Related Experiment Video
Updated: Jun 26, 2025
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Performance of an Open-Source Large Language Model in Extracting Information from Free-Text Radiology Reports
Bastien Le Guellec1, Alexandre Lefèvre1, Charlotte Geay1
1From the Department of Neuroradiology (B.L.G., A.L., C.B., J.P.P., G.K.), Department of Public Health (B.L.G., P.A., A.H.), and INclude Health Data Warehouse (C.G., L.S.), CHU Lille-Université Lille, Rue Emile Laine, 59000 Lille, France; Department of Radiology, UC Davis Health, Sacramento, Calif (L.H.B.); Université Lille, INSERM, CHU Lille, Institut Pasteur de Lille, U1167-RID-AGE - Facteurs de risque et déterminants moléculaires des maladies liées au vieillissement, Lille, France (P.A., A.H.); INSERM, U1172-LilNCog-Lille Neuroscience & Cognition, Université Lille, Lille, France (J.P.P., G.K.); and UAR 2014-US 41-PLBS-Plateformes Lilloises en Biologie & Santé, Université Lille, Lille, France (J.P.P., G.K.).
Abstract:
Purpose To assess the performance of a local open-source large language model (LLM) in various information extraction tasks from real-life emergency brain MRI reports. Materials and Methods All consecutive emergency brain MRI reports written in 2022 from a French quaternary center were retrospectively reviewed. Two radiologists identified MRI scans that were performed in the emergency department for headaches. Four radiologists scored the reports' conclusions as either normal or abnormal. Abnormalities were labeled as either headache-causing or incidental. Vicuna (LMSYS Org), an open-source LLM, performed the same tasks. Vicuna's performance metrics were evaluated using the radiologists' consensus as the reference standard. Results Among the 2398 reports during the study period, radiologists identified 595 that included headaches in the indication (median age of patients, 35 years [IQR, 26-51 years]; 68% [403 of 595] women). A positive finding was reported in 227 of 595 (38%) cases, 136 of which could explain the headache. The LLM had a sensitivity of 98.0% (95% CI: 96.5, 99.0) and specificity of 99.3% (95% CI: 98.8, 99.7) for detecting the presence of headache in the clinical context, a sensitivity of 99.4% (95% CI: 98.3, 99.9) and specificity of 98.6% (95% CI: 92.2, 100.0) for the use of contrast medium injection, a sensitivity of 96.0% (95% CI: 92.5, 98.2) and specificity of 98.9% (95% CI: 97.2, 99.7) for study categorization as either normal or abnormal, and a sensitivity of 88.2% (95% CI: 81.6, 93.1) and specificity of 73% (95% CI: 62, 81) for causal inference between MRI findings and headache. Conclusion An open-source LLM was able to extract information from free-text radiology reports with excellent accuracy without requiring further training. Keywords: Large Language Model (LLM), Generative Pretrained Transformers (GPT), Open Source, Information Extraction, Report, Brain, MRI Supplemental material is available for this article. Published under a CC BY 4.0 license. See also the commentary by Akinci D'Antonoli and Bluethgen in this issue.
