Multi-modal learning for inpatient length of stay prediction

Junde Chen, Yuxin Wen, Michael Pokojovy, Tzu-Liang Bill Tseng, Peter McCaffrey, Alex Vo, Eric Walser, Scott Moen

Abstract: Highlights•Combine multiple predictive models using various data modalities.•Attention-embedded 1D convolutional neural network is proposed for LoS prediction.•A customized loss function is used to address LoS data skewness.•LoS prediction task is approached as a regression problem.