Hospitalization Length of Stay Prediction using Patient Event Sequences

Emil Riis Hansen, Thomas Dyhre Nielsen, Thomas Mulvad, Mads Nibe Strausholm, Tomer Sagi +1 more
3/20/2023
cs.LGcs.AI

No official code found. Best implementation: dkw-aau/medic_transformer (3 stars, last commit 2023-06-27).

Abstract

Predicting patients hospital length of stay (LOS) is essential for improving resource allocation and supporting decision-making in healthcare organizations. This paper proposes a novel approach for predicting LOS by modeling patient information as sequences of events. Specifically, we present a transformer-based model, termed Medic-BERT (M-BERT), for LOS prediction using the unique features describing patients medical event sequences. We performed empirical experiments on a cohort of more than 45k emergency care patients from a large Danish hospital. Experimental results show that M-BERT can achieve high accuracy on a variety of LOS problems and outperforms traditional nonsequence-based machine learning approaches.

View on arXivView PDF

Code Implementations(1)

dkw-aau/medic_transformerCommunity100%

Experimental code for using transformer models on patient event sequences

30PythonDec 9, 20223 years ago

Similar Papers

Length of Stay prediction for Hospital Management using Domain Adaptation

86% match2023

A Hybrid Data-Driven Approach For Analyzing And Predicting Inpatient Length Of Stay In Health Centre

83% match2025

Machine Learning and Statistical Insights into Hospital Stay Durations: The Italian EHR Case

83% match2025

Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction

83% match1 repo32025

ICU Mortality Prediction Using Long Short-Term Memory Networks

82% match2023

Equitable Length of Stay Prediction for Patients with Learning Disabilities and Multiple Long-term Conditions Using Machine Learning

82% match2024

Cite this paper

@article{hansen2023hospitalization,
  title  = {Hospitalization Length of Stay Prediction using Patient Event Sequences},
  author = {Emil Riis Hansen and Thomas Dyhre Nielsen and Thomas Mulvad and Mads Nibe Strausholm and Tomer Sagi and Katja Hose},
  year   = {2023},
  eprint = {2303.11042},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.11042v1}
}

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/2303.11042.svg)](https://codeofpaper.com/paper/2303.11042)

Discussion