Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 5, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.2K

Large Language Models for Accurate Medical Chart Abstraction: Enabling Scalable and Secure AI Deployment in Stroke.

Zhusi Zhong1, Carl M Porto1, David Hong1

  • 1From the Warren Alpert Medical School of Brown University (Z.Z., C.M.P, M.G., R.K., G.K., L.B., J.R.F., E.S., S.C., L.S., G.B., M.J., S.Y., Z.J., D.N.W.), Department of Radiology (Z.Z., G.B., M.J., Z.J.), Brown University Health, Department of Interventional Radiology (D.N.W.), Brown University Health, Department of Neurosurgery (J.R.F.), Brown University Health, Providence 02903, USA.

AJNR. American Journal of Neuroradiology
|February 20, 2026
PubMed
Summary

Related Concept Videos

Brain Imaging01:14

Brain Imaging

1.0K
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans),  magnetic resonance imaging (MRI),  functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
1.0K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Role of Perfusion Parameters on Outcomes and Safety of Endovascular Therapy in Posterior Cerebral Artery Stroke.

Stroke·2026
Same author

International survey on the management of cervical artery dissection: assessing consensus and variability in practice.

Journal of thrombosis and thrombolysis·2026
Same author

KRAS inhibition is an effective therapy for appendiceal adenocarcinoma.

Journal of hematology & oncology·2026
Same author

Impact of Readmission Hospital Site on Outcomes in Patients With Intracerebral Hemorrhage Undergoing Surgery: A Nationwide Cohort Study.

Journal of the American Heart Association·2026
Same author

Press releases in neurosurgery: is scientific accuracy compromised in public reporting of neurosurgery research?

Journal of neurosurgery·2026
Same author

Revisiting Predicted Age of Disease Onset in a Korean Kindred with the Transthyretin Asp38Val Variant.

Korean circulation journal·2026

Large language models (LLMs) can accurately extract clinical data from neurointerventional stroke reports. This AI approach aids research by structuring complex medical information efficiently.

Area of Science:

  • Artificial Intelligence
  • Medical Informatics
  • Neurointerventional Radiology

Background:

  • Medical chart abstraction is vital for clinical research and quality monitoring.
  • Unstructured procedure reports hinder large-scale analysis of clinical data.

Purpose of the Study:

  • To develop and evaluate a prompting-based large language model (LLM) framework.
  • Automate extraction of structured clinical variables from neurointerventional procedure reports for acute ischemic stroke (AIS) patients with large-vessel occlusions (LVO).

Main Methods:

  • Retrospective analysis of 2,416 neurointerventional thrombectomy reports.
  • Evaluation of 22 instruction-tuned LLMs using Quick Response and Chain-of-Thought (CoT) prompting strategies.
  • Benchmarking against non-expert staff annotations and medical expert ratings for accuracy and agreement.

Related Experiment Videos

Last Updated: May 5, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.2K

Main Results:

  • LLaMA3.3-70B achieved 94.8% accuracy, outperforming non-expert annotations.
  • CoT prompting enhanced inferential variable extraction; Quick Response excelled for direct procedural fields.
  • AI predictions aligned better with expert interpretations than non-expert staff, especially for structured variables.

Conclusions:

  • Prompted LLMs can accurately and scalably extract critical clinical information from neurovascular radiology reports.
  • This framework supports integration into retrospective research and automated stroke registry curation without custom preprocessing.