Enhancing Pulmonary Disease Prediction Using Large Language Models With Feature Summarization and Hybrid Retrieval-Augmented Generation: Multicenter Methodological Study Based on Radiology Report
These findings highlight the potential of LLMs to revolutionize pulmonary disease prediction, particularly in resource-constrained settings, by surpassing traditional models in both accuracy and flexibility. The proposed prompt engineering strategy not only improves predictive performance but also enhances the adaptability of LLMs in complex medical contexts, offering a promising tool for advancing disease diagnosis and clinical decision-making.
Authors
- Yiming Yang (ORCID: https://orcid.org/0000-0003-1359-0364)
- Shuai Mao (ORCID: https://orcid.org/0000-0003-1630-6162)
- Li Li (ORCID: https://orcid.org/0000-0002-3515-7353)
- Congmin Zhu (ORCID: https://orcid.org/0000-0002-0472-9128)
- Honglei Liu (ORCID: https://orcid.org/0000-0003-2963-5248)
- Xiangdong Mu
- Yuqing Yang
- Chunting Tan (ORCID: https://orcid.org/0000-0002-6004-3390)
- Ruiteng Li
Institutions
- Beijing University of Posts and Telecommunications (CN)
- Capital Medical University (CN)
- Beijing YouAn Hospital (CN)
- Beijing Friendship Hospital (CN)
- Beijing Tsinghua Chang Gung Hospital (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-04-22
- DOI
- https://doi.org/10.2196/72638
- Citations
- 1
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.36