LGMar 20, 2017

The Use of Autoencoders for Discovering Patient Phenotypes

arXiv:1703.07004v130 citations
Originality Synthesis-oriented
AI Analysis

This work addresses patient outcome prediction in healthcare, but it is incremental as it applies existing autoencoder methods to medical data.

The study tackled the problem of discovering patient phenotypes to predict intervention responses by using autoencoders to create low-dimensional embeddings, comparing fixed-length and recurrent sequence-to-sequence models on 35,500 patients from the MIMIC III dataset.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes