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
•Radiology Business
Study Highlights Limitations of AI in Prostate MRI Screening
New research points to several shortcomings in implementing AI for MRI-based prostate cancer screening.
•AuntMinnie
Deep Learning Model Predicts Brain Tumor MRI Enhancement Without Gadolinium
German researchers developed a deep learning approach to predict MRI contrast enhancement in brain tumors without the need for gadolinium-based agents.
•Radiology Business
SimonMed Imaging Introduces Paid AI Add-Ons for Routine Exams
SimonMed Imaging is launching new AI-powered elective services for routine imaging exams with additional out-of-pocket costs for patients.