Background: With the rapid development of artificial intelligence, large language models (LLMs) have shown strong capabilities in natural language understanding, reasoning, and generation, attracting much research interest in applying LLMs to health and medicine. Critical care medicine (CCM) provides diagnosis and treatment for patients with critical illness who often require intensive monitoring and interventions in intensive care units (ICUs). Whether LLMs can be applied to CCM, and whether they can operate as ICU experts in assisting clinical decision-making rather than “stochastic parrots,” remains uncertain. Objective: This scoping review aims to provide a panoramic portrait of the application of LLMs in CCM, identifying the advantages, challenges, and future potential of LLMs in this field. Methods: This study was conducted in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Literature was searched across 7 databases, including PubMed, Embase, Scopus, Web of Science, CINAHL, IEEE Xplore, and ACM Digital Library, from the first available paper to August 22, 2025. Results: From an initial 2342 retrieved papers, 41 were selected for final review. LLMs played an important role in CCM through the following 3 main channels: clinical decision support, medical documentation and reporting, and medical education and doctor-patient communication. Compared to traditional artificial intelligence models, LLMs have advantages in handling unstructured data and do not require manual feature engineering. Meanwhile, applying LLMs to CCM has faced challenges, including hallucinations and poor interpretability, sensitivity to prompts, bias and alignment challenges, and privacy and ethical issues. Conclusions: Although LLMs are not yet ICU experts, they have the potential to become valuable tools in CCM, helping to improve patient outcomes and optimize health care delivery. Future research should enhance model reliability and interpretability, improve model training and deployment scalability, integrate up-to-date medical knowledge, and strengthen privacy and ethical guidelines, paving the way for LLMs to fully realize their impact in critical care. Trial Registration: OSF Registries yn328; https://osf.io/yn328/

BACKGROUND With the rapid development of artificial intelligence, large language models (LLMs) have shown strong capabilities in natural language understanding, reasoning, and generation, attracting much research interest in applying LLMs to health and medicine. Critical care medicine (CCM) provides diagnosis and treatment for patients with critical illness who often require intensive monitoring and interventions in intensive care units (ICUs). Whether LLMs can be applied to CCM, and whether they can operate as ICU experts in assisting clinical decision-making rather than “stochastic parrots,” remains uncertain. OBJECTIVE This scoping review aims to provide a panoramic portrait of the application of LLMs in CCM, identifying the advantages, challenges, and future potential of LLMs in this field. METHODS This study was conducted in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Literature was searched across 7 databases, including PubMed, Embase, Scopus, Web of Science, CINAHL, IEEE Xplore, and ACM Digital Library, from the first available paper to August 22, 2025. RESULTS From an initial 2342 retrieved papers, 41 were selected for final review. LLMs played an important role in CCM through the following 3 main channels: clinical decision support, medical documentation and reporting, and medical education and doctor-patient communication. Compared to traditional artificial intelligence models, LLMs have advantages in handling unstructured data and do not require manual feature engineering. Meanwhile, applying LLMs to CCM has faced challenges, including hallucinations and poor interpretability, sensitivity to prompts, bias and alignment challenges, and privacy and ethical issues. CONCLUSIONS Although LLMs are not yet ICU experts, they have the potential to become valuable tools in CCM, helping to improve patient outcomes and optimize health care delivery. Future research should enhance model reliability and interpretability, improve model training and deployment scalability, integrate up-to-date medical knowledge, and strengthen privacy and ethical guidelines, paving the way for LLMs to fully realize their impact in critical care. CLINICALTRIAL OSF Registries yn328; https://osf.io/yn328/

Objective: To identify distinct subtypes of ICU patients with Acute Kidney Injury (AKI) using serum electrolyte data and assess their associations with in-hospital mortality risk. Methods: This study used the eICU Collaborative Research Database (eICU-CRD) as its primary data source. AKI patients were identified according to the KDIGO clinical practice guidelines. Using K-Medoids clustering, we identified distinct AKI subtypes based on the first serum electrolyte measurements taken within 24 h of AKI diagnosis in the ICU. Logistic regression analysis was then employed to assess associations between these subtypes and in-hospital mortality risk. Within each subtype, we further examined the relationship between two AKI-related treatments, diuretics and renal replacement therapy (RRT), and mortality risk. Finally, to validate the identified subtypes, we replicated the entire analysis using a critical care dataset from a grade A tertiary hospital in Beijing, China. Results: We identified three distinct AKI subtypes from 15,838 eligible patients in the eICU-CRD. Subtype 1 (6364 patients, 40.2%) showed the lowest risk of in-hospital death and had all serum electrolyte levels within normal ranges. Subtype 2 (6624 patients, 41.8%) carried a moderate death risk and was characterized by abnormally high chloride levels. Subtype 3 (2850 patients, 18.0%) had the highest death risk, presenting with high serum phosphate and low bicarbonate levels. Importantly, the associations between treatments and mortality risk differed significantly by subtype. In the high-risk Subtype 3, both diuretics (OR = 0.71, p = 0.010) and RRT (OR = 0.78, p = 0.045) were associated with a lower risk of in-hospital death. However, in Subtype 2, both diuretics (OR = 1.30, p = 0.044) and RRT (OR = 1.56, p = 0.003) were associated with an increased risk. Neither treatment showed a significant association with death risk in Subtype 1. These findings were validated in the critical care database (431 AKI patients) from a Chinese local hospital, where the same three subtypes emerged with consistent electrolyte patterns, death risk profiles, and associations between treatments and mortality risks, validating the stability of the identified subtypes. Conclusions: Serum electrolyte data can help identify ICU AKI subtypes with different mortality risks. Additionally, associations between treatments (diuretics and RRT) and mortality risk vary significantly across these subtypes. These results generate the hypothesis that AKI subtyping could potentially inform personalized management strategies.