The Foundational Capabilities of Large Language Models in Predicting Postoperative Risks Using Clinical Notes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alba, Charles, Xue, Bing, Abraham, Joanna, Kannampallil, Thomas, Lu, Chenyang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908294549864448
author Alba, Charles
Xue, Bing
Abraham, Joanna
Kannampallil, Thomas
Lu, Chenyang
author_facet Alba, Charles
Xue, Bing
Abraham, Joanna
Kannampallil, Thomas
Lu, Chenyang
contents Clinical notes recorded during a patient's perioperative journey holds immense informational value. Advances in large language models (LLMs) offer opportunities for bridging this gap. Using 84,875 pre-operative notes and its associated surgical cases from 2018 to 2021, we examine the performance of LLMs in predicting six postoperative risks using various fine-tuning strategies. Pretrained LLMs outperformed traditional word embeddings by an absolute AUROC of 38.3% and AUPRC of 33.2%. Self-supervised fine-tuning further improved performance by 3.2% and 1.5%. Incorporating labels into training further increased AUROC by 1.8% and AUPRC by 2%. The highest performance was achieved with a unified foundation model, with improvements of 3.6% for AUROC and 2.6% for AUPRC compared to self-supervision, highlighting the foundational capabilities of LLMs in predicting postoperative risks, which could be potentially beneficial when deployed for perioperative care
format Preprint
id arxiv_https___arxiv_org_abs_2402_17493
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Foundational Capabilities of Large Language Models in Predicting Postoperative Risks Using Clinical Notes
Alba, Charles
Xue, Bing
Abraham, Joanna
Kannampallil, Thomas
Lu, Chenyang
Computation and Language
J.3; I.2.7
Clinical notes recorded during a patient's perioperative journey holds immense informational value. Advances in large language models (LLMs) offer opportunities for bridging this gap. Using 84,875 pre-operative notes and its associated surgical cases from 2018 to 2021, we examine the performance of LLMs in predicting six postoperative risks using various fine-tuning strategies. Pretrained LLMs outperformed traditional word embeddings by an absolute AUROC of 38.3% and AUPRC of 33.2%. Self-supervised fine-tuning further improved performance by 3.2% and 1.5%. Incorporating labels into training further increased AUROC by 1.8% and AUPRC by 2%. The highest performance was achieved with a unified foundation model, with improvements of 3.6% for AUROC and 2.6% for AUPRC compared to self-supervision, highlighting the foundational capabilities of LLMs in predicting postoperative risks, which could be potentially beneficial when deployed for perioperative care
title The Foundational Capabilities of Large Language Models in Predicting Postoperative Risks Using Clinical Notes
topic Computation and Language
J.3; I.2.7
url https://arxiv.org/abs/2402.17493