MedEx: A Hybrid Cloud-Local LLM Approach for Clinical Data Interpretation

ACL ARR 2025 May Submission7284 Authors

Abstract: Deploying large language models (LLMs) in clinical settings faces critical trade-offs: cloud LLMs, with their extensive parameters and superior performance, pose risks to sensitive clinical data privacy, while local LLMs preserve privacy but often fail at complex clinical interpretation tasks. We propose MedEx, a hybrid framework where a cloud LLM decomposes complex clinical tasks into manageable subtasks and prompt generation, while a local LLM executes these subtasks in a privacy-preserving manner. Without accessing clinical data, the cloud LLM generates and validates subtask prompts using clinical guidelines and synthetic test cases. The local LLM executes subtasks locally and synthesizes outputs generated by the cloud LLM. We evaluate MedEx on pancreatic cancer staging using 100 radiology reports under NCCN guidelines. On free-text reports, MedEx achieves 70.21\% accuracy, outperforming local model baselines (without guideline: 48.94\%, with guideline: 56.59\%) and board-certified clinicians (gastroenterologists: 59.57\%, surgeons: 65.96\%, radiologists: 55.32\%). On structured reports, MedEx reaches 85.42\% accuracy, showing clear superiority across all settings.

Paper Type: Long

Research Area: Special Theme (conference specific)

Research Area Keywords: Interdisciplinary Recontextualization of NLP

Contribution Types: NLP engineering experiment, Data analysis

Languages Studied: English, Korean

Submission Number: 7284