Research on Hospital Medical Expense Based on BP Neural Network

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 220)


Data on hospitalization expense for coronary heart disease from 2009 to 2010 in one tertiary hospital were taken as examples, so as to construct fitting models for hospitalization expense based on BP neural network. Sensitivity analysis of influence factors was executed to evaluate the effect degrees of influence factors on hospitalization expense. The purposes of this study was to evaluate application value of BP neural network used in hospitalization expense study, explore and analyze the evaluation method fitting for the construction and character of hospitalization expense, and use medical costs rationally and control irrational increase of hospitalization expense. The results showed that the main influence factors of hospitalization expense were hospitalization days, treatment outcome, times of rescuing, and age, the comprehensive influences of which were 0.83101, 0.76113, 0.73227, and 0.44537, respectively.


Hospitalization expense BP Neural network Influence factors Sensitivity analysis 


  1. 1.
    Ge ZX, Sun ZQ (2007) Neural network theory and Matlab 2007 simulation, vol 1(2). Electrics Industry, Beijing 45–49Google Scholar
  2. 2.
    Liu B (2006) Research of model construction for hospitalization expense based on BP neural network, vol 2(6). Zhejiang University, Hangzhou, pp 101–109Google Scholar
  3. 3.
    Yan yan J, Jie Y (2006) The study of reasons and countermeasures for rapid rise of medical service costs. Cost Theor Appl 3(7):81–86Google Scholar
  4. 4.
    Wang J, Li M, Hu YT (2009) The analysis on the influencing factors of hospitalization expenses of the patients with gastric cancer by using bp neural network. Chin J Health stat, 4(14):99–103Google Scholar
  5. 5.
    Rumelart DE, James L (2009) McClelland and the PDP research group, ends. Parallel Diatribe 5(5):123–126Google Scholar
  6. 6.
    TED Processing (1986) Voles 1 and 2, vol 6(12). The M. I. T. Press, Cambridge, pp 171–176Google Scholar
  7. 7.
    SPSS (2009) Inc. neural network algorithms. Chicago Ill, 7(15):17–23Google Scholar
  8. 8.
    Xuan Jun D, Wei Na J (2010) Predictive efficiency comparison of ARIMA-time series and BP neural net model on infectious diseases. Mod Pract Med 8(3):142–145Google Scholar
  9. 9.
    Liu HB, Yang YL, Duan ZW (2009) Based on the neural network model to predict the future of coal workers pneumoconiosis hazard research. Chin J Health Stat 9(4):617–618Google Scholar
  10. 10.
    Zhang Q, Tian J (2009) Research on hybrid prediction methods of silicosis based on BP neural. Network 10(4):264–267MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Feng Yin Su
    • 1
  • Jian Hui Wu
    • 1
  • Chao Chen
    • 1
  • Dong Wang
    • 1
  1. 1.Hubei Province Key Laboratory of Occupational Health and Safety for Coal Industry, Department of Epidemiology and Health StatisticsHubei United UniversityTangshanChina

Personalised recommendations