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 Experiment Videos

Supporting Literature Reviews: A Comparison Between Human and Generative Artificial Intelligence Screening for a

Tami H Wyatt1, Heather Carter-Templeton2, Jordan Wrigley3

  • 1The University of Tennessee, College of Nursing, Knoxville, TN.

Computers, Informatics, Nursing : CIN
|June 23, 2026
PubMed
Summary

Related Concept Videos

Genetic Screens02:46

Genetic Screens

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 result in visible changes...
Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...

You might also read

Related Articles

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

Sort by
Same author

Development and Implementation of the Health Informatics Competency Assessment (HICA): A Pilot Study.

Computers, informatics, nursing : CIN·2026
Same author

Neurocognitive functioning of patients with sickle cell disease in low- and middle-income countries.

Blood global hematology·2026
Same author

Charting the future of ACMI: a report from the 2025 ACMI symposium.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Retractions in Nursing as a Systems Problem: A Journal Systems Framework Perspective.

Journal of nursing scholarship : an official publication of Sigma Theta Tau International Honor Society of Nursing·2026
Same author

Nursing Workforce Sustainability: An Evolutionary Concept Analysis.

The Journal of nursing administration·2026
Same author

The RESILIENT Study: A Retrospective, Descriptive, Correlational Investigation of Correlates of Oral Endocrine Therapy Adherence in Older Women With Breast Cancer.

Cancer medicine·2026

Artificial intelligence (AI) tools can assist in scoping reviews, but human oversight is crucial. While AI speeds up initial screening, it may reduce scholarly engagement and critical appraisal depth.

Area of Science:

  • Bibliometrics
  • Information Science
  • Health Sciences Research

Background:

  • Scoping reviews map literature and identify knowledge gaps but are labor-intensive.
  • Artificial intelligence (AI) tools offer potential efficiencies in systematic review processes.
  • Uncertainty exists regarding AI's accuracy and impact on the rigor of literature reviews.

Purpose of the Study:

  • To compare the effectiveness of ChatGPT 3.5 with human reviewers in title and abstract screening for scoping reviews.
  • To assess the potential time efficiencies and impact on scholarly engagement when using AI in literature screening.

Main Methods:

  • A retrospective cross-sectional agreement design was employed.
  • Title and abstract screening decisions from ChatGPT 3.5 were compared against those of a human research team.
Keywords:
Home care modelLarge language modelsScoping reviewemerging technologies

Related Experiment Videos

  • 3148 articles were screened, with exclusion decisions analyzed for agreement and discrepancies.

    • Main Results:

    • Human reviewers excluded 84.5% of articles during title and abstract screening.
    • ChatGPT 3.5 excluded 48.7% of articles during the same screening phase.
    • AI-assisted screening may filter irrelevant studies but requires careful consideration of human review depth.

    Conclusions:

    • AI tools may offer time savings in scoping reviews by automating initial screening.
    • The efficiencies of AI must be weighed against potential reductions in critical appraisal and scholarly dialogue.
    • Maintaining human involvement is essential for deep comprehension and rigorous evidence synthesis in literature reviews.