Data Mining Applied to the Predictive Model of Triage System in Emergency Department

Authors: Wen-Tsann Lin, Yung-Tsan Jou, Yih-Chuan Wu, Yuan-Du Hsiao

Abstract:

The Emergency Department of a medical center in Taiwan cooperated to conduct the research. A predictive model of triage system is contracted from the contract procedure, selection of parameters to sample screening. 2,000 pieces of data needed for the patients is chosen randomly by the computer. After three categorizations of data mining (Multi-group Discriminant Analysis, Multinomial Logistic Regression, Back-propagation Neural Networks), it is found that Back-propagation Neural Networks can best distinguish the patients- extent of emergency, and the accuracy rate can reach to as high as 95.1%. The Back-propagation Neural Networks that has the highest accuracy rate is simulated into the triage acuity expert system in this research. Data mining applied to the predictive model of the triage acuity expert system can be updated regularly for both the improvement of the system and for education training, and will not be affected by subjective factors.

Keywords: Back-propagation Neural Networks, Data Mining, Emergency Department, Triage System.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1074839

References:

[1] X. K. Zhou, "Discussion on the features of high emergency resources consumers by data mining technology (unpublished thesis) ", National Taiwan University, Taiwan, 2004.
[2] Department of Health, DOH, Appraisal Standard of Emergency Departments. Website of DOH, Executive Yuan, Taiwan, 2009.
[3] A. Wollaston, P. Fahey, M. McKay, D. Hegney, P. Miller, & J. Wollaston, "Reliability and validity of the toowoomba adult trauma triage tool: a Queensland, Australia study," Accident and Emergency Nursing, vol.12(4), 2004, pp.230-237.
[4] R. M. Russo, V. J. Gururaj, A. S. Bunye, Y. H. Kim, & S. Ner, "Triage abilities of nurse practitioner vs. pediatrician," American Journal of Disease of Children, 129(6), 1975, pp.673-675.
[5] J. Y. Zhan, "Discussion on the accuracy rate of the nursing staff-s emergency triage and its correlation between the decision making capability (unpublished thesis) ", National Taipei College of Nursing, Taiwan, 2003.
[6] J. Brillman, D. Doezema, & D. Tandberg, "Triage´╝ÜLimitations in predicting the need for emergency care and hospital admissions," Annals of Emergency Medicine, vol.27(4), 1996, pp.493-500.
[7] E. G. Estrada, "Triage Systems," Nursing Clinics of North America, vol.16(1), 1981, pp.13-22.
[8] A. VanBoxel, "How We Do It: Improving the triage process," Journal of Emergency Nursing, vol.21(4), 1995, pp.332-334.
[9] J. Reinschmidt, H. Gottschalk, H. Kim, & D. Zwietering, Intelligent Miner for Data: Enhance Your Business Intelligence. USA: IBM International Technical Support Organization. 1999.
[10] M. L. Huang, & H. Y. Chen, "Development and comparison of automated classifiers for glaucoma diagnosis using stratus optical coherence tomography," Investigative Ophthalmology & Visual Science, vol.46(11), 2005, pp.4121-4129.
[11] M. A. Abdelfattah, A. T. El-Shahat, M. E. Ahmad, A. A. Mosaad, M. O. Mohamed, & E. S. Gamal, "Discrimination function based on hyaluronic acid and its degrading enzymes and degradation products for differentiating crrhotic from non-cirrhotic liver diseased patients in chronic HCV infection," Clinica Chimica Acta, vol.369(1), 2006, pp.66-72.
[12] E. Turban, J. E. Aronson, & T. P. Liang, Decision Support and Intelligent Systems (7th ed.). Pearson: Prentice Hall, 2005.
[13] R. Sharda, & D. Delen, "Predicting box-office success of motion pictures with neural networks," Expert Systems with Applications, vol.30(2), 2006, pp.243-254.
[14] A. M. Heidar, B. K. Nicolaos, & B. Mahesh, "Short-tern electric power load forecasting using feedforward neural networks," Expert Systems, vol.21(3), 2004, pp. 157-166.
[15] G. Handyside, Triage in Emergency Practice. St. Louis, MO: Mosby, 1996.
[16] Y. C. Ye, The Application and Practice of Neural Network Models, Taipei: Scholar Books, 2011