Toward reviewable medical evidence synthesis for care delivery
Abstract Large language model systems can retrieve and cite medical evidence, yet their outputs may remain difficult to review during care. We define reviewability through evidence adequacy for action-changing claims, exact source verification, and presentation matched to a specified reviewer and decision point. We propose a workflow-adaptive framework with a stable audit core, claim-specific stopping and escalation, and technical and human-factors evaluation.
Authors
- Zonghai Yao (ORCID: https://orcid.org/0000-0002-5707-8410)
- Hong Yu
Institutions
- University of Massachusetts Lowell (US)
- University of Massachusetts Amherst (US)
- Bedford VA Research Corporation (US)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2026-09-19
- DOI
- https://doi.org/10.1038/s41746-026-03195-z
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00