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

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...
Improving Translational Accuracy02:07

Improving Translational Accuracy

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...
Language Development01:22

Language Development

Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...

You might also read

Related Articles

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

Sort by
Same author

Glucagon-Like Peptide-1 Receptor Agonists and Risk of Mental Health Disorders in Type 2 Diabetes: Active Comparator, New User Cohort Study.

Diabetes, obesity & metabolism·2026
Same author

ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.

Journal of biomedical informatics·2026
Same author

Comparative bleeding risk between angiotensin II receptor blockers with high versus low P-glycoprotein inhibitory activity in patients with atrial fibrillation receiving direct oral anticoagulants.

Hypertension research : official journal of the Japanese Society of Hypertension·2026
Same author

Nutritional and biological insights into natural α-glycerylphosphoryl derivatives (α-NGPs): a comprehensive review of α-GPA, α-GPC, α-GPE, α-GPI, and α-GPS.

Critical reviews in food science and nutrition·2026
Same author

Clopidogrel Vs Aspirin Monotherapy for Secondary Prevention After Percutaneous Coronary Intervention: A Nationwide Cohort Study.

JACC. Asia·2026
Same author

Three-dimensional distribution of roadside airborne/tire-wear particles and implications for pedestrian exposure.

Journal of hazardous materials·2026

Related Experiment Video

Updated: Jul 12, 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

From study design to executable code: automating target trial emulation with large language models.

Hanjae Kim1,2,3, Minseong Kim1, Seonji Kim1,2

  • 1Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, Republic of Korea.

JAMIA Open
|July 10, 2026
PubMed
Summary

THESEUS uses large language models to convert health study descriptions into reproducible analytic workflows. This tool enhances standardization and automates code generation for observational research.

Keywords:
OHDSIhuman-in-the-loop AIlarge language modelsreproducibility of resultstarget trial emulation

Related Experiment Videos

Last Updated: Jul 12, 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

Area of Science:

  • Health Informatics
  • Computational Epidemiology
  • Artificial Intelligence in Healthcare

Background:

  • Implementing target trial emulation (TTE) studies requires standardized and reproducible analytic workflows, which are technically challenging.
  • Existing methods for creating these workflows can be complex and time-consuming.

Purpose of the Study:

  • To develop and evaluate the Text-guided Health-study Estimation and Specification Engine Using Strategus (THESEUS).
  • To leverage large language models (LLMs) for translating free-text study descriptions into structured analytic specifications and R scripts within the OHDSI ecosystem.

Main Methods:

  • THESEUS employs a two-step process: an LLM maps study descriptions to a JSON schema, followed by rule-based logic converting specifications into Strategus R scripts.
  • Standardization accuracy was evaluated by comparing specifications generated by 8 LLMs across 15 OHDSI-based and 15 non-OHDSI TTE studies.

Main Results:

  • Under primary analysis, overall standardization accuracy ranged from 0.93-0.97 (OHDSI) and 0.82-0.95 (non-OHDSI).
  • Gemini-3.1-Pro and GPT-5.5 demonstrated high accuracy, with GPT-5.5 excelling at the field level in full-analysis settings.
  • THESEUS was implemented as a web application and coding-agent tools.

Conclusions:

  • THESEUS facilitates the reliable interpretation of study descriptions and deterministic workflow construction in observational research.
  • The system supports the translation of natural language study descriptions into executable and shareable code for standardized observational research.