We use autoencoders to create low-dimensional embeddings of underlying patient phenotypes that we hypothesize are a governing factor in determining how different patients will react to different interventions. We compare the performance of autoencoders that take fixed length sequences of concatenated timesteps as input with a recurrent sequence-to-sequence autoencoder. We evaluate our methods on around 35,500 patients from the latest MIMIC III dataset from Beth Israel Deaconess Hospital.
@article{arxiv.1703.07004,
title = {The Use of Autoencoders for Discovering Patient Phenotypes},
author = {Harini Suresh and Peter Szolovits and Marzyeh Ghassemi},
journal= {arXiv preprint arXiv:1703.07004},
year = {2017}
}