ArticleClinical neuroradiology2025
Llama 3.1 405B Is Comparable to GPT-4 for Extraction of Data from Thrombectomy Reports-A Step Towards Secure Data Extraction.
Article in Clinical neuroradiology, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
2 citing papers in PubMed.
- Reply to the Letter to the Editor: Blind spots in radiology leadership regarding human resources and organization management in the era of artificial intelligence.European radiology · 2026Article
- Systematic Review of Large Language Models and Natural Language Processing in Stroke Care: Applications, Challenges, and Future Directions.Stroke (Hoboken, N.J.) · 2026Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
10 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
purposeGPT‑4 has been shown to correctly extract procedural details from free-text reports on mechanical thrombectomy. However, GPT may not be suitable for analyzing reports containing personal data. The purpose of this study was to evaluate the ability of the large language models (LLM) Llama3.1 405B, Llama3 70B, Llama3 8B, and Mixtral 8X7B, that can be operated offline, to extract procedural details from free-text reports on mechanical thrombectomies.
methodsFree-text reports on mechanical thrombectomy from two institutions were included. A detailed prompt was used in German and English languages. The ability of the LLMs to extract procedural data was compared to GPT‑4 using McNemar's test. The manual data entries made by an interventional neuroradiologist served as the reference standard.
results100 reports from institution 1 (mean age 74.7 ± 13.2 years; 53 females) and 30 reports from institution 2 (mean age 72.7 ± 13.5 years; 18 males) were included. Llama 3.1 405B extracted 2619 of 2800 data points correctly (93.5% [95%CI: 92.6%, 94.4%], p = 0.39 vs. GPT-4). Llama3 70B with the English prompt extracted 2537 data points correctly (90.6% [95%CI: 89.5%, 91.7%], p < 0.001 vs. GPT-4), and 2471 (88.2% [95%CI: 87.0%, 89.4%], p < 0.001 vs. GPT-4) with the German prompt. Llama 3 8B extracted 2314 data points correctly (86.1% [95%CI: 84.8%, 87.4%], p < 0.001 vs. GPT-4), and Mixtral 8X7B extracted 2411 (86.1% [95%CI: 84.8%, 87.4%], p < 0.001 vs. GPT-4) correctly.
conclusionLlama 3.1 405B was equal to GPT‑4 for data extraction from free-text reports on mechanical thrombectomies and may represent a data secure alternative, when operated locally.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.