As large language models (LLMs) become increasingly integrated into clinical decision-making, their ethical alignment is as critical as factual accuracy. However, most evaluations focus on correctness while overlooking dimensions that influence patient outcomes and trust. To assess the ethical and contextual performance of three advanced LLMs—ChatGPT, Claude, and Gemini—across intensive care unit (ICU) scenarios and examine how specific ethical dimensions contribute to perceived clinical reliability. In this exploratory cross-model observational study, the models were evaluated using four ethically complex ICU cases. Responses were rated across ten ethical dimensions derived from biomedical ethics and AI ethics. Content analysis identified ethical reasoning patterns. Two expert ICU nurses independently rated clinical accuracy based on diagnosis and management appropriateness, with scores averaged across raters. Ethical dimensions were assessed by three domain experts, yielding 72 evaluations. Regression analysis at the model–scenario level (n = 12) examined associations between ethical scores and perceived clinical accuracy Across 12 model–scenario configurations, autonomy, oversight capability, and transparency were the strongest predictors of perceived clinical accuracy, whereas justice and nonmaleficence showed limited influence. Although findings are exploratory due to the small sample, ethical features accounted for significant variation in perceived reliability. Qualitative analysis showed Gemini produced more transparent and autonomy-supporting responses than Claude or ChatGPT. Ethical quality in AI-generated clinical decisions shapes expert perceptions of accuracy. These findings are hypothesis-generating and should be interpreted cautiously; larger studies are needed to confirm them. Ethical evaluation should be a core component of AI benchmarking in healthcare.

Objective: To compare the diagnostic accuracy and clinical decision-making of experienced community nurses versus state-of-the-art generative AI (GenAI) systems for simulated patient case scenarios. Methods: In the months of 5 to 6/2024, 114 community Israeli nurses completed a questionnaire including 4 medical case studies. Responses were also collected from 3 GenAI models (ChatGPT-4, Claude 3.0, and Gemini 1.5), analyzed both without word limits and with a 10-word constraint. Responses were scored on accuracy, speed, and comprehensiveness. Results: Nurses scored higher on average compared to the shortened GenAI responses. GenAI responses were faster but more verbose, and contained unnecessary information. Gemini (full version) and Claude (full version) achieved the highest accuracy among the GenAI models. Conclusions: While GenAI shows potential to support aspects of nursing practice, human clinicians currently exhibit advantages in holistic clinical reasoning abilities, a skill requiring experience, contextual knowledge, and ability to bring concise and practical responses. Further research is needed before GenAI can adequately substitute nursing expertise.

Background Understanding how clinicians arrive at decisions in actual practice settings is vital for advancing personalized, evidence-based care. However, systematic analysis of qualitative decision data poses challenges. Methods We analyzed transcribed interviews with Hebrew-speaking clinicians on decision processes using natural language processing (NLP). Word frequency and characterized terminology use, while large language models (ChatGPT from OpenAI and Gemini by Google) identified potential cognitive paradigms. Results Word frequency analysis of clinician interviews identified experience and knowledge as most influential on decision-making. NLP tentatively recognized heuristics-based reasoning grounded in past cases and intuition as dominant cognitive paradigms. Elements of shared decision-making through individualizing care with patients and families were also observed. Limited Hebrew clinical language resources required developing preliminary lexicons and dynamically adjusting stopwords. Findings also provided preliminary support for heuristics guiding clinical judgment while highlighting needs for broader sampling and enhanced analytical frameworks. Conclusions This study represents the first use of integrated qualitative and computational methods to systematically elucidate clinical decision-making. Findings supported experience-based heuristics guiding cognition. With methodological enhancements, similar analyses could transform global understanding of tailored care delivery. Standardizing interdisciplinary collaborations on developing NLP tools and analytical frameworks may advance equitable, evidence-based healthcare by elucidating real-world clinical reasoning processes across diverse populations and settings.

BACKGROUND:This study investigated medication dose calculation accuracy among nurses, nursing students, and Generative AI (GenAI) models, examining error prevention strategies across generational cohorts. METHODS:A cross-sectional study was conducted from June to August 2024, involving 101 pediatric/neonatal nurses, 91 nursing students, and four GenAI models. Participants completed a questionnaire on calculation proficiency and provided recommendations for error prevention. Qualitative responses were analyzed to describe attitudes and perceptions. RESULTS:70% of nurses reported previous medication errors compared to 19.5% of students. Thematic analysis identified six key areas for error prevention: double-checking, calculation methods, work environment, training, drug configuration, and technology use. Only students recommended GenAI integration, while nurses emphasized double-checking. CONCLUSIONS:The study highlights generational differences in medication safety approaches and suggests potential benefits of incorporating GenAI as an additional verification layer. These findings contribute to improving nursing education and practice through technological advancements while addressing persistent medication calculation challenges.

Background Endovascular intervention is often associated with improvements in physical function in patients with peripheral artery disease. Self-efficacy, the belief in one’s ability to successfully carry out specific behaviors, is a well-established determinant of exercise engagement in diverse populations, including those with peripheral artery disease. However, the role of self-efficacy in maintaining basic and instrumental activities of daily living following endovascular intervention is unclear. Aim To investigate the relationship between self-efficacy and functioning, walking capacity, and emotional well-being in patients with peripheral artery disease before and after endovascular interventions. Methods Twenty-eight individuals with peripheral artery disease presenting with either intermittent claudication or critical limb-threatening ischemia—who underwent endovascular interventions participated in this study. Standardized questionnaires were used to assess self-efficacy, anxiety, and depression. Daily-steps were calculated by a smartwatch. Independence in performing daily living activities was assessed using the modified Barthel Activities of Daily-Living Index and the independence in instrumental activities of daily-living questionnaire. Data was collected before the intervention (T1), at three months (T2), and at six months post-intervention (T3); this design enabled a comprehensive analysis of changes over time. Results Initially, higher self-efficacy correlated with better functioning of daily activities (r = 0.437, p < 0.01) and instrumental activities (r = 0.475, p < 0.01). At six months, higher self-efficacy correlated positively with all domains, including increased step count (r = 0.555, p < 0.01). Self-efficacy had a significant negative correlation with reported anxiety (r = -0.574, p < 0.01) and depression levels (r = -0.622, p < 0.01) post-treatment. A positive association was observed between female sex and self-efficacy in those with initially high self-efficacy levels. Conclusions Self-efficacy influences outcomes such as functional abilities, physical activity, and mental wellness in patients with peripheral artery disease following endovascular interventions.