Karakus, Serhat

Abstract Rationale Clear and accurate communication is essential in critical care, yet patients with non-English language preferences (NELP) often face limited access to professional interpreters. Although machine translation has been explored in healthcare, most studies have focused on written translation. Their use in real-time, two-way interpretation specifically for high-stakes ICU conversations remains largely unexamined. To bridge this gap, we developed AI-TransLATE (AI-enhanced Transition to Language-Agnostic Transcultural Engagement), a voice-to-voice multilingual interpretation tool designed to support real-time interactions in critical care. Following successful initial validation, we evaluated clinicians’ perceptions of its usability in simulated ICU encounters and compared its performance with commercially available AI tools, including Gemini and ChatGPT. Methods We developed three standardized ICU role-play scenarios focused on shared decision-making regarding ECMO, tracheostomy, and comfort care, designed to encourage natural, unscripted dialogue. Clinicians were asked to use the AI translation tools during these encounters in Spanish, Chinese, or Arabic, while a bilingual research team member acted as the patient’s family member. After each simulation, participants completed a post-session survey evaluating communication quality, satisfaction (using a 5-point Likert scale), and usability through the System Usability Scale (SUS). Results Eighteen clinicians participated, including residents, fellows, and attending physicians with an average of 3.6 ± 1.2 years of postgraduate experience. Fifty-four post-simulation surveys were completed across Arabic, Chinese, and Spanish languages comparing AI-TransLATE, ChatGPT, and Google Gemini. Participants rated the simulation as realistic across all cases (ECMO = 3.94 ± 0.66; Tracheostomy = 4.22 ± 0.43; Comfort Care = 4.06 ± 0.42; p = 0.32). Satisfaction was highest for AI-TransLATE (4.11 ± 0.68) and ChatGPT (4.00 ± 0.69) but lowest for Gemini (2.06 ± 1.00; p < 0.001). Willingness to use in real life followed the same trend. (AI-TransLATE = 4.00 ± 0.69, ChatGPT = 3.89 ± 0.96, Gemini = 2.00 ± 1.03 (p < 0.001)). SUS scores supported these findings (AI-TransLATE = 71.25 ± 13.35; ChatGPT = 72.22 ± 15.57; Gemini = 40.28 ± 21.30; p < 0.001), corresponding to good usability for AI-TransLATE and ChatGPT and poor usability for Gemini. Clinicians mentioned interruptions, uneven translation flow, and difficulty judging accuracy, but appreciated it when the AI-TransLATE conveyed tone and intonation, enabling smoother, more natural communication. Conclusion Overall, AI-TransLATE and ChatGPT demonstrated strong usability and satisfaction, showing promise as clinical communication tools; however, further validation in real-world ICU settings is warranted, and data privacy and confidentiality remain important considerations. This abstract is funded by: Critical care research committee mayo clinic

Abstract Rationale Critical care education has been identified as a global priority to improve the early identification and management of common syndromes, including sepsis and respiratory failure. International practice varies widely, and frontline clinical team perspectives remain poorly defined. The CERTAIN (Checklist for Early Recognition and Treatment of Acute Illness and iNjury) program provides a structured, checklist-based approach shown to improve the delivery of best practices and patient-centered outcomes worldwide. Over the past decade we have performed a needs assessment at the start of each international CERTAIN program. We performed a retrospective analysis of these data to examine the critical care domains prioritized by frontline interprofessional teams to inform global training priorities. MethodsWe developed an anonymous online survey consisting of 20 previously defined activities essential to the practice of critical care. Participants ranked these activities using Q-sort methodology on a forced distribution scale from -4 (lowest priority) to + 4 (highest priority). Individual rankings were summed across all participants to generate aggregate scores for each activity, with higher values reflecting greater collective prioritization. Aggregate scores were calculated for the entire cohort and each site and summarized with bar plots to illustrate prioritization patterns across critical care domains. ResultsA total of 213 intensivists, emergency medicine physicians, nurses, and pharmacists from hospitals in China (75), Cambodia (70), Croatia (31), Japan (24) and India (13) completed the survey. The distribution of priorities across content domains is illustrated in Figure. Management of shock, sepsis, mechanical ventilation, and respiratory failure received the highest aggregate scores. Interprofessional critical care coordination was the only process of care activity identified as high priority, and transitions of care, patient centered communication, and shared decision making were consistently ranked lowest. While minor variation existed across individual sites, resuscitation and the acute management of high-risk clinical conditions were consistently prioritized over processes of care and patient-centered care domains. ConclusionThis multicenter analysis demonstrates consistent interprofessional clinician prioritization of acute clinical management topics for training. These insights inform both areas of emphasis and highlight challenges that CERTAIN and other programs face to improve global patient care delivery. Variation in care processes has been consistently identified as the largest modifiable factor to improve patient outcomes, and cultural differences may present barriers to engagement on the best approaches to patient centered care. Figure. Distribution of aggregate Q-sort scores across 20 critical care activities. Scores represent summed participant rankings (n=213) from -4 (lowest priority) to +4 (highest priority). This abstract is funded by: None