Operationalizing machine-assisted translation in healthcare

Abstract

Over 25 million U.S. patients with a non-English language preference face unsafe care because discharge instructions and other materials are rarely translated in time. Advances in translation assisted by large language models can close this gap, but implementation guidance is scarce. Using the Consolidated Framework for Implementation Research, we outline key considerations-innovation, individuals, inner setting, implementation process, and outer setting-to offer healthcare leaders and policymakers a practical roadmap for language model machine-assisted translation integration.

Topics & Concepts