Sex-Specific Prompt Engineering for OSA Severity Classification Using Large Language Models 


Vol. 14,  No. 9, pp. 713-721, Sep.  2025
https://doi.org/10.3745/TKIPS.2025.14.9.713


PDF
  Abstract

Obstructive Sleep Apnea (OSA) is a prevalent but underdiagnosed sleep disorder associated with serious health risks. Although polysomnography (PSG) is the diagnostic gold standard, its cost and clinical burden limit scalability. This study explores the use of Large Language Models (LLMs), particularly the lightweight GPT-4o-mini, to classify OSA severity (Normal, Moderate, Severe) based solely on non-invasive demographic and sleep questionnaire data, without access to PSG features. We develop a prompt engineering pipeline that incorporates sex-specific feature importance extracted from Random Forest classifiers to design three types of prompts: Basic, Role-Based, and Chain-of-Thought (CoT). Experimental results show that Chain-of-Thought (CoT) prompts with feature emphasis tailored to male and female subgroups achieve F1 scores of up to 0.60–0.62, outperforming non-sex-specific (generic) prompts and matching the performance of Random Forest baselines. These findings highlight the effectiveness of sex-aware, few-shot prompting in improving diagnostic performance. Our results suggest that prompt-based LLMs can serve as interpretable, low-resource alternatives to traditional supervised models, with potential for scalable and equitable OSA screening.

  Statistics
  Cite this article

[IEEE Style]

S. Ryu, H. J. Kim, Y. Lee, "Sex-Specific Prompt Engineering for OSA Severity Classification Using Large Language Models," The Transactions of the Korea Information Processing Society, vol. 14, no. 9, pp. 713-721, 2025. DOI: https://doi.org/10.3745/TKIPS.2025.14.9.713.

[ACM Style]

Seungyeon Ryu, Hyeon Jin Kim, and Younghan Lee. 2025. Sex-Specific Prompt Engineering for OSA Severity Classification Using Large Language Models. The Transactions of the Korea Information Processing Society, 14, 9, (2025), 713-721. DOI: https://doi.org/10.3745/TKIPS.2025.14.9.713.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals