Enhancing Medical Diagnosis with Fine-Tuned Large Language Models: Addressing Cardiogenic Pulmonary Edema (CPE)

Yen Jung Chiu; Chao Chun Chuang; Kuo Yuan Hwa

doi:10.1145/3707127.3707138

Enhancing Medical Diagnosis with Fine-Tuned Large Language Models: Addressing Cardiogenic Pulmonary Edema (CPE)

Yen Jung Chiu, Chao Chun Chuang, Kuo Yuan Hwa^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Large Language Models (LLMs) have revolutionized natural language processing (NLP) with significant advancements in text generation. LLMs often struggle with complex domain-specific tasks, such as medical report analysis, despite their capabilities. This study focuses on enhancing LLM performance for medical applications, particularly in diagnosing and managing cardiogenic pulmonary edema (CPE). This research explores fine-tuning LLMs to develop a real-time CPE chatbot for Intensive Care Units (ICUs). The chatbot aims to provide diagnostic suggestions and explanations based on patient data. In the results, the LLaMa3-8B model performed better in predicting patients' CPE stage and keyword extraction. The accuracies achieved 72% and 86%.

Original language	English
Title of host publication	ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering
Publisher	Association for Computing Machinery, Inc
Pages	66-71
Number of pages	6
ISBN (Electronic)	9798400718274
DOIs	https://doi.org/10.1145/3707127.3707138
State	Published - 06 02 2025
Externally published	Yes
Event	11th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2024 - Osaka, Japan Duration: 08 11 2024 → 11 11 2024

Publication series

Name	ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering

Conference

Conference	11th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2024
Country/Territory	Japan
City	Osaka
Period	08/11/24 → 11/11/24

Bibliographical note

Publisher Copyright:
Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

Keywords

Edema
hospital
LLM
Medical report
Natural language model

Access to Document

10.1145/3707127.3707138

Cite this

Chiu, Y. J., Chuang, C. C., & Hwa, K. Y. (2025). Enhancing Medical Diagnosis with Fine-Tuned Large Language Models: Addressing Cardiogenic Pulmonary Edema (CPE). In ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering (pp. 66-71). (ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering). Association for Computing Machinery, Inc. https://doi.org/10.1145/3707127.3707138

Chiu, Yen Jung ; Chuang, Chao Chun ; Hwa, Kuo Yuan. / Enhancing Medical Diagnosis with Fine-Tuned Large Language Models : Addressing Cardiogenic Pulmonary Edema (CPE). ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering. Association for Computing Machinery, Inc, 2025. pp. 66-71 (ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering).

@inproceedings{690851070e064b5a8a3b1f8a8716a85a,

title = "Enhancing Medical Diagnosis with Fine-Tuned Large Language Models: Addressing Cardiogenic Pulmonary Edema (CPE)",

abstract = "Large Language Models (LLMs) have revolutionized natural language processing (NLP) with significant advancements in text generation. LLMs often struggle with complex domain-specific tasks, such as medical report analysis, despite their capabilities. This study focuses on enhancing LLM performance for medical applications, particularly in diagnosing and managing cardiogenic pulmonary edema (CPE). This research explores fine-tuning LLMs to develop a real-time CPE chatbot for Intensive Care Units (ICUs). The chatbot aims to provide diagnostic suggestions and explanations based on patient data. In the results, the LLaMa3-8B model performed better in predicting patients' CPE stage and keyword extraction. The accuracies achieved 72% and 86%.",

keywords = "Edema, hospital, LLM, Medical report, Natural language model",

author = "Chiu, {Yen Jung} and Chuang, {Chao Chun} and Hwa, {Kuo Yuan}",

note = "Publisher Copyright: Copyright {\textcopyright} 2024 held by the owner/author(s). Publication rights licensed to ACM.; 11th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2024 ; Conference date: 08-11-2024 Through 11-11-2024",

year = "2025",

month = feb,

day = "6",

doi = "10.1145/3707127.3707138",

language = "英语",

series = "ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering",

publisher = "Association for Computing Machinery, Inc",

pages = "66--71",

booktitle = "ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering",

}

Chiu, YJ, Chuang, CC & Hwa, KY 2025, Enhancing Medical Diagnosis with Fine-Tuned Large Language Models: Addressing Cardiogenic Pulmonary Edema (CPE). in ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering. ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering, Association for Computing Machinery, Inc, pp. 66-71, 11th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2024, Osaka, Japan, 08/11/24. https://doi.org/10.1145/3707127.3707138

Enhancing Medical Diagnosis with Fine-Tuned Large Language Models: Addressing Cardiogenic Pulmonary Edema (CPE). / Chiu, Yen Jung; Chuang, Chao Chun; Hwa, Kuo Yuan.
ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering. Association for Computing Machinery, Inc, 2025. p. 66-71 (ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Enhancing Medical Diagnosis with Fine-Tuned Large Language Models

T2 - 11th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2024

AU - Chiu, Yen Jung

AU - Chuang, Chao Chun

AU - Hwa, Kuo Yuan

PY - 2025/2/6

Y1 - 2025/2/6

N2 - Large Language Models (LLMs) have revolutionized natural language processing (NLP) with significant advancements in text generation. LLMs often struggle with complex domain-specific tasks, such as medical report analysis, despite their capabilities. This study focuses on enhancing LLM performance for medical applications, particularly in diagnosing and managing cardiogenic pulmonary edema (CPE). This research explores fine-tuning LLMs to develop a real-time CPE chatbot for Intensive Care Units (ICUs). The chatbot aims to provide diagnostic suggestions and explanations based on patient data. In the results, the LLaMa3-8B model performed better in predicting patients' CPE stage and keyword extraction. The accuracies achieved 72% and 86%.

AB - Large Language Models (LLMs) have revolutionized natural language processing (NLP) with significant advancements in text generation. LLMs often struggle with complex domain-specific tasks, such as medical report analysis, despite their capabilities. This study focuses on enhancing LLM performance for medical applications, particularly in diagnosing and managing cardiogenic pulmonary edema (CPE). This research explores fine-tuning LLMs to develop a real-time CPE chatbot for Intensive Care Units (ICUs). The chatbot aims to provide diagnostic suggestions and explanations based on patient data. In the results, the LLaMa3-8B model performed better in predicting patients' CPE stage and keyword extraction. The accuracies achieved 72% and 86%.

KW - Edema

KW - hospital

KW - LLM

KW - Medical report

KW - Natural language model

UR - http://www.scopus.com/inward/record.url?scp=85219193680&partnerID=8YFLogxK

U2 - 10.1145/3707127.3707138

DO - 10.1145/3707127.3707138

M3 - 会议稿件

AN - SCOPUS:85219193680

T3 - ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering

SP - 66

EP - 71

BT - ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering

PB - Association for Computing Machinery, Inc

Y2 - 8 November 2024 through 11 November 2024

ER -

Chiu YJ, Chuang CC, Hwa KY. Enhancing Medical Diagnosis with Fine-Tuned Large Language Models: Addressing Cardiogenic Pulmonary Edema (CPE). In ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering. Association for Computing Machinery, Inc. 2025. p. 66-71. (ICBBE 2024 - Proceedings of 2024 11th International Conference on Biomedical and Bioinformatics Engineering). doi: 10.1145/3707127.3707138

Enhancing Medical Diagnosis with Fine-Tuned Large Language Models: Addressing Cardiogenic Pulmonary Edema (CPE)

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this