RetSTA: An LLM-Based Approach for Standardizing Clinical Fundus Image Reports
This work addresses a domain-specific problem for healthcare by standardizing clinical fundus reports to improve data integration and AI understanding, though it is incremental as it builds on existing LLM fine-tuning methods.
The paper tackles the lack of unified standards in clinical fundus image reports by developing RetSTA-7B, an LLM-based approach that standardizes reports using a bilingual terminology and achieves superior performance in bilingual standardization tasks compared to other LLMs.
Standardization of clinical reports is crucial for improving the quality of healthcare and facilitating data integration. The lack of unified standards, including format, terminology, and style, is a great challenge in clinical fundus diagnostic reports, which increases the difficulty for large language models (LLMs) to understand the data. To address this, we construct a bilingual standard terminology, containing fundus clinical terms and commonly used descriptions in clinical diagnosis. Then, we establish two models, RetSTA-7B-Zero and RetSTA-7B. RetSTA-7B-Zero, fine-tuned on an augmented dataset simulating clinical scenarios, demonstrates powerful standardization behaviors. However, it encounters a challenge of limitation to cover a wider range of diseases. To further enhance standardization performance, we build RetSTA-7B, which integrates a substantial amount of standardized data generated by RetSTA-7B-Zero along with corresponding English data, covering diverse complex clinical scenarios and achieving report-level standardization for the first time. Experimental results demonstrate that RetSTA-7B outperforms other compared LLMs in bilingual standardization task, which validates its superior performance and generalizability. The checkpoints are available at https://github.com/AB-Story/RetSTA-7B.