Analysis of technical nonconformities in health systems with LLMs: an interdisciplinary scoping review protocol

This scoping review protocol outlines a methodological approach to investigate how Artificial Intelligence (AI), particularly Large Language Models (LLMs), is employed to support regulatory compliance and software quality within medical systems. The development of healthcare software requires strict adherence to complex global regulations (such as IEC 62304, FDA guidelines, and LGPD), making manual validation processes costly and time-consuming. Following the Joanna Briggs Institute (JBI) framework , this study will systematically search four major databases (IEEE Xplore, PubMed, Scopus, and Web of Science). The objective is to map current literature, identify existing AI-driven tools for source code and requirements analysis, and pinpoint knowledge gaps. Ultimately, this review aims to provide a scientific foundation for developing new solutions that mitigate regulatory bottlenecks and ensure patient safety during the medical software development lifecycle