Ensuring trustworthy AI assisted guideline development for clinical practice
Li et al. introduce Quicker, an agentic large language model system that drafts clinical guideline recommendations through a GRADE-based workflow. Building on gaps in the authors' own evaluation, we propose safeguards for trustworthy use: verifiable, design-aware evidence bundles with explicit scope; calibrated, uncertainty-aware deferral; targeted human validation and modular quality gates; and governance against contamination and over-reliance. Trustworthiness, however, is necessary but not sufficient for clinician trust.
Authors
- Quan Zhang (ORCID: https://orcid.org/0000-0001-9715-4521)
- Yuanyuan Fu (ORCID: https://orcid.org/0000-0001-7715-0558)
Institutions
- University of Hawaiʻi at Mānoa (US)
- Hawaii Department of Health (US)
- University of Hawaii System (US)
- Hawaii Pacific University (US)
- University of Hawaii–West Oahu (US)
- Cancer Center of Hawaii (US)
- Institute for Social and Economic Research (GB)
- University of Hawaii Cancer Center
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2026-08-27
- DOI
- https://doi.org/10.1038/s41746-026-03098-z
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- American Association for Cancer Research
- American Gastroenterological Association
- National Institutes of Health