Niven, Alexander

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.

To identify medical phrases utilized by the critical care team that may have an unintended impact on the critically ill patient, we administered an anonymous survey to multi-professional critical care team members. We elicited examples of imprecise language that may have a negative emotional impact on the critically ill. Of the 1600 providers surveyed, 265 offered 1379 examples (912 unique) which were clustered into 5 categories. Medical jargon (eg, “riding the vent”) was most prevalent (n = 549). There were 217 negative suggestions (eg, “you will feel a stick and a burn”). Hyperboles (eg, “black cloud”) were common (n = 198) while homonyms (ie “he fibbed”) accounted for 150 examples. Phrases such as “code brown in there” were categorized as metonyms (n = 144). 121 metaphors/similes (eg, “rearranging deck chairs on the Titanic”) were provided. Phrases that have the potential to negatively impact critically ill patient perceptions are commonplace in critical care practice. Whether these everyday communication habits lead to an unintended nocebo effect on mental health outcomes of the critically ill deserves further study.