Artificial Intelligence Applications Versus Manual Methods For Literature Retrieval: A Comparative Analysis
Western Journal of Nursing Research · 2026-08 · 48 (8) · 887-894
DOI: 10.1177/01939459261451723 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Western Journal of Nursing Research, online erschienen am 10.06.2026. Verfasst von Jenny O'Rourke und 2 weiteren Autor:innen. Beteiligte Einrichtung: Parkinson School of Health Sciences and Public Health, Loyola University Chicago, IL, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Information Storage and Retrieval. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben.
Abstract (Originalsprache)
Background
Artificial intelligence (AI), particularly generative and large language models, is being used in nursing education, practice, and scholarly writing. Generative AI applications have been specifically examined for their use in conducting literature reviews with evidence supporting reduced production time of scholarly work. However, there has been limited investigation of their levels of accuracy with identifying references for a literature review.
Objective
The purpose of this study was to compare human-generated citations of literature reviews with AI literature-review generated citations.
Methods
Using a comparative exploratory design, references from 4 human-written literature reviews, 2 published and 2 unpublished, on 4 different topics, were compared to references derived from 2 AI literature applications, Consensus and Elicit. Three prompting strategies were utilized, including prompts generated using ChatGPT-4. Agreement between the AI and human references was evaluated.
Results
The percent of agreement between AI and human generated reference lists ranged from 0% to 63.6%. The Consensus application had a greater overall mean rate of match (21.3%) as compared to Elicit (3.7%). The use of a ChatGPT-4 prompt did not significantly impact results, and there were no differences based on published or unpublished literature reviews.
Conclusion
The 2 literature-based applications examined in this study offered a glimpse of their potential use and limitations. The use of an AI literature review application may support but not replace human work.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Parkinson School of Health Sciences and Public Health, Loyola University Chicago, IL, USA.
- Mayo Clinic-Office of the Chief Technology Officer, Rochester, MN, USA.
- Marcella Niehoff School of Nursing, Loyola University Chicago, IL, USA.
ORCID-Profile: Jenny O'Rourke, Ginger Schroers
Zitieren
APA
O'Rourke, J., Byrne, M., & Schroers, G. (2026). Artificial Intelligence Applications Versus Manual Methods For Literature Retrieval: A Comparative Analysis. Western Journal of Nursing Research, 48(8), 887-894. https://doi.org/10.1177/01939459261451723
Vancouver
O'Rourke J, Byrne M, Schroers G. Artificial Intelligence Applications Versus Manual Methods For Literature Retrieval: A Comparative Analysis. Western Journal of Nursing Research. 2026;48(8):887-894. doi:10.1177/01939459261451723
BibTeX
@article{ORourke2026,
author = {O'Rourke, Jenny and Byrne, Matthew and Schroers, Ginger},
title = {Artificial Intelligence Applications Versus Manual Methods For Literature Retrieval: A Comparative Analysis},
journal = {Western Journal of Nursing Research},
year = {2026},
volume = {48},
number = {8},
pages = {887--894},
doi = {10.1177/01939459261451723}
}
EUVIMED