Comparative Analysis of Open-Source Language Models in Summarizing Medical Text Data

被引:0
|
作者
Chen, Yuhao [1 ]
Wang, Zhimu [1 ]
Zulkernine, Farhana [1 ]
机构
[1] Queens Univ, Sch Comp, Kingston, ON, Canada
来源
2024 IEEE INTERNATIONAL CONFERENCE ON DIGITAL HEALTH, ICDH 2024 | 2024年
基金
加拿大自然科学与工程研究理事会;
关键词
Biomedical summarization; Large Language Model; Generative Model;
D O I
10.1109/ICDH62654.2024.00030
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Unstructured text in medical notes and dialogues contains rich information. Recent advancements in Large Language Models (LLMs) have demonstrated superior performance in question answering and summarization tasks on unstructured text data, outperforming traditional text analysis approaches. However, there is a lack of scientific studies in the literature that methodically evaluate and report on the performance of different LLMs, specifically for domain-specific data such as medical chart notes. We propose an evaluation approach to analyze the performance of open-source LLMs such as Llama2 and Mistral for medical summarization tasks, using GPT-4 as an assessor. Our innovative approach to quantitative evaluation of LLMs can enable quality control, support the selection of effective LLMs for specific tasks, and advance knowledge discovery in digital health.
引用
收藏
页码:126 / 128
页数:3
相关论文
共 27 条
  • [1] Enhancing Code Security Through Open-Source Large Language Models: A Comparative Study
    Ridley, Norah
    Branca, Enrico
    Kimber, Jadyn
    Stakhanova, Natalia
    FOUNDATIONS AND PRACTICE OF SECURITY, PT I, FPS 2023, 2024, 14551 : 233 - 249
  • [2] Iterative Refactoring of Real-World Open-Source Programs with Large Language Models
    Choi, Jinsu
    An, Gabin
    Yoo, Shin
    SEARCH-BASED SOFTWARE ENGINEERING, SSBSE 2024, 2024, 14767 : 49 - 55
  • [3] Toponym resolution leveraging lightweight and open-source large language models and geo-knowledge
    Hu, Xuke
    Kersten, Jens
    Klan, Friederike
    Farzana, Sheikh Mastura
    INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE, 2024,
  • [4] Comparative Analysis of Large Language Models in Chinese Medical Named Entity Recognition
    Zhu, Zhichao
    Zhao, Qing
    Li, Jianjiang
    Ge, Yanhu
    Ding, Xingjian
    Gu, Tao
    Zou, Jingchen
    Lv, Sirui
    Wang, Sheng
    Yang, Ji-Jiang
    BIOENGINEERING-BASEL, 2024, 11 (10):
  • [5] Comparative diagnostic accuracy of GPT-4o and LLaMA 3-70b: Proprietary vs. open-source large language models in radiology☆
    Li, David
    Gupta, Kartik
    Bhaduri, Mousumi
    Sathiadoss, Paul
    Bhatnagar, Sahir
    Chong, Jaron
    CLINICAL IMAGING, 2025, 118
  • [6] Performance Assessment of Large Language Models in Medical Consultation: Comparative Study
    Seo, Sujeong
    Kim, Kyuli
    Yang, Heyoung
    JMIR MEDICAL INFORMATICS, 2025, 13
  • [7] An Experimental Research of Text-to-SQL for Heterogeneous Data in Large Language Models
    Yang, Weiwei
    Wang, Xiaoliang
    Chen, Bosheng
    Liu, Yong
    Wang, Bing
    Wang, Hui
    Wang, Xiaoke
    Zhua, Haitao
    Wang, Zhehao
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT I, ICIC 2024, 2024, 14875 : 378 - 389
  • [8] MediGPT: Exploring Potentials of Conventional and Large Language Models on Medical Data
    Rony, Mohammad Abu Tareq
    Islam, Mohammad Shariful
    Sultan, Tipu
    Alshathri, Samah
    El-Shafai, Walid
    IEEE ACCESS, 2024, 12 : 103473 - 103487
  • [9] Requirements Verification Through the Analysis of Source Code by Large Language Models
    Couder, Juan Ortiz
    Gomez, Dawson
    Ochoa, Omar
    SOUTHEASTCON 2024, 2024, : 75 - 80
  • [10] An open-source fine-tuned large language model for radiological impression generation: a multi-reader performance study
    Serapio, Adrian
    Chaudhari, Gunvant
    Savage, Cody
    Lee, Yoo Jin
    Vella, Maya
    Sridhar, Shravan
    Schroeder, Jamie Lee
    Liu, Jonathan
    Yala, Adam
    Sohn, Jae Ho
    BMC MEDICAL IMAGING, 2024, 24 (01):