Oncotarget

Research Papers:

Artificial neural network approach to predict surgical site infection after free-flap reconstruction in patients receiving surgery for head and neck cancer

Pao-Jen Kuo, Shao-Chun Wu, Peng-Chen Chien, Shu-Shya Chang, Cheng-Shyuan Rau, Hsueh-Ling Tai, Shu-Hui Peng, Yi-Chun Lin, Yi-Chun Chen, Hsiao-Yun Hsieh and Ching-Hua Hsieh _

PDF  |  HTML  |  How to cite

Oncotarget. 2018; 9:13768-13782. https://doi.org/10.18632/oncotarget.24468

Metrics: PDF 1398 views  |   HTML 3161 views  |   ?  


Abstract

Pao-Jen Kuo1,*, Shao-Chun Wu2,*, Peng-Chen Chien1, Shu-Shya Chang1, Cheng-Shyuan Rau3, Hsueh-Ling Tai1, Shu-Hui Peng1, Yi-Chun Lin1, Yi-Chun Chen1, Hsiao-Yun Hsieh1 and Ching-Hua Hsieh1,4

1Department of Plastic and Reconstructive Surgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan

2Department of Anesthesiology, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan

3Department of Neurosurgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan

4Center for Vascularized Composite Allotransplantation, Chang Gung Memorial Hospital, Taoyuan, Taiwan

*These authors have contributed equally to this work

Correspondence to:

Ching-Hua Hsieh, email: [email protected]

Keywords: artificial neural network (ANN); free-flap reconstruction; head and neck cancer; logistic regression (LR); surgical site infection (SSI)

Received: September 04, 2017    Accepted: February 03, 2018    Published: February 09, 2018

ABSTRACT

Background: The aim of this study was to develop an effective surgical site infection (SSI) prediction model in patients receiving free-flap reconstruction after surgery for head and neck cancer using artificial neural network (ANN), and to compare its predictive power with that of conventional logistic regression (LR).

Materials and methods: There were 1,836 patients with 1,854 free-flap reconstructions and 438 postoperative SSIs in the dataset for analysis. They were randomly assigned tin ratio of 7:3 into a training set and a test set. Based on comprehensive characteristics of patients and diseases in the absence or presence of operative data, prediction of SSI was performed at two time points (pre-operatively and post-operatively) with a feed-forward ANN and the LR models. In addition to the calculated accuracy, sensitivity, and specificity, the predictive performance of ANN and LR were assessed based on area under the curve (AUC) measures of receiver operator characteristic curves and Brier score.

Results: ANN had a significantly higher AUC (0.892) of post-operative prediction and AUC (0.808) of pre-operative prediction than LR (both P<0.0001). In addition, there was significant higher AUC of post-operative prediction than pre-operative prediction by ANN (p<0.0001). With the highest AUC and the lowest Brier score (0.090), the post-operative prediction by ANN had the highest overall predictive performance.

Conclusion: The post-operative prediction by ANN had the highest overall performance in predicting SSI after free-flap reconstruction in patients receiving surgery for head and neck cancer.


Creative Commons License All site content, except where otherwise noted, is licensed under a Creative Commons Attribution 4.0 License.
PII: 24468