Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data

01/06/2020
by   Ethan Steinberg, et al.
0

Widespread adoption of electronic health records (EHRs) has fueled development of clinical outcome models using machine learning. However, patient EHR data are complex, and how to optimally represent them is an open question. This complexity, along with often small training set sizes available to train these clinical outcome models, are two core challenges for training high quality models. In this paper, we demonstrate that learning generic representations from the data of all the patients in the EHR enables better performing prediction models for clinical outcomes, allowing for these challenges to be overcome. We adapt common representation learning techniques used in other domains and find that representations inspired by language models enable a 3.5 standard baselines, with the average improvement rising to 19 small number of patients are available for training a prediction model for a given clinical outcome.

READ FULL TEXT

page 2

page 6

page 7

page 12

research
05/05/2018

Learning Patient Representations from Text

Mining electronic health records for patients who satisfy a set of prede...
research
06/05/2023

Fair Patient Model: Mitigating Bias in the Patient Representation Learned from the Electronic Health Records

Objective: To pre-train fair and unbiased patient representations from E...
research
12/22/2022

Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models

Question: Can an encoder-decoder architecture pretrained on a large data...
research
03/31/2019

Surrogate-guided sampling designs for classification of rare outcomes from electronic medical records data

Scalable and accurate identification of specific clinical outcomes has b...
research
04/10/2023

Toward Cohort Intelligence: A Universal Cohort Representation Learning Framework for Electronic Health Record Analysis

Electronic Health Records (EHR) are generated from clinical routine care...
research
08/02/2016

Clinical Tagging with Joint Probabilistic Models

We describe a method for parameter estimation in bipartite probabilistic...
research
02/08/2021

Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration

Outcome prediction from clinical text can prevent doctors from overlooki...

Please sign up or login with your details

Forgot password? Click here to reset