Barwise, Amelia

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 Introduction Large Language Models (LLMs) have proven effective at analyzing unstructured and structured data from electronic health records (EHR). Their reliance on static EHR data means they miss the dynamic, high-resolution physiological signals that are the first indicators of patient decline, creating a fundamental data lag as clinical documentation of an event may occur hours after its onset. This represents a critical gap in the ability to develop truly effective triage tools. Furthermore, while LLMs can synthesize multi-source data for acuity assessment, they exhibit known limitations, including hallucinations that constrain autonomous use in safety-critical settings. In contrast, a Vision-Language Model (VLM) with strong image-grounded clinical reasoning can interpret vital sign trend images, surpassing the limitations of current EHR-based models. This approach provides immediate triage evaluations that lead to earlier detection of patient deterioration. Methods This mixed-methods study deployed a VLM (Gemini 2.5) integrated within the eICU dashboard. We used near-real-time two-hour trends in heart rate, blood pressure, respiratory rate, and oxygen saturation from consecutive patient cases during alerts in hospital floor units monitored by eICU that admit acute medical and surgical patients. To increase the diversity of the sample, we sought routine cases from patients without alerts and emergent cases from patients admitted to the medical, surgical, trauma, and mixed ICUs. A structured context prompt was used to generate a standardized summary including clinical interpretation, data quality and artifact assessment, triage recommendation, and the model’s chain-of-thought reasoning. Results We included patients from Mayo Clinic Rochester, MN, using an 800-patient cohort for prompt development and a 100-patient cohort for validation against clinically adjudicated results. In the validation cohort the VLM achieved 80% accuracy (80/100). An analysis of the 20 incorrect predictions revealed a clear pattern of conservative over-triage: 80% (16/20) of errors were clinically acceptable adjacent-class discrepancies (routine↔urgent or urgent↔emergent). Only 4/20 discrepancies represented a substantive misclassification. Most errors therefore reflected conservative prioritization rather than incorrect assessment. The model demonstrated a perfect safety profile, underestimating patient acuity in 0% of cases, and thus avoiding the most clinically dangerous error. These results confirm the feasibility of VLM-based approach and provide a strong foundation for the proposed work. Conclusion This VLM performs cross-modal reasoning by fusing deep visual perception with broad clinical context. The result is a fully contextualized and explainable triage prioritization, which provides direct decision support and integrates into the clinical workflow, allowing for faster and more confident acute care assessments. This abstract is funded by: none

Introduction Patient dehumanization when caring for critically ill patients in the intensive care unit (ICU) is commonplace. The Get to Know Me board (GTKMB) has been identified as a valuable tool for promoting humanized care and communication in the ICU; however, its implementation is highly variable. This study aimed to identify the barriers and facilitators influencing consistent implementation of the GTKMB in the ICU. Materials and methods We conducted multidisciplinary focus groups via teleconference with ICU clinicians at a large quaternary care academic medical center. A thematic content analysis was performed to identify key themes and concepts related to GTKMB implementation. Results Thirty-eight clinicians participated across six focus groups, including 10 nurses, 7 physicians, 6 advanced practice providers, 5 rehabilitation therapists (allied health clinicians), 1 respiratory therapist and 1 social worker. Major themes related to barriers and facilitators of GTKMB implementation included, (1) identifying appropriate patients and optimal timing for completing the GTKMB, (2) logistical challenges such as access to the board, visibility and unclear responsibility for completion, (3) the importance of clinician role modeling supporting the board completion, and (4) opportunities to improve the design and functionality of the board itself. Conclusion Although clinicians recognize the GTKMB as a meaningful tool to support humanized care in the ICU, inconsistent implementation limits its potential impact. This study highlights several key barriers and facilitators to its use. Future efforts should focus on targeted quality improvement initiatives to enhance consistent completion and integration of the GTKMB into ICU practice.

The intensive care unit (ICU) is a highly disease-focused environment where patients are often perceived primarily through their diagnoses rather than as individuals. The Get-To-Know-Me Board (GTKMB) was introduced as a humanizing tool to highlight patients’ personal attributes and foster person-centered care. Despite being found valuable in supporting humanized caring and fostering communication, completion rates at our institution remained low. Through a stakeholder-driven quality improvement initiative, we tested sequential interventions including reminders and checklists, visual magnets, and educational pamphlets to improve and increase the use of the GTKMB. These measures produced modest gains, with reminders and checklists yielding the most notable improvement. Barriers to using the GKTMB included unclear ownership, timing, and inconsistent integration into workflow. Our experience underscores both the promise and limitations of humanizing interventions in critical care. Sustainable implementation requires multidisciplinary buy-in and integration into daily routines. Whereas humanizing tools such as the GTKMB should be evaluated for their impact on meaningful patient outcomes, such outcomes are not clearly established; therefore, we embark on the necessary first step of a method of implementation.

Abstract The use of antibiotics in the hospice setting is complicated by differing patient goals, elevated side effects, and limited information regarding effectiveness. Here, we describe a case and apply the four-quadrant approach (4QA). This includes analyzing the case through the lenses of (1) medical indications related to improving function and reducing symptoms; (2) patient preferences, which vary among patients from complete avoidance of antibiotics to a therapeutic dosage to treat infection; (3) quality-of-life factors that include managing infectious symptoms versus antibiotic side effects; and (4) contextual features, which include antimicrobial resistance concerns and cost considerations. Antibiotics may be beneficial in some cases and should not be denied to patients enrolled in hospice care. More robust evidence-based information about outcomes is needed to inform discussions at the time of enrollment. Applying the 4QA to a case can help determine the best approach for each individual patient.

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.