Neural Networks Applied to Medical Data for Prediction of Patient Outcome

  • Machi Suka
  • Shinichi Oeda
  • Takumi Ichimura
  • Katsumi Yoshida
  • Jun Takezawa
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 6)

Prediction is vital in clinical fields, because it influences decision making for treatment and resource allocation. At present, medical records are readily accessible from hospital information systems. Based on the analysis of medical records, a number of predictive models have been developed to support the prediction of patient outcome. However, predictive models that achieve the desired predictive performance are few and far between.

In this chapter, we describe the capability of NNs applied to medical data for the prediction of patient outcome. Firstly, we applied a simple three-layer backpropagation NN to a dataset of intensive care unit (ICU) patients [12, 13] to develop a predictive model that estimates the probability of nosocomial infection. The predictive performance of the NN was compared with that of logistic regression using the cross-validation method.

Secondly, we invented a method of modeling time sequence data for prediction using multiple NNs. Based on the dataset of ICU patients, we examined whether multiple NNs outperform both logistic regression and the application of a single NN in the long-term prediction of nosocomial infection. According to the results of these studies, careful preparation of datasets improves the predictive performance of NNs, and accordingly, NNs outperform multivariate regression models. It is certain that NNs have capabilities as good predictive models. Further studies using real medical data may be required to achieve the desired predictive performance.


Logistic Regression Intensive Care Unit Admission Nosocomial Infection Predictive Performance Hide Neuron 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Dayhoff JE and DeLeo JM (2001). Artificial neural networks: Opening the black box. Cancer 91(8 Suppl): 1615–1635.CrossRefGoogle Scholar
  2. 2.
    Grobman WA and Stamilio DM (2006). Methods of clinical prediction. Am J Obstet Gynecol 194: 888–894.CrossRefGoogle Scholar
  3. 3.
    Hanley JA and McNeil BJ (1982). The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143: 29–36.Google Scholar
  4. 4.
    Harrell FE Jr, Lee KL, and Pollock BG (1988). Regression models in clinical studies: Determining relationships between predictors and response. J Natl Cancer Inst 80: 1198–1202.CrossRefGoogle Scholar
  5. 5.
    Ichimura T, Oeda S, Suka M, Mackin KJ, and Yoshida K (2004). Adaptive learning methods of reflective neural networks and immune multi-agent neural networks. In: Knowledge-Based Intelligent Systems for Healthcare. Advanced Knowledge International, Ichimura T and Yoshida K (eds), Adelaide, pp. 11–49.Google Scholar
  6. 6.
    Knaus WA, Draper EA, Wagner DP, and Zimmerman JE (1985). APACHE II: A severity of disease classification system. Cril Care Med 13: 818–829.CrossRefGoogle Scholar
  7. 7.
    Lavrac N (1999). Selected techniques for data mining in medicine. Artif Intell Med 16: 3–23.CrossRefGoogle Scholar
  8. 8.
    Lucas PJF and Abu-Hanna A (1999). Prognostic methods in medicine. Artif Intell Med 15: 105–119.CrossRefGoogle Scholar
  9. 9.
    Ohno-Machado L (2001). Modeling medical prognosis: Survival analysis techniques. J Biomed Inform 34: 428–439.CrossRefGoogle Scholar
  10. 10.
    Rumelhart DE, Hinton GE, and Williams RJ (1986). Learning representations by back-propagation errors. Nature 323: 533–536.CrossRefGoogle Scholar
  11. 11.
    Sargent DJ (2001). Comparison of artificial neural networks with other statistical approaches: Results from medical data sets. Cancer 91(8 Suppl): 1636–1642.CrossRefGoogle Scholar
  12. 12.
    Suka M, Oeda S, Ichimura T, Yoshida K, and Takezawa J (2004). Comparison of proportional hazard model and neural network models in a real data set of intensive care unit patients. Medinfo 11(Pt 1): 741–745.Google Scholar
  13. 13.
    Suka M, Yoshida K, and Takezawa J (2006). A practical tool to assess the incidence of nosocomial infection in Japanese intensive care units: The Japanese Nosocomial Infection Surveillance System. J Hosp Inf 63: 179–184.CrossRefGoogle Scholar
  14. 14.
    Tu JV (1996). Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 49: 1225–1231.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Machi Suka
    • 1
  • Shinichi Oeda
    • 2
  • Takumi Ichimura
    • 3
  • Katsumi Yoshida
    • 1
  • Jun Takezawa
    • 4
  1. 1.Department of Preventive MedicineSt. Marianna University School of MedicineKawasakiJapan
  2. 2.Department of Information and Computer EngineeringKisarazu National College of TechnologyKisarazuJapan
  3. 3.Graduate School of Information SciencesHiroshima City UniversityHiroshimaJapan
  4. 4.Department of Emergency and Intensive Care MedicineNagoya University Graduate School of MedicineNagoyaJapan

Personalised recommendations