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

Extraction: Advanced Methods00:56

Extraction: Advanced Methods

446
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...
446
Higher Mental Functions of the Brain: Language01:10

Higher Mental Functions of the Brain: Language

824
Language is a system of communication that allows the expression of thoughts, ideas, and feelings. The brain processes language in both hemispheres.
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
824
Improving Translational Accuracy02:07

Improving Translational Accuracy

2.6K
2.6K
Lagging Strand Synthesis01:59

Lagging Strand Synthesis

13.6K
13.6K
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
lncRNA - Long Non-coding RNAs02:39

lncRNA - Long Non-coding RNAs

2.8K
2.8K

You might also read

Related Articles

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

Sort by
Same author

Leveraging artificial intelligence for evidence synthesis.

JBI evidence synthesis·2026
Same author

Combining Quizartinib with intensive chemotherapy in older patients with newly diagnosed AML: results of the UK NCRI AML18 Trial.

Blood·2026
Same author

Critical time intervention to prevent homelessness and improve health for people leaving prison: the PHaCT pilot RCT.

Public health research (Southampton, England)·2026
Same author

Evaluating search approaches for a network meta-analysis: a case study of Epistemonikos Database of Trials, CENTRAL, and other sources.

BMC medical research methodology·2026
Same author

Decision on Optimal Combinatorial Therapies in Immune-mediated inflammatory diseases using Systems approaches (DocTIS): protocol for a single-arm, adaptive basket trial in rheumatoid and psoriatic arthritis.

Rheumatology advances in practice·2026
Same author

A Model to Assess the Costs and Consequences of Changes in Diet and Nutrition From Potential Population-Wide Policies: The Microsimulation of Nutrition, Diabetes, and Cardiovascular Disease (MONDAC).

Preventing chronic disease·2026

Related Experiment Video

Updated: Jul 1, 2025

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

555

Data extraction for evidence synthesis using a large language model: A proof-of-concept study.

Gerald Gartlehner1,2, Leila Kahwati1, Rainer Hilscher1

  • 1Social, Statistical, and Environmental Sciences, RTI International, Research Triangle Park, North Carolina, USA.

Research Synthesis Methods
|March 3, 2024
PubMed
Summary

Large language models (LLMs) show promise for improving data extraction in evidence synthesis. Claude 2 achieved 96.3% accuracy in extracting data elements from studies, demonstrating high reliability and ease of use.

Keywords:
accuracyartificial intelligencedata extractionevidence synthesislarge language modelsproof of concept

More Related Videos

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

447
Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.2K

Related Experiment Videos

Last Updated: Jul 1, 2025

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

555
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

447
Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.2K

Area of Science:

  • Artificial Intelligence
  • Biomedical Informatics
  • Evidence Synthesis

Background:

  • Data extraction is vital for evidence synthesis but is time-consuming and prone to errors.
  • Previous machine learning efforts have not fully met accuracy and usability needs for data extraction.
  • Large language models (LLMs) present new opportunities to improve data extraction efficiency and accuracy.

Purpose of the Study:

  • To evaluate the performance of a large language model (Claude 2) for data extraction in evidence synthesis.
  • To compare the accuracy and usability of LLM-based data extraction against traditional human extraction methods.
  • To assess the potential of LLMs to enhance the efficiency and accuracy of data extraction for systematic reviews.

Main Methods:

  • A proof-of-concept study using Claude 2 (browser version) for data extraction.
  • Analysis of 10 randomized controlled trial publications from a single systematic review.
  • Extraction of 160 data elements across 16 distinct types from study documents (PDFs).

Main Results:

  • Claude 2 achieved an overall accuracy of 96.3% across 160 data elements.
  • High test-retest reliability was observed (Replication 1: 96.9%, Replication 2: 95.0%).
  • The LLM demonstrated ease of use, requiring no technical expertise or labeled training data (zero-shot learning).

Conclusions:

  • LLMs, exemplified by Claude 2, have significant potential to enhance data extraction efficiency and accuracy in evidence synthesis.
  • The zero-shot learning capability of LLMs reduces barriers to implementation in systematic reviews.
  • Further research can explore broader applications and validation of LLMs in scientific data extraction.