A comparison of attentional neural network architectures for modeling with electronic medical records.
Attention networks learn an intelligent weighted averaging mechanism over a series of entities, providing increases to both performance and interpretability. In this article, we propose a novel time-aware transformer-based network and compare it to another leading model with similar characteristics. We also decompose model performance along several critical axes and examine which features contribute most to our model's performance.
Author(s): Finch, Anthony, Crowell, Alexander, Chang, Yung-Chieh, Parameshwarappa, Pooja, Martinez, Jose, Horberg, Michael
DOI: 10.1093/jamiaopen/ooab064