Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing

Author:

Hsu Enshuo1,Roberts Kirk1

Affiliation:

1. University of Texas Health Science Center at Houston

Abstract

Abstract

The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning offer partial solutions to this issue, particularly using large language models (LLMs), but their performance still trails traditional supervised methods with moderate amounts of gold-standard data. In particular, inferencing with LLMs is computationally heavy. We propose an approach leveraging fine-tuning LLMs and weak supervision with virtually no domain knowledge that still achieves consistently dominant performance. Using a prompt-based approach, the LLM is used to generate weakly-labeled data for training a downstream BERT model. The weakly supervised model is then further fine-tuned on small amounts of gold standard data. We evaluate this approach using Llama2 on three different n2c2 datasets. With no more than 10 gold standard notes, our final BERT models weakly supervised by fine-tuned Llama2-13B consistently outperformed out-of-the-box PubMedBERT by 4.7–47.9% in F1 scores. With only 50 gold standard notes, our models achieved close performance to fully fine-tuned systems.

Publisher

Research Square Platform LLC

Reference34 articles.

1. Zhang, J., Hsieh, C.-Y., Yu, Y., Zhang, C. & Ratner, A. A Survey on Programmatic Weak Supervision. Preprint at http://arxiv.org/abs/2202.05433 (2022).

2. Ontology-driven and weakly supervised rare disease identification from clinical notes;Dong H;BMC Med Inform Decis Mak,2023

3. Weakly supervised spatial relation extraction from radiology reports;Datta S;JAMIA Open,2023

4. Few-shot learning for medical text: A review of advances, trends, and opportunities;Ge Y;Journal of Biomedical Informatics,2023

5. Using weak supervision and deep learning to classify clinical notes for identification of current suicidal ideation;Cusick M;J Psychiatr Res,2021

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3