Answers are grounded in this paper and cite their sources.
This supplement presents a transparent methodological record of an AI-assisted, human-supervised workflow for literature triage, survey drafting, and evidence verification in integrative review articles. The document reports the main protocol structure and representative prompts used to support recurring tasks, but it is not a complete transcript of all searches, AI interactions, deep-research cycles, manual reading, or author-led revisions. The workflow combines conventional scholarly practices with selective use of LLMs for organizing candidate sources, stress-testing conceptual frameworks, drafting and revising survey paragraphs, and conducting citation-support and quality-assurance checks. It is structured into four phases---Ideation & Scoping, Framework Evaluation, Paragraph Writing & Editing, and Verification & Quality Assurance---with selected prompts and gate criteria provided in the appendix for auditability. LLMs are used as assistive tools only; all sources, claims, interpretations, citations, and final manuscript text must be reviewed, verified, and approved by the human author(s), who retain full responsibility for the work.
No takes yet. Share an insight, caveat, or question.
Marcin Mirończuk (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: