Related Experiment Video
Updated: Jun 18, 2025
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Evaluating local open-source large language models for data extraction from unstructured reports on mechanical
Aymen Meddeb1,2, Philipe Ebert3, Keno Kyrill Bressem4
1Department of Neuroradiology, Charité Universitätsmedizin Berlin, Berlin, Germany aymen.meddeb@charite.de.
Background:
A study was undertaken to assess the effectiveness of open-source large language models (LLMs) in extracting clinical data from unstructured mechanical thrombectomy reports in patients with ischemic stroke caused by a vessel occlusion.
Methods:
We deployed local open-source LLMs to extract data points from free-text procedural reports in patients who underwent mechanical thrombectomy between September 2020 and June 2023 in our institution. The external dataset was obtained from a second university hospital and comprised consecutive cases treated between September 2023 and March 2024. Ground truth labeling was facilitated by a human-in-the-loop (HITL) approach, with time metrics recorded for both automated and manual data extractions. We tested three models-Mixtral, Qwen, and BioMistral-assessing their performance on precision, recall, and F1 score across 15 clinical categories such as National Institute of Health Stroke Scale (NIHSS) scores, occluded vessels, and medication details.
Results:
The study included 1000 consecutive reports from our primary institution and 50 reports from a secondary institution. Mixtral showed the highest precision, achieving 0.99 for first series time extraction and 0.69 for occluded vessel identification within the internal dataset. In the external dataset, precision ranged from 1.00 for NIHSS scores to 0.70 for occluded vessels. Qwen showed moderate precision with a high of 0.85 for NIHSS scores and a low of 0.28 for occluded vessels. BioMistral had the broadest range of precision, from 0.81 for first series times to 0.14 for medication details. The HITL approach yielded an average time savings of 65.6% per case, with variations from 45.95% to 79.56%.
Conclusion:
This study highlights the potential of using LLMs for automated clinical data extraction from medical reports. Incorporating HITL annotations enhances precision and also ensures the reliability of the extracted data. This methodology presents a scalable privacy-preserving option that can significantly support clinical documentation and research endeavors.
