Saved in:
Bibliographic Details
Main Authors: Shyam, Midhun, Basilakis, Jim, Luken, Kieran, Thomas, Steven, Crozier, John, Middleton, Paul M., Wang, X. Rosalind
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.04969
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908521157623808
author Shyam, Midhun
Basilakis, Jim
Luken, Kieran
Thomas, Steven
Crozier, John
Middleton, Paul M.
Wang, X. Rosalind
author_facet Shyam, Midhun
Basilakis, Jim
Luken, Kieran
Thomas, Steven
Crozier, John
Middleton, Paul M.
Wang, X. Rosalind
contents Triage notes, created at the start of a patient's hospital visit, contain a wealth of information that can help medical staff and researchers understand Emergency Department patient epidemiology and the degree of time-dependent illness or injury. Unfortunately, applying modern Natural Language Processing and Machine Learning techniques to analyse triage data faces some challenges: Firstly, hospital data contains highly sensitive information that is subject to privacy regulation thus need to be analysed on site; Secondly, most hospitals and medical facilities lack the necessary hardware to fine-tune a Large Language Model (LLM), much less training one from scratch; Lastly, to identify the records of interest, expert inputs are needed to manually label the datasets, which can be time-consuming and costly. We present in this paper a pipeline that enables the classification of triage data using LLM and limited compute resources. We first fine-tuned a pre-trained LLM with a classifier using a small (2k) open sourced dataset on a GPU; and then further fine-tuned the model with a hospital specific dataset of 1000 samples on a CPU. We demonstrated that by carefully curating the datasets and leveraging existing models and open sourced data, we can successfully classify triage data with limited compute resources.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04969
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Classification of kinetic-related injury in hospital triage data using NLP
Shyam, Midhun
Basilakis, Jim
Luken, Kieran
Thomas, Steven
Crozier, John
Middleton, Paul M.
Wang, X. Rosalind
Computation and Language
Machine Learning
Triage notes, created at the start of a patient's hospital visit, contain a wealth of information that can help medical staff and researchers understand Emergency Department patient epidemiology and the degree of time-dependent illness or injury. Unfortunately, applying modern Natural Language Processing and Machine Learning techniques to analyse triage data faces some challenges: Firstly, hospital data contains highly sensitive information that is subject to privacy regulation thus need to be analysed on site; Secondly, most hospitals and medical facilities lack the necessary hardware to fine-tune a Large Language Model (LLM), much less training one from scratch; Lastly, to identify the records of interest, expert inputs are needed to manually label the datasets, which can be time-consuming and costly. We present in this paper a pipeline that enables the classification of triage data using LLM and limited compute resources. We first fine-tuned a pre-trained LLM with a classifier using a small (2k) open sourced dataset on a GPU; and then further fine-tuned the model with a hospital specific dataset of 1000 samples on a CPU. We demonstrated that by carefully curating the datasets and leveraging existing models and open sourced data, we can successfully classify triage data with limited compute resources.
title Classification of kinetic-related injury in hospital triage data using NLP
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2509.04969