Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports
This addresses radiologist burnout by reducing administrative workload and improving reporting efficiency, though it appears incremental as it builds on existing LLM and RLHF methods.
The paper tackles the problem of radiologist burnout from manually creating 'Impression' sections in radiology reports by proposing a coarse-to-fine framework using open-source LLMs (LLaMA and Mistral) to automatically generate and personalize impressions from clinical findings, fine-tuned on a large dataset from the University of Chicago Medicine.
The manual creation of the "Impression" section in radiology reports is a primary driver of radiologist burnout. To address this challenge, we propose a coarse-to-fine framework that leverages open-source large language models (LLMs) to automatically generate and personalize impressions from clinical findings. The system first produces a draft impression and then refines it using machine learning and reinforcement learning from human feedback (RLHF) to align with individual radiologists' styles while ensuring factual accuracy. We fine-tune LLaMA and Mistral models on a large dataset of reports from the University of Chicago Medicine. Our approach is designed to significantly reduce administrative workload and improve reporting efficiency while maintaining high standards of clinical precision.