ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission

Kexin Huang, Jaan Altosaar, Rajesh Ranganath
4/10/2019
cs.CLcs.LG

Official code: kexinhuang12345/clinicalBERT (453 stars, last commit 2022-10-17).

Abstract

Clinical notes contain information about patients that goes beyond structured data like lab values and medications. However, clinical notes have been underused relative to structured data, because notes are high-dimensional and sparse. This work develops and evaluates representations of clinical notes using bidirectional transformers (ClinicalBERT). ClinicalBERT uncovers high-quality relationships between medical concepts as judged by humans. ClinicalBert outperforms baselines on 30-day hospital readmission prediction using both discharge summaries and the first few days of notes in the intensive care unit. Code and model parameters are available.

View on arXivView PDF

Code Implementations(1)

kexinhuang12345/clinicalBERTOfficial100%

ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission (CHIL 2020 Workshop)

453125Python, Jupyter NotebookMar 30, 20194 years ago
clinicalberthospital-readmissionprediction

Similar Papers

Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV

83% match2026

A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models

82% match2026

Clinical Notes Reveal Physician Fatigue

81% match2023

Assessing mortality prediction through different representation models based on concepts extracted from clinical notes

81% match2022

FineEHR: Refine Clinical Note Representations to Improve Mortality Prediction

81% match2023

A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction

81% match1 repo372022

Cite this paper

@article{huang2019clinicalbert,
  title  = {ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission},
  author = {Kexin Huang and Jaan Altosaar and Rajesh Ranganath},
  year   = {2019},
  eprint = {1904.05342},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1904.05342}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1904.05342.svg)](https://codeofpaper.com/paper/1904.05342)

Discussion