English

The Use of Autoencoders for Discovering Patient Phenotypes

Machine Learning 2017-03-22 v1

Abstract

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.

Keywords

Cite

@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}
}