A fine-tuned, domain-specific LLM (LLM-RadSum) outperforms GPT-4o in accurately summarizing radiology reports across multiple patient demographics and modalities.
Key Details
- 1LLM-RadSum, based on Llama2, was trained and evaluated on over 1 million CT and MRI radiology reports from five hospitals.
- 2The model achieved higher F1 scores in summarization compared to GPT-4o (0.58 vs. 0.3, p < 0.001), consistent across anatomic regions, modalities, sex, and ages.
- 388.9% of LLM-RadSum's outputs were 'completely consistent' with original reports, versus 43.1% for GPT-4o.
- 481.5% of LLM-RadSum outputs met senior radiologists’ standards for safety and clinical use; most GPT-4o outputs required minor edits.
- 5Human evaluation included 1,800 randomly selected reports, underscoring generalizability within diverse hospital settings.
Why It Matters
This study demonstrates the tangible benefits of local domain adaptation of LLMs in radiology report workflows, setting the stage for safer and more accurate clinical deployment of AI-generated content. It prompts strategic considerations for hospitals about investing in specialty versus general-purpose AI models for radiology.
Source
AuntMinnie
Related News
•HealthExec
New Report Highlights Clinical AI Performance, Sustainability, and Adoption Challenges
A multi-institutional review details key challenges, progress, and sustainability concerns in deploying clinical AI in real-world healthcare settings.
•Cardiovascular Business
FDA Clears AI Platform for Comprehensive Cardiac Risk Assessment on CT
HeartLung Corporation's AI-CVD receives FDA clearance for opportunistic multi-condition screening on routine chest CT scans.
•AuntMinnie
LLM Boosts Terminology Expansion in Radiology Reports Over RadLex
A large language model (LLM) significantly outperforms RadLex in expanding terms for radiology report language standardization.