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 Concept Videos

Improving Translational Accuracy02:07

Improving Translational Accuracy

3.7K
3.7K
Improving Translational Accuracy02:07

Improving Translational Accuracy

15.3K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
15.3K

You might also read

Related Articles

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

Sort by
Same author

TRPV1 Agonist Capsaicin Enhances Oxidative-Stress Resistance and Regeneration in Dorsal Root Ganglia and Schwann Cells.

Cells·2026
Same author

Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL-Based Cortical Thickness Estimates.

Human brain mapping·2026
Same author

Virtual reality-based oculography detects internuclear ophthalmoplegia in multiple sclerosis and other neurological disorders.

Journal of neurology·2026
Same author

Sex-specific analysis of early disease course and treatment in a German multiple sclerosis cohort.

Multiple sclerosis (Houndmills, Basingstoke, England)·2026
Same author

Incidence of multiple sclerosis in Switzerland - results from the Swiss multiple sclerosis registry.

Multiple sclerosis and related disorders·2026
Same author

Sex-Specific Differences in Amino Acids and Neurotransmitters in Multiple Sclerosis Patients Compared to Non-Neuroinflammatory Controls: A Retrospective Case-Control Study.

Neurochemical research·2026

Related Experiment Video

Updated: Mar 3, 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

1.3K

Improving reliability and accuracy of structured data extraction using a consensus large-language model approach-a

Philip Lennart Poser1, Rafael Klimas1, Justus Luerweg1

  • 1Department of Neurology, St. Josef-Hospital, Ruhr-University Bochum, Bochum, Germany.

Frontiers in Artificial Intelligence
|March 2, 2026
PubMed
Summary

Large language models (LLMs) can now analyze clinical reports for Multiple Sclerosis (MS) research. A consensus approach using LLMs achieved accuracy comparable to human specialists, enabling efficient data analysis.

Keywords:
data extractionlarge language modelmultiple sclerosisneurologyreal world evidencestructured data

More Related Videos

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
10:46

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

Published on: December 9, 2015

11.2K
Author Spotlight: Creating a Versatile Experimental Autoimmune Encephalomyelitis Model Relevant for Both Male and Female Mice
05:44

Author Spotlight: Creating a Versatile Experimental Autoimmune Encephalomyelitis Model Relevant for Both Male and Female Mice

Published on: October 13, 2023

2.5K

Related Experiment Videos

Last Updated: Mar 3, 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

1.3K
A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
10:46

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

Published on: December 9, 2015

11.2K
Author Spotlight: Creating a Versatile Experimental Autoimmune Encephalomyelitis Model Relevant for Both Male and Female Mice
05:44

Author Spotlight: Creating a Versatile Experimental Autoimmune Encephalomyelitis Model Relevant for Both Male and Female Mice

Published on: October 13, 2023

2.5K

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Clinical Data Management

Background:

  • Standardization of clinical data documentation is lacking, hindering large-scale retrospective research.
  • Manual data extraction is time-consuming, costly, and prone to bias.
  • A semi-automated approach using large-language models (LLMs) was developed to address these challenges in Multiple Sclerosis (MS) outpatient reports.

Purpose of the Study:

  • To develop and evaluate a semi-automated method for extracting structured data from MS outpatient reports using LLMs.
  • To compare the accuracy of LLM-generated data with manual evaluation by neurology specialists.
  • To assess the effectiveness of an LLM consensus approach in improving data extraction quality.

Main Methods:

  • Utilized commercial LLMs (OpenAI, Anthropic, Google) for zero-shot learning on 30 anonymized MS outpatient reports.
  • Implemented an LLM consensus mechanism by combining outputs from three different models.
  • Iteratively refined prompts over several runs and assessed error rates against a reference standard.
  • Calculated true-error rates for both LLM consensus and neurologist outputs, considering only content deviations.

Main Results:

  • Prompt engineering iterations led to a significant reduction in LLM error rates.
  • The LLM consensus approach overcame performance ceilings observed with individual LLMs.
  • The LLM consensus achieved a true-error rate of 1.48%, comparable to that of neurology specialists (approx. 2%).

Conclusions:

  • The developed LLM-based method offers a fast, reliable, and accessible way to analyze large volumes of unstructured clinical data.
  • LLM consensus significantly enhances output quality, making it comparable to expert manual data creation.
  • While promising for time and cost efficiency, rigorous validation of LLM-based methods in scientific research remains crucial.