Predicting Length of Stay Ranges by Using Novel Deep Neural Networks

Background And Aims: Accurately predicting length of stay (LOS) is considered a challenging task for health care systems globally. In previous studies on LOS range prediction, researchers commonly pre-classified the LOS ranges, which were the same for all patients in the same classification, and then utilized a classifier for prediction. In this study, we innovatively aimed to predict the specific LOS range for each patient (the LOS range was different for each patient).

Methods: In the modified deep neural network (DNN), the overall sample error (root mean square error (RMSE) method), the estimated sample error (ERR method), the probability distribution with different loss functions (Dis_Loss1, Dis_Loss2, and Dis_Loss3 method), and the generative adversarial networks (WGAN-GP for LOS method) are used for LOS range prediction. The Medical Information Mart for Intensive Care III (MIMIC-III) database is used to validate these methods.

Results: The RMSE method is convenient for LOS range prediction, but the predicted ranges are all consistent in the same batch of samples. The ERR method can achieve better prediction results in samples with low errors. However, the prediction effect is worse in samples with larger errors. The Dis_Loss1 method encounters a training instability problem. The Dis_Loss2 and Dis_Loss3 methods perform well in making predictions. Although WGAN-GP for LOS method does not show a substantial advantage over other methods, this method might have the potential to improve the predictive performance.

Conclusion: The results show that it is possible to achieve an acceptable accurate LOS range prediction through a reasonable model design, which may help physicians in the clinic.