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

Data Collection I01:30

Data Collection I

7.7K
Data collection gathers information needed to make accurate judgments about a patient's present condition. During a health history interview, subjective data is collected from the patient, their caregivers, or family members, and objective data is collected through observations and physical assessment. Patients are the primary source of subjective data. Thus information gathered from patients through interviews, observations, and physical examination is primary data. Secondary sources of...
7.7K
Data Validation01:03

Data Validation

6.3K
Data validation is an essential part of a comprehensive assessment. Validation is confirming or verifying and opening the door to gathering more assessment data as it clarifies vague or unclear data. The process of checking and verifying the collected information is called data validation. The primary purpose of data validation is to ensure data is as free from error, bias, and misinterpretation as possible.
Nursing assessment guides are generally based on holistic models rather than medical...
6.3K
Genetic Screens02:46

Genetic Screens

5.5K
Genetic screens are tools used to identify genes and mutations responsible for phenotypes of interest. Genetic screens help identify individuals or a group of people at risk of developing  genetic diseases and help them with early intervention, targeted therapy, and reproductive options.
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which...
5.5K

You might also read

Related Articles

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

Sort by
Same author

Neural Networks or Linguistic Features? - Comparing Different Machine-Learning Approaches for Automated Assessment of Text Quality Traits Among L1- and L2-Learners' Argumentative Essays.

International journal of artificial intelligence in education·2025
Same author

Who am I? A second-order meta-analytic review of correlates of the self in childhood and adolescence.

Psychological bulletin·2024
Same author

A closer look at the domain-specific associations of openness with language achievement: Evidence on the role of intrinsic value from two large-scale longitudinal studies.

The British journal of educational psychology·2022
Same author

New wine in an old bottle? A facet-level perspective on the added value of Grit over BFI-2 Conscientiousness.

PloS one·2020

Related Experiment Video

Updated: Jan 7, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.2K

Data extraction by generative artificial intelligence: Assessing determinants of accuracy using human-extracted data

Thorben Jansen1, Lucas W Liebenow1, Ute Mertens1

  • 1Leibniz Institute for Science and Mathematics Education, Kiel University.

Psychological Bulletin
|December 15, 2025
PubMed
Summary
This summary is machine-generated.

Generative artificial intelligence (genAI) shows potential for accelerating psychological data extraction in systematic reviews, but accuracy varies significantly across variables and requires careful human oversight.

More Related Videos

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

16.4K

Related Experiment Videos

Last Updated: Jan 7, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.2K
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

16.4K

Area of Science:

  • Psychological Science
  • Artificial Intelligence in Research

Background:

  • Systematic literature reviews in psychology rely on accurate data extraction for reliability.
  • Current data extraction methods are time-consuming, hindering research efficiency.
  • Generative artificial intelligence (genAI), specifically large language models (LLMs), has shown promise in medical data extraction.

Purpose of the Study:

  • To systematically assess the accuracy and error patterns of genAI for data extraction across various psychological domains.
  • To compare genAI-extracted data with human-extracted data in psychological systematic reviews.
  • To identify factors influencing genAI extraction accuracy in psychological research.

Main Methods:

  • Compared genAI-extracted data with human-extracted data from 2,179 studies across 22 systematic review databases.
  • Utilized eight different large language models (LLMs) for data extraction.
  • Analyzed extraction accuracy and error patterns for 186 variables.

Main Results:

  • LLM extraction accuracy was unacceptable for 20% of variables and acceptable but not high for 15%.
  • Accuracy varied most by variable, followed by systematic review, and least by LLM.
  • Higher accuracy was observed for context/moderator variables compared to effect size variables.
  • Extraction accuracy positively correlated with variable description detail and LLM size.

Conclusions:

  • GenAI demonstrates potential to accelerate data extraction in psychological systematic reviews, but current accuracy is variable.
  • Accuracy is influenced by the type of variable, detail in descriptions, and LLM capabilities.
  • Further research is needed to optimize genAI use while maintaining human control for reliable psychological research.