Karakus, Ibrahim S

Abstract Effective communication in the intensive care unit (ICU) is essential, particularly for patients with non-English language preference, yet timely access to professional interpreters remains limited. While artificial intelligence (AI)-based translation tools have been explored in outpatient and nonacute care settings, studies evaluating their use in acute care, environments such as the ICU remain limited. To address this gap, we developed AI-TransLATE (AI-enhanced Transition to Language-Agnostic Transcultural Engagement), a speech-based translation tool designed for multilingual communication in critical care settings. This study aimed to assess the interpretation quality of AI-TransLATE across four languages—Spanish, Chinese, Arabic, and Turkish—using scripted ICU scenarios. We created ICU communication scripts and recorded bilingual research team members simulating clinical interactions. Two independent bilingual evaluators assessed interpretation quality using a 5-point Likert scale across fluency, adequacy, meaning preservation, and severity of errors. Clarity and cultural appropriateness were also rated. Percentage agreement was used to assess interrater agreement. AI-TransLATE achieved acceptable composite scores (≥16/20) across all languages. Spanish and Turkish performed consistently well; Chinese and Arabic showed variability due to omissions and terminology errors. AI-TransLATE shows promise as a clinical communication tool, but further evaluation in real-world, unscripted ICU settings is needed.

Background: Patients with non-English Language Preference are at risk of adverse health outcomes, particularly at end of life and during serious illness. Medical interpreters often feel unprepared to interpret conversations about serious illness. Best practice guidelines recommend a pre-encounter huddle between clinician and interpreter to better prepare both providers. The CHECK-IN (Check in for Exchange of Clinical and Key Information) guide is a simple communication tool designed to facilitate this pre-encounter huddle. We describe the results of a pilot feasibility study of the CHECK-IN guide performed in a simulation environment. The primary objectives of the study were to evaluate the feasibility, acceptability, and preliminary performance of the CHECK-IN guide. Methods: This U.S.-based study is a single-center simulation-based nonblinded randomized pilot feasibility study. Participating clinicians were randomized to usual practice (control) vs. introduction to the CHECK-IN guide (intervention). Clinicians completed pre- and post-session surveys. Participating clinicians were evaluated using the Faculty Observation Rating Scale (FORS), Interpreter Scale (IS), and Interpreter Impact Rating Scale (IIRS). Results: Participants had a highly favorable opinion on the acceptability, appropriateness, and feasibility of the CHECK-IN tool; 91% of participants agreed/strongly agreed on the acceptability of the tool, 91% agreed/strongly agreed on the appropriateness of the tool, and 100% agreed/strongly agreed on the feasibility of the tool. There were no statistical differences between control and intervention groups for the IS, IIRS, and FORS scores. Conclusion: The CHECK-IN guide is a promising tool to guide a pre-encounter huddle between clinician and interpreter, thereby improving interpreter-mediated communication when having conversations about serious illness.