Differential Diagnosis of Dengue and Chikungunya in Colombian Children Using Machine Learning

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11238)


Dengue and chikungunya are vector borne diseases endemic in tropical countries around the world, with very similar clinical presentation, which makes it hard for physicians to tell them apart. Here we propose the use of Machine Learning based classifiers to perform differential diagnosis of dengue and chikungunya in pediatric patients, using simple blood test results as predictors instead of symptoms. Three variables (platelet count, white cell count and hematocrit percentage) from 447 pediatric patients from Hospital Infantil Napoleón Franco Pareja were collected to construct a dataset, later partitioned into train and test sets using Stratified Random Sampling. Grid Search with Stratified 5-Fold Cross-Validation was conducted to assess the performance of Logistic Regression, Support Vector Machine, and CART Decision Tree classifiers. Cross-Validation results show a L2 Logistic Regression model with second degree polynomial features outperforming the other models considered, with a cross-validated Receiver Operating Characteristic Area Under the Curve (ROC AUC) score of 0.8694. Subsequent results over the test set showed a 0.8502 ROC AUC score. Despite a reduced sample and a heavily imbalanced data set, ROC AUC score results are promising and support our approach for dengue and chikungunya differential diagnosis.


Dengue Chikungunya Logistic Regression Support vector machine Decision Tree CART 


  1. 1.
    Bhatt, S., et al.: The global distribution and burden of dengue. Nature 496(7446), 504–507 (2013)., Scholar
  2. 2.
    Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth and Brooks, Monterey (1984)zbMATHGoogle Scholar
  3. 3.
    Caglioti, C., Lalle, E., Castilletti, C., Carletti, F., Capobianchi, M.R., Bordi, L.: Chikungunya virus infection: an overview. New Microbiologica 36(3), 211–227 (2013).
  4. 4.
    Caicedo, W., Quintana, M., Pinzón, H.: Differential diagnosis of hemorrhagic fevers using ARTMAP. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds.) IBERAMIA 2012. LNCS (LNAI), vol. 7637, pp. 221–230. Springer, Heidelberg (2012). Scholar
  5. 5.
    Caicedo-Torres, W., Paternina, Á., Pinzón, H.: Machine learning models for early dengue severity prediction. In: Montes-y-Gómez, M., Escalante, H.J., Segura, A., Murillo, J.D. (eds.) IBERAMIA 2016. LNCS (LNAI), vol. 10022, pp. 247–258. Springer, Cham (2016). Scholar
  6. 6.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995). Scholar
  7. 7.
    Faisal, T., Taib, M.N., Ibrahim, F.: Neural network diagnostic system for dengue patients risk classification. J. Med. Syst. 36(2), 661–676 (2012). Scholar
  8. 8.
    Shameem Fathima, A., Manimeglai, D.: Analysis of significant factors for dengue infection prognosis using the random forest classifier. Int. J. Adv. Comput. Sci. Appl. (IJACSA) 6(2) (2015).
  9. 9.
    Fullerton, L.M., Dickin, S.K., Schuster-Wallace, C.J.: Mapping global vulnerability to dengue using the water associated disease index. Technical report, United Nations University (2014)Google Scholar
  10. 10.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016).
  11. 11.
    Keerthi, S.S., Lin, C.J.: Asymptotic behaviors of support vector machines with Gaussian kernel. Neural Comput. 15(7), 1667–1689 (2003). Scholar
  12. 12.
    Khan, M.I.H., et al.: Factors predicting severe dengue in patients with dengue fever. Mediterr. J. Hematol. Infect. Diseases 5(1) (2013)Google Scholar
  13. 13.
    Laoprasopwattana, K., Kaewjungwad, L., Jarumanokul, R., Geater, A.: Differential diagnosis of chikungunya, dengue viral infection and other acute febrile illnesses in children. Pediatr. Infect. Disease J. 31(5) (2012).,_Dengue.8.aspxCrossRefGoogle Scholar
  14. 14.
    Lee, V.J., et al.: Simple clinical and laboratory predictors of chikungunya versus dengue infections in adults. PLoS Negl. Trop. Diseases 6(9), 1–9 (2012). Scholar
  15. 15.
    Lee, V.J., et al.: Simple clinical and laboratory predictors of chikungunya versus dengue infections in adults. PLoS Negl. Trop. Diseases 6(9), e1786 (2012)., Scholar
  16. 16.
    Mardekian, S.K., Roberts, A.L.: Diagnostic options and challenges for dengue and chikungunya viruses. BioMed. Res. Int. 2015, 834371 (2015). Scholar
  17. 17.
    McCullagh, P., Nelder, J.: Generalized Linear Models. Chapman & Hall/CRC Monographs on Statistics & Applied Probability, 2nd edn. Taylor & Francis, Boa Raton (1989).
  18. 18.
    Pan American Health Organization: Chikungunya: Statistical Data (2014). Accessed 29 Feb 2016
  19. 19.
    Paternina-Caicedo, A., et al.: Features of dengue and chikungunya infections of Colombian children under 24 months of age admitted to the emergency department. J. Trop. Pediatr. (2017). Scholar
  20. 20.
    Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  21. 21.
    Potts, J.A., et al.: Prediction of dengue disease severity among pediatric Thai patients using early clinical laboratory indicators. PLoS Negl. Trop. Dis. 4(8), e769 (2010)CrossRefGoogle Scholar
  22. 22.
    World Health Organization: Chikungunya (2015). Accessed 29 Feb 2016

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Engineering, Computer and Mathematical SciencesAuckland University of TechnologyAucklandNew Zealand
  2. 2.Department of Computer ScienceUniversidad Tecnológica de BolívarCartagenaColombia
  3. 3.Hospital Infantil Napoleón Franco ParejaCartagenaColombia
  4. 4.Facultad de MedicinaUniversidad de CartagenaCartagenaColombia

Personalised recommendations