L-PRISMA: An Extension of PRISMA in the Era of Generative Artificial Intelligence (GenAI)
For researchers conducting systematic reviews, this provides a responsible method to incorporate GenAI without sacrificing core PRISMA principles.
This paper extends the PRISMA framework for systematic reviews by integrating a GenAI-assisted statistical pre-screening step with human oversight, aiming to improve efficiency while maintaining reproducibility and transparency. The approach addresses challenges of LLM non-determinism and hallucination.
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.