Objectives: Acute kidney injury (AKI) is common in intensive care unit (ICU) patients and is associated with high mortality, prolonged ICU stays, and increased costs. Early prediction is crucial for timely intervention and improved outcomes. Various prediction models, including machine learning, deep learning, and dynamic prediction frameworks, have been developed, but their modeling approaches, data utilization, and clinical applicability require further investigation. This review comprehensively assesses the modeling methods, data utilization strategies, and clinical applicability of AKI prediction models in the ICU, identifies current challenges, and proposes future research directions. Materials and Methods: A systematic search was conducted in PubMed, Embase, Scopus, Web of Science, IEEE Xplore, and ACM Digital Library up to December 12, 2024. Studies were included if they reported AKI prediction models using ICU-specific data, included at least 2 predictors, and evaluated model performance. Extracted data included study characteristics, model details, data sources, performance metrics, and validation methods. The risk of bias was assessed using PROBAST (Prediction Model Risk of Bias Assessment Tool), and the reporting quality was evaluated using the TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) guideline. Results: From 1305 screened studies, 47 met the inclusion criteria. Models ranged from machine learning to advanced deep learning techniques. Only 14 studies conducted external validation. Most studies (n = 44) had a high risk of bias, particularly in generalizability and clinical applicability. Discussion: Although AI models have shown promise in predicting AKI in ICU settings, key challenges remain. These include limited external validation, lack of dynamic modeling, insufficient interpretability, and poor consideration of clinical integration. Different study designs, prediction windows, and data sources also hinder model comparability. Conclusions: Future research should prioritize dynamic, interpretable, and externally validated models. These efforts are critical to bridge the gap between model development and clinical implementation and to enhance the real-world applicability of AI in AKI prediction.

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: Multi-source evidence fusion aims to process and combine evidence from different sources to support rational and reliable decision-making. The evidential reasoning (ER) approach is a helpful method to deal with information from multiple sources with uncertainty. It has been widely used in business analytics, healthcare management, and other fields for optimal decision-making. However, computerized implementation of the ER approach usually requires much expertise and effort. At present, some ER-based computerized tools, such as the intelligent decision system (IDS), have been developed by professionals to provide decision support. Nevertheless, IDS is not open source, and the user interfaces are a bit complicated for non-professional users. The lack of a free-to-access and easy-to-use computerized tool limits the application of ER. Methods: We designed and developed a Python package that could efficiently implement the ER approach for multi-source evidence fusion. Further, based on it, we built an online web-based system, providing not only real-time evidence fusion but also visualized illustrations of combined results. Finally, a comparison study between the Python package and IDS was conducted. Results: A Python package, ERTool, was developed to implement the ER approach automatically and efficiently. The online version of the ERTool provides a more convenient way to handle evidence fusion tasks. Conclusions: ERTool, compatible with Python 3 and can be installed through the Python Package Index at https://pypi.org/project/ERTool/ , was developed to implement the ER approach. The ERTool has advantages in easy accessibility, clean interfaces, and high computing efficiency, making it a key tool for researchers and practitioners in multiple evidence-based decision-making. It helps bridge the gap between the algorithmic ER and its practical application and facilitates its widespread adoption in general decision-making contexts.

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/

This study employed the MIMIC-IV database as data source to investigate the use of dynamic, high-frequency, multivariate time-series vital signs data, including temperature, heart rate, mean blood pressure, respiratory rate, and SpO2, monitored first 8 hours data in the ICU stay. Various clustering algorithms were compared, and an end-to-end multivariate time series clustering system called Time2Feat, combined with K-Means, was chosen as the most effective method to cluster patients in the ICU. In clustering analysis, data of 8,080 patients admitted between 2008 and 2016 was used for model development and 2,038 patients admitted between 2017 and 2019 for model validation. By analyzing the differences in clinical mortality prognosis among different categories, varying risks of ICU mortality and hospital mortality were found between different subgroups. Furthermore, the study visualized the trajectory of vital signs changes. The findings of this study provide valuable insights into the potential use of multivariate time-series clustering systems in patient management and monitoring in the ICU setting.

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.