Comparison of artificial neural network and logistic regression models for predicting mortality in elderly patients with hip fracture

Lin, Chen-Chiang; Ou, Yang-Kun; Chen, Shyh-Huei; Liu, Yung-Ching; Lin, Jinn

doi:10.1016/j.injury.2010.04.023

« Previous Next »Injury
Volume 41, Issue 8 , Pages 869-873, August 2010

Comparison of artificial neural network and logistic regression models for predicting mortality in elderly patients with hip fracture

Chen-Chiang Lin
- Department of Orthopedics, National Taiwan University Hospital Yun-Lin Branch, Douliou City, Yunlin 640, Taiwan
- Department of Industrial Engineering and Management, National Yunlin University of Science and Technology, 123 Section 3, University Road, Douliou City, Yunlin 640, Taiwan
Yang-Kun Ou
- Department of Industrial Engineering and Management, National Yunlin University of Science and Technology, 123 Section 3, University Road, Douliou City, Yunlin 640, Taiwan
Shyh-Huei Chen
- Department of Industrial Engineering and Management, National Yunlin University of Science and Technology, 123 Section 3, University Road, Douliou City, Yunlin 640, Taiwan
Yung-Ching Liu
- Department of Industrial Engineering and Management, National Yunlin University of Science and Technology, 123 Section 3, University Road, Douliou City, Yunlin 640, Taiwan
Jinn Lin
- Department of Orthopedics, National Taiwan University Hospital Yun-Lin Branch, Douliou City, Yunlin 640, Taiwan
- Corresponding author. Tel.: +886 5 532 3911; fax: +886 5 537 9742.

Accepted 22 April 2010.

Abstract

Purpose

Older patients with hip fracture have a mortality rate one year after surgery of 20–30%. The purpose of this study is to establish a predictive model to assess the outcome of surgical treatment in older patients with hip fracture.

Methods

A database of information from 286 consecutive cases of surgery for hip fracture from the Department of Orthopedics, National Taiwan University Hospital Yun-Lin Branch, was utilised for model building and testing. Both logistic regression and artificial neural network (ANN) models were developed. Cases were randomly assigned to training and testing datasets. A testing dataset was utilised to test the accuracy of both models (n=89).

Results

The areas under the receiver operator characteristic curves of both models were utilised to compare predictability and accuracy. The logistic regression training and testing datasets had an area of 0.938 (95% CI: 0.904, 0.972) and 0.784 (95% CI: 0.669, 0.899), respectively, below the 0.998 (95% CI: 0.995, 1.000) and 0.949 (95% CI: 0.857, 1.000) of the final ANN model.

Conclusion

Overall, ANNs have higher predictive ability than logistic regression, perhaps because they are not affected by interactions between factors. They may assist in complex decision making in the clinical setting.

Keywords: Mortality, Predicting, Hip fracture, Artificial neural network, Logistic regression