Reply to ensuring trustworthy AI assisted guideline development for clinical practice.

Abstract

In this Reply, we respond to the Matters Arising by Zhang and Fu regarding the trustworthiness of AI-assisted clinical guideline development, using Quicker as a case study. We clarify which safeguards for transparency, traceability, and uncertainty handling are already embedded, to a substantial extent, in Quicker's design, and outline areas of alignment on validation, governance, and modular evaluation. We further discuss broader challenges related to trust, safeguards, and responsible deployment of large language model-based systems in evidence-based medicine. We emphasize that advancing such systems requires not only technical acceleration, but also systematic human oversight, rigorous evaluation frameworks, and community-wide governance to ensure safe and trustworthy clinical adoption.