Predictive model for 5-year mortality after breast cancer surgery in Taiwan residents

Su-Hsin Huang,Ming-Feng Houg,Hon-Yi Shi,Joon-Khim Loh,Jinn-Tsong Tsai

doi:10.1186/s40880-017-0192-9

Abstract

BackgroundFew studies of breast cancer surgery outcomes have used longitudinal data for more than 2 years. This study aimed to validate the use of the artificial neural network (ANN) model to predict the 5-year mortality of breast cancer patients after surgery and compare predictive accuracy between the ANN model, multiple logistic regression (MLR) model, and Cox regression model.MethodsThis study compared the MLR, Cox, and ANN models based on clinical data of 3632 breast cancer patients who underwent surgery between 1996 and 2010. An estimation dataset was used to train the model, and a validation dataset was used to evaluate model performance. The sensitivity analysis was also used to assess the relative significance of input variables in the prediction model.ResultsThe ANN model significantly outperformed the MLR and Cox models in predicting 5-year mortality, with higher overall performance indices. The results indicated that the 5-year postoperative mortality of breast cancer patients was significantly associated with age, Charlson comorbidity index (CCI), chemotherapy, radiotherapy, hormone therapy, and breast cancer surgery volumes of hospital and surgeon (all P < 0.05). Breast cancer surgery volume of surgeon was the most influential (sensitive) variable affecting 5-year mortality, followed by breast cancer surgery volume of hospital, age, and CCI.ConclusionsCompared with the conventional MLR and Cox models, the ANN model was more accurate in predicting 5-year mortality of breast cancer patients who underwent surgery. The mortality predictors identified in this study can also be used to educate candidates for breast cancer surgery with respect to the course of recovery and health outcomes.

Highlights

Few studies of breast cancer surgery outcomes have used longitudinal data for more than 2 years
Chemotherapy, radiotherapy, and hormone therapy were received by 41.8%, 11.0%, and 71.4% of the patients, respectively
Comparisons of samples in the training, testing, and validation datasets showed that the artificial neural network (ANN) model significantly outperformed the multiple logistic regression (MLR) and COX models in terms of sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and AUC (Table 3)

Summary

Introduction

Few studies of breast cancer surgery outcomes have used longitudinal data for more than 2 years. This study aimed to validate the use of the artificial neural network (ANN) model to predict the 5-year mortality of breast cancer patients after surgery and compare predictive accuracy between the ANN model, multiple logistic regression (MLR) model, and Cox regression model. Few studies have compared the artificial neural network (ANN), multiple logistic regression (MLR), and Cox regression prediction models in terms of internal validity (reproducibility), which is an essential performance metric [5, 6]. The ANN model used in the present study was a standard feed-forward, back-propagation neural network with three layers: an input layer, a hidden layer, and an output layer. The hidden neurons extract important features contained in the input data

Objectives

Methods

Results

Discussion

Conclusion