Unsupervised patient representations from clinical notes with interpretable classification decisions

11/14/2017
by   Madhumita Sushil, et al.
0

We have two main contributions in this work: 1. We explore the usage of a stacked denoising autoencoder, and a paragraph vector model to learn task-independent dense patient representations directly from clinical notes. We evaluate these representations by using them as features in multiple supervised setups, and compare their performance with those of sparse representations. 2. To understand and interpret the representations, we explore the best encoded features within the patient representations obtained from the autoencoder model. Further, we calculate the significance of the input features of the trained classifiers when we use these pretrained representations as input.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/03/2018

Patient representation learning and interpretable evaluation using clinical notes

We have three contributions in this work: 1. We explore the utility of a...
research
05/19/2017

Learning Effective Representations from Clinical Notes

Clinical notes are a rich source of information about patient state. How...
research
06/25/2021

Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis

Confounding bias is a crucial problem when applying machine learning to ...
research
06/22/2023

Identifying and Disentangling Spurious Features in Pretrained Image Representations

Neural networks employ spurious correlations in their predictions, resul...
research
05/08/2022

Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations

Clinical notes are becoming an increasingly important data source for ma...
research
11/30/2021

What Do You See in this Patient? Behavioral Testing of Clinical NLP Models

Decision support systems based on clinical notes have the potential to i...
research
12/06/2021

Tele-EvalNet: A Low-cost, Teleconsultation System for Home based Rehabilitation of Stroke Survivors using Multiscale CNN-LSTM Architecture

Technology has an important role to play in the field of Rehabilitation,...

Please sign up or login with your details

Forgot password? Click here to reset