Model comparison in Emergency Severity Index level prediction

作者：

Highlights：

• We model ESI prediction using data from 870 patients over one month in 2008.

• Three methods are compared: regression, Bayesian networks and neural networks.

• Saturated oxygen level and chief complaint are significant predictors of ESI level.

• Models performed best using all data and had about 68% accuracy.

• Naïve Bayesian networks are recommended over neural networks and logistic regression.

摘要

Highlights•We model ESI prediction using data from 870 patients over one month in 2008.•Three methods are compared: regression, Bayesian networks and neural networks.•Saturated oxygen level and chief complaint are significant predictors of ESI level.•Models performed best using all data and had about 68% accuracy.•Naïve Bayesian networks are recommended over neural networks and logistic regression.

论文关键词：Neural networks,Naïve Bayesian networks,Ordinal logistic regression,Emergency Severity Index (ESI)

论文评审过程：Available online 29 June 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.06.026