EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access

AI-TransLATE: Validation of a Speech-Based Multilingual Interpretation Tool in Critical Care

Ibrahim S Karakus, Shashank Gupta, Rana Gur, Marco A Bracamonte Aranibar, Abdelhamed Elgazar, Hossam Gad, Xuechao Hao, Fabio Morales Salas, Sude Kilickaya, Alexander Niven, Oguz Kilickaya, Amelia Barwise

Applied Clinical Informatics · 01.10.2025 · 16 (05) · 1917-1924

DOI: 10.1055/a-2771-6216 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Applied Clinical Informatics, erschienen am 01.10.2025. Verfasst von Ibrahim S Karakus und 11 weiteren Autor:innen. Beteiligte Einrichtung: Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, Minnesota, United States. Hauptthemen laut MEDLINE: Multilingualism, Critical Care, Translating, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: The Critical Care Research Committee Mayo Clinic, NCATS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MultilingualismCritical CareTranslatingArtificial IntelligenceSpeechHumansIntensive Care Units

Autor:innen und Institutionen

  • Division of Pulmonary and Critical Care Medicine, Mayo Clinic, Rochester, Minnesota, United States.
  • Department of Anesthesiology and Perioperative Medicine, Rochester, Minnesota, United States.
  • Department of Emergency Medicine, Mayo Clinic, Rochester, Minnesota, United States.
  • Department of Biomedical Engineering, University of Minnesota, Twin Cities, Minnesota, United States.
  • Division of Biomedical Ethics, Rochester, Department of Quantitative Health Science, Minnesota, United States.

Förderung

  • The Critical Care Research Committee Mayo Clinic
  • NCATS NIH HHS

Zitieren

APA

Karakus, I. S., Gupta, S., Gur, R., Bracamonte Aranibar, M. A., Elgazar, A., Gad, H., Hao, X., Morales Salas, F., Kilickaya, S., Niven, A., Kilickaya, O., & Barwise, A. (2025). AI-TransLATE: Validation of a Speech-Based Multilingual Interpretation Tool in Critical Care. Applied Clinical Informatics, 16(05), 1917-1924. https://doi.org/10.1055/a-2771-6216

Vancouver

Karakus IS, Gupta S, Gur R, Bracamonte Aranibar MA, Elgazar A, Gad H, et al. AI-TransLATE: Validation of a Speech-Based Multilingual Interpretation Tool in Critical Care. Applied Clinical Informatics. 2025;16(05):1917-1924. doi:10.1055/a-2771-6216

BibTeX
@article{Karakus2025,
  author = {Karakus, Ibrahim S and Gupta, Shashank and Gur, Rana and Bracamonte Aranibar, Marco A and Elgazar, Abdelhamed and Gad, Hossam and Hao, Xuechao and Morales Salas, Fabio and Kilickaya, Sude and Niven, Alexander and Kilickaya, Oguz and Barwise, Amelia},
  title = {AI-TransLATE: Validation of a Speech-Based Multilingual Interpretation Tool in Critical Care},
  journal = {Applied Clinical Informatics},
  year = {2025},
  volume = {16},
  number = {05},
  pages = {1917--1924},
  doi = {10.1055/a-2771-6216}
}
Kostenlos starten →