The AI-augmented researcher: Optimizing systematic reviews in ergonomics

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.