A Research and Application Based on Gradient Boosting Decision Tree

  • Yun Xi
  • Xutian Zhuang
  • Xinming Wang
  • Ruihua Nie
  • Gansen ZhaoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11242)


Hand, foot, and mouth disease(HFMD) is an infectious disease of the intestines that damages people’s health, severe cases could lead to cardiorespiratory failure or death.

Therefore, severe cases’ identification of HFMD is important. A real-time, automatic and efficient prediction system based on multi-source data (structured and unstructured data), and gradient boosting decision tree(GBDT) is proposed in this paper for severe HFMD identification. A missing data imputation method based on GBDT model is proposed.

Experimental result shows that our model can identify severe HFMD with a reasonable area under the ROC curve (AUC) of 0.94, and which is better than that of PCIS by 17%.


Severe HFMD Disease identification Missing data Machine learning 



We would like to thank Guangzhou Women and Children Medical Center, for supporting clinical data during this research.

This research is supported by national Natural Science Foundation of China (NSFC), grant No. 61471176, Pearl River Nova Program of Guangzhou, grant No. 201610010199, Science Foundation for Excellent Youth Scholars of Guangdong Province, grant No. YQ2015046, Science and Technology Planning Project of Guangdong Province, grant Nos. 2017A010101015, 2017B030308009, 2017KZ010101, Special Project for Youth Top-notch Scholars of Guangdong Province, grant No. 2016TQ03X100, and also supported by Joint Foundation of BLUEDON Information Security Technologies Co., grand No. LD20170204 and LD20170207.


  1. 1.
    Solomon, T., Lewthwaite, P., et al.: Virology, epidemiology, pathogenesis, and control of enterovirus 71. Lancet Infecti. Dis. 10(11), 778–790 (2010)CrossRefGoogle Scholar
  2. 2.
    Zhang, S.: Nearest neighbor selection for iteratively KNN imputation. J. Syst. Softw. 85(11), 2541–2552 (2012)CrossRefGoogle Scholar
  3. 3.
    Ravì, D., Wong, C., et al.: Deep learning for health informatics. IEEE J. Biomed. Health Inf. 21(1), 4–21 (2017)CrossRefGoogle Scholar
  4. 4.
    Xing, W., Qiaohong, L., et al.: Hand, foot, and mouth disease in china, 2008–12: an epidemiological study. Lancet Infect. Dis. 14(4), 308–318 (2014)CrossRefGoogle Scholar
  5. 5.
    Chen, K.T., Chang, H.L., et al.: Epidemiologic features of hand-foot-mouth disease and herpangina caused by enterovirus 71 in Taiwan 1998–2005. Pediatrics 120(2), e244–e252 (2007)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Yang, T., Xu, G., et al.: A case-control study of risk factors for severe hand-foot-mouth disease among children in ningbo, China, 2010–2011. Eur. J. Pediatr. 171(9), 1359–1364 (2012)CrossRefGoogle Scholar
  7. 7.
    Sui, M., Huang, X., et al.: Application and comparison of laboratory parameters for forecasting severe hand-foot-mouth disease using logistic regression, discriminant analysis and decision tree. Clin. Lab. 62(6), 1023–1031 (2016)Google Scholar
  8. 8.
    Zhang, B., Wan, X., et al.: Machine learning algorithms for risk prediction of severe hand-foot-mouth disease in children. Sci. Rep. 7(1), 5368 (2017)CrossRefGoogle Scholar
  9. 9.
    Chen, T., Guestrin, C.: XGBOOST: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794. ACM (2016)Google Scholar
  10. 10.
    Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 1189–1232 (2001)Google Scholar
  11. 11.
    Xu, D., Zhang, M., et. al.: Data-driven information extraction from chinese electronic medical records. PloS one 10(8), e0136270 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Yun Xi
    • 1
  • Xutian Zhuang
    • 1
  • Xinming Wang
    • 1
  • Ruihua Nie
    • 1
  • Gansen Zhao
    • 1
    Email author
  1. 1.School of Computer ScienceSouth China Normal UniversityGuangzhouChina

Personalised recommendations