LLaMA 3.1 extracts data from Dutch brain MRI reports

Researchers utilized the open-weight LLaMA 3.1 large language model to automatically extract structured information from 947 Dutch brain MRI reports. The model demonstrated high performance in identifying visual rating scores for atrophy and lesion mentions, achieving over 90% accuracy for several categories. While zero-shot performance was strong for categorical data, few-shot prompting significantly improved accuracy for numerical variables like microbleed and infarct counts, suggesting LLaMA 3.1's potential for large-scale medical research. AI

IMPACT Demonstrates LLM capabilities in specialized medical data extraction, potentially accelerating research and clinical insights.

RANK_REASON Academic paper detailing the application of an LLM to a specific domain. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• LLaMA 3.1

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →