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

Systematic Sampling Method01:17

Systematic Sampling Method

10.3K
Sampling is a technique to select a portion (or subset) of the larger population and study that portion (the sample) to gain information about the population. Data are the result of sampling from a population. The sampling method ensures that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
Systematic sampling is one of the simplest methods...
10.3K
Extraction: Advanced Methods00:56

Extraction: Advanced Methods

1.2K
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
1.2K

You might also read

Related Articles

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

Sort by
Same author

Advancing the Oncology Data Paradigm: Multisite Expansion of Structured Cancer Data Capture at the Point of Care.

JCO oncology practice·2026
Same author

Structured reasoning failures compromise LLM interpretation of clinical oncology notes.

NPJ digital medicine·2026
Same author

Bone-Modifying Agents in Metastatic Castration-Resistant Prostate Cancer.

JAMA network open·2026
Same author

Reply to: Prostate-Specific Membrane Antigen Positron Emission Tomography and Radiometabolic Therapies in Metastatic Castration-Resistant Prostate Cancer.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2026
Same author

Impact of Race, Socioeconomic Status, and Clinicopathologic Features on Clinical Outcomes in Triple-Negative Breast Cancer in the ECOG-ACRIN EA1131 Trial.

JCO oncology advances·2026
Same author

Dynamic-EASIX DRI Model: A Novel Tool for Predicting Outcomes After Allogeneic Hematopoietic Cell Transplantation.

Transplantation and cellular therapy·2026

Related Experiment Video

Updated: Apr 24, 2026

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.8K

Collaborative large language models for automated data extraction in living systematic reviews.

Muhammad Ali Khan1, Umair Ayub1, Syed Arsalan Ahmed Naqvi1

  • 1Department of Medicine, Mayo Clinic, Phoenix, AZ, 85054, United States.

Journal of the American Medical Informatics Association : JAMIA
|January 21, 2025
PubMed
Summary

Automated data extraction using large language models (LLMs) in a simulated two-reviewer process shows promise for living systematic reviews. Cross-critique of discordant responses significantly improves accuracy.

Keywords:
data extractionlarge language modelsmeta-analysisnatural language processingsystematic review

More Related Videos

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
08:53

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community

Published on: May 31, 2019

5.1K
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

484

Related Experiment Videos

Last Updated: Apr 24, 2026

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.8K
Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
08:53

Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community

Published on: May 31, 2019

5.1K
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

484

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Systematic Review Methodology

Background:

  • Data extraction is a time-consuming bottleneck in conducting living systematic reviews (LSRs).
  • Automating this process is crucial for efficient and up-to-date evidence synthesis.

Purpose of the Study:

  • To develop and evaluate a generalizable, automated data extraction workflow using large language models (LLMs).
  • To mimic the real-world two-reviewer process for enhanced accuracy in data extraction for LSRs.

Main Methods:

  • Utilized a dataset of 22 publications from a published LSR, focusing on 23 key variables.
  • Employed GPT-4-turbo and Claude-3-Opus for data extraction, simulating a two-reviewer workflow with cross-critique for discordant responses.
  • Assessed performance using accuracy metrics against a gold standard.

Main Results:

  • High concordance (96%) and accuracy (0.99) were observed in the prompt development set.
  • In the held-out test set, 87% of responses were concordant with 0.94 accuracy.
  • Cross-critique resolved 51% of discordant responses, increasing their accuracy to 0.76.

Conclusions:

  • Concordant LLM responses are generally accurate, and cross-critique effectively improves accuracy for discordant extractions.
  • LLM-driven, simulated two-reviewer workflows offer a viable approach for efficient data extraction, enabling the feasibility of truly living systematic reviews.