The AI-augmented researcher: Optimizing systematic reviews in ergonomics.

Authors

David Ernesto Puentes-Lagos, Karen Lange-Morales, Aida Josefina Rojas-Fajardo

Published in

Work (Reading, Mass.). Pages 10519815261478123. Oct 16, 2026. Epub Oct 16, 2026.

Abstract

BackgroundThe emergence of Academic Artificial Intelligence (AAI) agents is reshaping Systematic Literature Reviews (SLR) by expanding evidence screening and synthesis beyond Boolean, metadata-based searches, but its use requires a clear, PRISMA-aligned human oversight model to avoid compromising research integrity.ObjectiveThis opinion article proposes the "AI-augmented researcher" as a multidimensional framework that synergizes human analytical rigor with Large Language Models (LLMs). Using a physical ergonomics case study, the paper establishes a normative integration strategy that demonstrates how AAI can accelerate evidence synthesis while maintaining strict PRISMA compliance under explicit human oversight.MethodologyA Workflow Comparative Analysis (WCA) applying a parallel-group design to physical ergonomics SLR. The procedure synchronized two approaches: 1) A "classical" SLR workflow, using Boolean syntax and paratextual screening (Metadata) across indexed databases; and 2) An AAI-driven workflow, utilizing LLM-based immersion via natural language prompting. Comparative metrics analyzed included execution time, record processing volume, and the identification of emerging trends-such as Ergonomics 4.0-benchmarked against the PRISMA 2020 protocol.ResultsThe AAI-augmented workflow reduced execution time by 96% (39 h to 1.5 h) while increasing record processing by 370%. Qualitatively, iterative prompting fostered a "hermeneutic dialogue," enabling the detection of complex "Ergonomics 4.0" trends obscured in syntactic searches.ConclusionsAAI serves as a cognitive enhancer, reconfiguring the researcher from a "data miner" to an "evidence curator". While efficiency is optimized, strict human oversight remains indispensable to mitigate algorithmic hallucinations and ensure ethical scientific integrity.

PMID:
42885447
Bibliographic data and abstract were imported from PubMed on 16 Oct 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.