L-PRISMA: An Extension of PRISMA in the Era of Generative Artificial Intelligence (GenAI)

TL;DR

This paper proposes an extension to the PRISMA framework by integrating Generative AI with human oversight to improve efficiency in systematic reviews while maintaining transparency and reproducibility.

Contribution

It introduces a hybrid approach combining GenAI automation with human oversight, addressing PRISMA principles in the context of AI-driven evidence synthesis.

Findings

Enhanced efficiency in literature screening and data extraction.

Maintained transparency and reproducibility through human oversight.

Addressed AI-related biases and hallucinations in systematic reviews.

Abstract

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework provides a rigorous foundation for evidence synthesis, yet the manual processes of data extraction and literature screening remain time-consuming and restrictive. Recent advances in Generative Artificial Intelligence (GenAI), particularly large language models (LLMs), offer opportunities to automate and scale these tasks, thereby improving time and efficiency. However, reproducibility, transparency, and auditability, the core PRISMA principles, are being challenged by the inherent non-determinism of LLMs and the risks of hallucination and bias amplification. To address these limitations, this study integrates human-led synthesis with a GenAI-assisted statistical pre-screening step. Human oversight ensures scientific validity and transparency, while the deterministic nature of the statistical layer enhances reproducibility. The proposed approach systematically enhances PRISMA guidelines, providing a responsible pathway for incorporating GenAI into systematic review workflows.