplete records. SIAM, PhiladelphiaCrossRefGoogle Scholar
  46. Pepe MS (2003) The statistical evaluation of medical tests for classification and prediction. Oxford University Press, OxfordGoogle Scholar
  47. Pongsumpun P, Tang IM (2001) A realistic age structured transmission model for dengue hemorrhagic fever in Thailand. Southeast Asian J Trop Med Public Health 32(2):336–340PubMedGoogle Scholar
  48. Qiao W, Gao Z, Harley R (2005) Continuous online identification of nonlinear plants in power systems with missing sensor measurements. In: IEEE international joint conference on neural networks, IEEE, Montreal, pp 1729–1734Google Scholar
  49. Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann, San FranciscoGoogle Scholar
  50. Ramos MM, Tomashek KM, Arguello DF, Luxemburger C, Quiones L, Lang J, Muoz-Jordan JL (2009) Early clinical features of dengue infection in Puerto Rico. Trans R Soc Trop Med Hyg 103(9):878–884PubMedCrossRefGoogle Scholar
  51. Roderick JL, Donald BR (2002) Statistical analysis with missing data, 2nd edn. Wiley, New YorkGoogle Scholar
  52. Ron K, George HJ (1997) Wrappers for feature subset selection. Artif Intell 97:273–324CrossRefGoogle Scholar
  53. Saeys Y, Inza I, LarrANNaga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23(19):2507–2517PubMedCrossRefGoogle Scholar
  54. Sa-Ngasang ASA, A-Nuegoonpipat A, Chanama S, Wibulwattanakij S, Pattanakul K, Sawanpanyalert P, Kurane I (2006) Specific IGM and IGG responses in primary and secondary dengue virus infections determined by enzyme-linked immunosorbent assay. Epidemiol Infect 134(4):820825CrossRefGoogle Scholar
  55. Schafer J (1997) Analysis of incomplete multivariate data. Chapman & Hall, LondonCrossRefGoogle Scholar
  56. Sree Hari Rao V, Naresh Kumar M (2010) Estimation of the parameters of an infectious disease model using neural networks. Nonlinear Anal: Real World Appl 11(3):1810–1818CrossRefGoogle Scholar
  57. Sree Hari Rao V, Naresh Kumar M (2012) A new intelligence-based approach for computer-aided diagnosis of dengue Fever, IEEE Transactions on Information Technology in Biomedicine 16(1):112–118Google Scholar
  58. Sree Hari Rao V, Naresh Kumar M (2011b) Novel algorithms for identification of influential features using particle swarm intelligence for effective diagnosis of dengue illness (preprint)Google Scholar
  59. Sree Hari Rao V, Naresh Kumar M (2011c) Novel non-parametric algorithms for imputation of missing values and knowledge extraction in databases (preprint)Google Scholar
  60. Sree Hari Rao V, Naresh Kumar M (2011d) Rule based approach for early diagnosis of dengue infection using clinical features for public health management (preprint)Google Scholar
  61. Stephen SW, Joseph EB, Anna PD, Murphy BR (2007) Prospects for a dengue virus vaccine. Nat Rev Microbiol 5:518–528CrossRefGoogle Scholar
  62. Tanner L, Schreiber M, Low J, Ong A, Tolfvenstam T (2008) Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness. PLoS Negl Trop Dis 2(3)Google Scholar
  63. Vaughn DW, Green S, Kalayanarooj S, Innis BL, Nimmannitya S, Suntayakorn S, Rothman AL, Ennis FA, Nisalak A (1997) Dengue in the early febrile phase: viremia and antibody responses. J Infect Dis 176:322–330PubMedCrossRefGoogle Scholar
  64. Vaughn D, Green S, Kalayanarooj S, Innis B, Nimmannitya S (2000) Dengue viremia titer, antibody response pattern, and virus serotype correlate with disease severity. J Infect Dis 181(1):2–9PubMedCrossRefGoogle Scholar
  65. Wearing HJ, Rohani P (2006) Ecological and immunological determinants of dengue epidemics. Proc Natl Acad Sci USA 103(31):802–807CrossRefGoogle Scholar
  66. WHO (2009) Dengue-guidelines for diagnosis, treatment, prevention and control. Tech. rep., WHO, GenevaGoogle Scholar
  67. Wilder-Smith A, Schwartz E (2005) Dengue in travelers. N Engl J Med 353:92432CrossRefGoogle Scholar
  68. Witten I, Frank E (2005) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, San FranciscoGoogle Scholar
  69. Wong SL, Zhang LV, Tong AHY, Li Z, Goldberg DS, King OD, Lesage G, Vidal M, Andrews B, Bussey H, Boone C, Roth FP (2004) Combining biological networks to predict genetic interactions. Proc Natl Acad Sci USA 101(44):15682–15687, + html PubMedCrossRefGoogle Scholar
  70. Yang Y, Webb GI (2001) Proportional k-interval discretization for naive-bayes classifiers. In: 12th European conference on machine learning. Springer. LNCS 2167:564–575Google Scholar
  71. Yang Y, Webb IG (2002) A comparative study of discretization methods for nave Bayes classifiers. In: Proceedings of PKAW, Japan, pp 159–173Google Scholar
  72. Zweig M, Campbell G (1993) Receiver-operating characteristic (roc) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 9(8):561–577Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Department of MathematicsJawaharlal Nehru Technological UniversityHyderabadIndia
  2. 2.Software and Database Systems GroupNational Remote Sensing Center (ISRO)HyderabadIndia

Personalised recommendations