This review, conducted by Shi et al., investigates the use of large language models in critical care medicine in intensive care units. Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines were used to conduct this literature review. IEEE, Web of Science, Embase, PubMed, CINAHL, ACM Digital Library, Scopus, and ACM Digital Library were used to obtain 2342 papers up to August 22, 2025. The literature was filtered, and 41 were actually reviewed. The results showed that large language models were used in critical care medicine through medical recordkeeping, clinical decision-making, and communication between doctors and patients. Large language models help process unstructured data but also raise ethical, bias, and privacy concerns, and struggle to interpret data. Although large language models have advantages in certain areas, they have disadvantages in others.