Predicting quality of life after breast cancer surgery using ANN-based models: performance comparison with MR.

Purpose: The goal was to develop models for predicting long-term quality of life (QOL) after breast cancer surgery.

Methods: Data were obtained from 203 breast cancer patients who completed the SF-36 health survey before and 2 years after surgery. Two of the models used to predict QOL after surgery were artificial neural networks (ANNs), which included one multilayer perceptron (MLP) network and one radial basis function (RBF) network. The third model was a multiple regression (MR) model. The criteria for evaluating the accuracy of the system models were mean square error (MSE) and mean absolute percentage error (MAPE).

Results: Compared to the MR model, the ANN-based models generally had smaller MSE values and smaller MAPE values in the test data set. One exception was the second year MSE for the test value. Most MAPE values for the ANN models ranged from 10 to 20 %. The one exception was the 6-month physical component summary score (PCS), which ranged from 23.19 to 26.86 %. Comparison of criteria for evaluating system performance showed that the ANN-based systems outperformed the MR system in terms of prediction accuracy. In both the MLP and RBF networks, surgical procedure type was the most sensitive parameter affecting PCS, and preoperative functional status was the most sensitive parameter affecting mental component summary score.

Conclusion: The three systems can be combined to obtain a conservative prediction, and a combined approach is a potential supplemental tool for predicting long-term QOL after surgical treatment for breast cancer.

Relevance: Patients should also be advised that their postoperative QOL might depend not only on the success of their operations but also on their preoperative functional status.