Background and objectivesExcess fluid balance in acute kidney injury (AKI) may be harmful, and conversely, some patients may respond to fluid challenges. This study aimed to develop a prediction model that can be used to differentiate between volume-responsive (VR) and volume-unresponsive (VU) AKI.MethodsAKI patients with urine output 5 l in the following 6 h in the US-based critical care database (Medical Information Mart for Intensive Care (MIMIC-III)) were considered. Patients who received diuretics and renal replacement on day 1 were excluded. Two predictive models, using either machine learning extreme gradient boosting (XGBoost) or logistic regression, were developed to predict urine output > 0.65 ml/kg/h during 18 h succeeding the initial 6 h for assessing oliguria. Established models were assessed by using out-of-sample validation. The whole sample was split into training and testing samples by the ratio of 3:1.Main resultsOf the 6682 patients included in the analysis, 2456 (36.8%) patients were volume responsive with an increase in urine output after receiving > 5 l fluid. Urinary creatinine, blood urea nitrogen (BUN), age, and albumin were the important predictors of VR. The machine learning XGBoost model outperformed the traditional logistic regression model in differentiating between the VR and VU groups (AU-ROC, 0.860; 95% CI, 0.842 to 0.878 vs. 0.728; 95% CI 0.703 to 0.753, respectively).ConclusionsThe XGBoost model was able to differentiate between patients who would and would not respond to fluid intake in urine output better than a traditional logistic regression model. This result suggests that machine learning techniques have the potential to improve the development and validation of predictive modeling in critical care research.
Early mobilization is a structured protocol designed to facilitate motor recovery in intensive care unit (ICU) patients with ICU-acquired weakness. This process is typically implemented by an interdisciplinary team of nurses, physical therapists, and other healthcare professionals. However, its application is often constrained by the patients' critical conditions, limited mobility, and the challenges of coordinating care within resource-intensive ICU environments. In this study, we developed a patient-centered virtual reality (VR) exergame through an interdisciplinary design process involving clinicians and therapists, tailored to the constraints of critical care. The exergame incorporates progressive mobility levels that mirror early mobilization practices, and includes an embodied avatar to provide guidance and motivation. Using Meta Quest 3 body tracking, the system captures and visualizes patients' movements, thereby providing motivational engagement and quantifiable mobility metrics. We evaluated the exergame in two stages: a dual-user study involving healthy participants and healthcare professionals or students (N = 13), and a subsequent study with cardiothoracic ICU patients (N = 18) to assess feasibility, design validity, and clinical acceptance. Across both studies, participants reported high enjoyment and engagement without discomfort or stress. Furthermore, patients demonstrated increases in movement speed, range of motion, and workspace volume of the upper body across game levels. Physiological monitoring further indicated that the exergame elicited exertion without inducing excessive cardiovascular responses. These findings highlight the feasibility of VR exergames as a clinically acceptable and engaging adjunct to early mobilization in critical care, offering a novel pathway to improve rehabilitation outcomes for ICU patients.
Mohamed R. Zughbur, Yaser Hamam, Ashraf Kagee
et al.
Abstract Armed conflicts have a devastating effect on the civilian population, not only by direct violence but also by causing long-lasting psychiatric conditions, such as post-traumatic stress disorder (PTSD), depression, and anxiety, as a result of exposure to traumatic events such as displacement, loss of loved ones, and destruction of homes. The military attack on Gaza, which has been ongoing since October 7, 2023, compounds an environment of continuing fear, uncertainty, and loss, which markedly increases the prevalence of mental health disorders. This study aims to assess the prevalence of anxiety, probable PTSD, and depression in the population of Gaza after one year of continuous war. This study aims to offer a comprehensive perspective on the mental health challenges experienced by the people of Gaza. Data collection was carried out between November 10, 2024, and January 10, 2025. Four hundred five participants completed an online self-reported questionnaire, distributed via emails, social media platforms, and community networks. The survey screened for symptoms of PTSD (PCL-5), anxiety (GAD-7), and depression (PHQ-9), and included items assessing exposure to war-related experiences. The findings indicated alarmingly high rates of mental health symptoms, with 72.7% of participants reporting moderate to severe depression (PHQ-9 ≥ 10), 65% reporting moderate to severe anxiety (GAD-7 ≥ 10), and 83.5% meeting the threshold for probable PTSD (PCL-5 ≥ 33). The mean scores indicated moderate to severe symptom levels for anxiety and depression, with GAD-7 at 13.16 and PHQ-9 at 14.32. The mean PCL-5 score was 48.16, reflecting a substantial burden of PTSD symptoms among participants. A substantial proportion had lost a family member (45.7%), experienced a military siege (82.5%), witnessed someone being killed or injured (80.5%), and reported losing their work due to the conflict (42.7%). Binary logistic regression analysis revealed that losing a family member was significantly associated with moderate or higher levels of depression (OR = 2.395, p = 0.010) and anxiety (OR = 1.929, p = 0.027). Similarly, living in the northern part of the Gaza Strip was significantly associated with moderate or higher levels of depression (OR = 1.755, p = 0.039) and anxiety (OR = 2.395, p = 0.010). The simultaneous presence of any two of the three mental health conditions was statistically significant, with p values for each pairwise association being less than 0.05. The study revealed that the population of Gaza had an extremely high prevalence of diagnosable mental disorders, as determined through validated screening tools for anxiety, depression, and PTSD. These findings have far-reaching implications, emphasizing the urgent need not only for medical and psychosocial support, but more critically, for an end to the ongoing violence that continues to devastate lives and communities.
Special situations and conditions, Medical emergencies. Critical care. Intensive care. First aid
Celine Tabche, Zeenah Atwan, Samar Al-Mutawakel
et al.
BackgroundThe Leadership in Emergencies (LIE) training programme, developed by WHO's Health Emergencies (WHE) Learning and Capacity Development Unit (LCD) and Eastern Mediterranean Region (EMR) Health Emergencies Department, aims to enhance emergency management and responders' technical and operational skills. WHO implemented a four-phase leadership programme to address leadership gaps in emergency response. This study evaluates its effectiveness using participant surveys and in-depth interviews.MethodsA total of 207 participants completed the survey, with 10 providing qualitative insights through interviews. The WHO Research Ethics Review Committee approved the study. It assessed the application of non-technical skills, field-level public health expertise, project management in humanitarian settings, and leadership competencies.ResultsParticipants frequently applied communication (35.7%), teamwork (36.7%), problem-solving (37.2%), and emotional intelligence (37.7%) skills. Field-level public health skills were frequently applied by 42.5%, and project management skills by 86.5%. Many reported career advancements, improved leadership, networking, stress management, and strategic thinking. The training was relevant, particularly simulation exercises, but challenges included balancing training with professional duties. Participants highlighted the need for structured follow-up. Future training should incorporate ongoing support mechanisms and emphasize simulation exercises and stakeholder engagement.ConclusionThe findings highlight the necessity of ongoing evaluations, practical simulations, and continuous enhancement of training programmes.
Medical emergencies. Critical care. Intensive care. First aid
Ayub Bagheri , Alireza Sharifi Niknafs, Bahar Farhadi
et al.
Introduction: Surgical site infection (SSI) constitutes a substantial complication after knee arthroplasty, contributing to notable morbidity. This study aimed to review the existing literature on the incidence and risk factors of SSI following knee arthroplasty.
Methods: A systematic search was undertaken across various international electronic databases, including Scopus, PubMed, Web of Science, and Persian electronic databases such as Iranmedex and the Scientific Information Database. The search strategy involved the use of keywords derived from Medical Subject Headings, such as “incidence”, “Surgical wound infection”, “Surgical site infection”, and “Arthroplasty”, covering records from the earliest available up to March 17, 2024.
Results: The study incorporated a collective participant group of 1,366,494 knee arthroplasty procedures from twenty-three chosen studies. The pooled incidence rate of SSI after knee arthroplasty was 1.7% (95% confidence interval (CI): 1.1% to 2.6%; I²=99.687%; P<0.001). The Odds Ratio (OR) for the incidence of SSI in males was observed to be significantly higher than that in females (OR: 1.617; 95% CI: 1.380 to 1.894; Z=5.951; P<0.001). The pooled incidence of SSI among diabetic patients was 1.3% (95% CI: 0.6% to 2.8%; I²=99.126%; P<0.001).
Conclusion: Based on the main findings, SSIs continue to be a significant complication of knee arthroplasty, with an incidence of 1.1% to 2.6%. Male gender and diabetes mellitus were associated with an augmented probability of SSIs following knee arthroplasty.
Medical emergencies. Critical care. Intensive care. First aid
Emergency and intensive care environments require predictive models that are both accurate and computationally efficient, yet clinical data in these settings are often severely imbalanced. Such skewness undermines model reliability, particularly for rare but clinically crucial outcomes, making robustness and scalability essential for real-world usage. In this paper, we systematically evaluate the robustness and scalability of classical machine learning models on imbalanced tabular data from MIMIC-IV-ED and eICU. Class imbalance was quantified using complementary metrics, and we compared the performance of tree-based methods, the state-of-the-art TabNet deep learning model, and a custom lightweight residual network. TabResNet was designed as a computationally efficient alternative to TabNet, replacing its complex attention mechanisms with a streamlined residual architecture to maintain representational capacity for real-time clinical use. All models were optimized via a Bayesian hyperparameter search and assessed on predictive performance, robustness to increasing imbalance, and computational scalability. Our results, on seven clinically vital predictive tasks, show that tree-based methods, particularly XGBoost, consistently achieved the most stable performance across imbalance levels and scaled efficiently with sample size. Deep tabular models degraded more sharply under imbalance and incurred higher computational costs, while TabResNet provided a lighter alternative to TabNet but did not surpass ensemble benchmarks. These findings indicate that in emergency and critical care, robustness to imbalance and computational scalability could outweigh architectural complexity. Tree-based ensemble methods currently offer the most practical and clinically feasible choice, equipping practitioners with a framework for selecting models suited to high-stakes, time-sensitive environments.
Syed Ahmad Chan Bukhari, Amritpal Singh, Shifath Hossain
et al.
Intensive Care Unit (ICU) patients often present with complex, overlapping signs of physiological deterioration that require timely escalation of care. Traditional early warning systems, such as SOFA or MEWS, are limited by their focus on single outcomes and fail to capture the multi-dimensional nature of clinical decline. This study proposes a multi-label classification framework to predict Care Escalation Triggers (CETs), including respiratory failure, hemodynamic instability, renal compromise, and neurological deterioration, using the first 24 hours of ICU data. Using the MIMIC-IV database, CETs are defined through rule-based criteria applied to data from hours 24 to 72 (for example, oxygen saturation below 90, mean arterial pressure below 65 mmHg, creatinine increase greater than 0.3 mg/dL, or a drop in Glasgow Coma Scale score greater than 2). Features are extracted from the first 24 hours and include vital sign aggregates, laboratory values, and static demographics. We train and evaluate multiple classification models on a cohort of 85,242 ICU stays (80 percent training: 68,193; 20 percent testing: 17,049). Evaluation metrics include per-label precision, recall, F1-score, and Hamming loss. XGBoost, the best performing model, achieves F1-scores of 0.66 for respiratory, 0.72 for hemodynamic, 0.76 for renal, and 0.62 for neurologic deterioration, outperforming baseline models. Feature analysis shows that clinically relevant parameters such as respiratory rate, blood pressure, and creatinine are the most influential predictors, consistent with the clinical definitions of the CETs. The proposed framework demonstrates practical potential for early, interpretable clinical alerts without requiring complex time-series modeling or natural language processing.
This study reveals the important role of prevention care and medication adherence in reducing hospitalizations. By using a structured dataset of 1,171 patients, four machine learning models Logistic Regression, Gradient Boosting, Random Forest, and Artificial Neural Networks are applied to predict five-year hospitalization risk, with the Gradient Boosting model achieving the highest accuracy of 81.2%. The result demonstrated that patients with high medication adherence and consistent preventive care can reduce 38.3% and 37.7% in hospitalization risk. The finding also suggests that targeted preventive care can have positive Return on Investment (ROI), and therefore ML models can effectively direct personalized interventions and contribute to long-term medical savings.
Chronic obstructive pulmonary disease (COPD) represents a significant global health burden, where precise severity assessment is particularly critical for effective clinical management in intensive care unit (ICU) settings. This study introduces an innovative machine learning framework for COPD severity classification utilizing the MIMIC-III critical care database, thereby expanding the applications of artificial intelligence in critical care medicine. Our research developed a robust classification model incorporating key ICU parameters such as blood gas measurements and vital signs, while implementing semi-supervised learning techniques to effectively utilize unlabeled data and enhance model performance. The random forest classifier emerged as particularly effective, demonstrating exceptional discriminative capability with 92.51% accuracy and 0.98 ROC AUC in differentiating between mild-to-moderate and severe COPD cases. This machine learning approach provides clinicians with a practical, accurate, and efficient tool for rapid COPD severity evaluation in ICU environments, with significant potential to improve both clinical decision-making processes and patient outcomes. Future research directions should prioritize external validation across diverse patient populations and integration with clinical decision support systems to optimize COPD management in critical care settings.
Tea Wick Barsten, Emilie Sunde, Øyvind Thomassen
et al.
Abstract Background Accidental hypothermia is associated with increased morbidity and mortality and poses a significant challenge for both professional and volunteer rescue services in prehospital settings. This study investigated the methods and equipment available to treat patients with cold stress or accidental hypothermia before reaching hospital in Norway. Methods We surveyed 156 respondents representing 708 units from both the professional and volunteer Norwegian prehospital chain of care between 2023 and 2024. Professional services included national ground ambulances, boat ambulances, national fixed wing and helicopter air ambulance services, search and rescue helicopter services, and urban search and rescue services. Volunteer services included Norwegian People’s Aid and the Norwegian Red Cross Search and Rescue Corps. The survey queried the availability of active warming equipment, passive insulation materials, thermometers for detecting hypothermia, and preferred sites for temperature measurements. The study also investigated whether there has been a development in available equipment compared to a similar study conducted in 2013. Results The survey achieved a response rate of 70.5%. Chemical heat pads were the most frequently used type of equipment for active external warming and were the only equipment used by volunteer rescue services. All services possessed equipment for passive external warming, with duvets, space blankets and wool- or cotton blankets being the most commonly available. Thermometers for detecting hypothermia were found in 86.3% of professional rescue services and 15% of volunteer units. Almost all respondents reported consistent equipment setups year-round. Conclusion All Norwegian prehospital services, both professional and volunteer, reported having equipment available for active and passive external warming. Thermometers for detecting hypothermia were reported by all professional services. The most notable change in the equipment available to treat patients with prehospital cold stress and accidental hypothermia in Norway was the increased availability of active external rewarming equipment in 2024 compared with that in 2013.
Medical emergencies. Critical care. Intensive care. First aid
William R. Kearns, Jessica Bertram, Myra Divina
et al.
Despite the high prevalence and burden of mental health conditions, there is a global shortage of mental health providers. Artificial Intelligence (AI) methods have been proposed as a way to address this shortage, by supporting providers with less extensive training as they deliver care. To this end, we developed the AI-Assisted Provider Platform (A2P2), a text-based virtual therapy interface that includes a response suggestion feature, which supports providers in delivering protocolized therapies empathetically. We studied providers with and without expertise in mental health treatment delivering a therapy session using the platform with (intervention) and without (control) AI-assistance features. Upon evaluation, the AI-assisted system significantly decreased response times by 29.34% (p=0.002), tripled empathic response accuracy (p=0.0001), and increased goal recommendation accuracy by 66.67% (p=0.001) across both user groups compared to the control. Both groups rated the system as having excellent usability.
Manuel Burger, Fedor Sergeev, Malte Londschien
et al.
Notable progress has been made in generalist medical large language models across various healthcare areas. However, large-scale modeling of in-hospital time series data - such as vital signs, lab results, and treatments in critical care - remains underexplored. Existing datasets are relatively small, but combining them can enhance patient diversity and improve model robustness. To effectively utilize these combined datasets for large-scale modeling, it is essential to address the distribution shifts caused by varying treatment policies, necessitating the harmonization of treatment variables across the different datasets. This work aims to establish a foundation for training large-scale multi-variate time series models on critical care data and to provide a benchmark for machine learning models in transfer learning across hospitals to study and address distribution shift challenges. We introduce a harmonized dataset for sequence modeling and transfer learning research, representing the first large-scale collection to include core treatment variables. Future plans involve expanding this dataset to support further advancements in transfer learning and the development of scalable, generalizable models for critical healthcare applications.
Nicholas Konz, Richard Osuala, Preeti Verma
et al.
Determining whether two sets of images belong to the same or different distributions or domains is a crucial task in modern medical image analysis and deep learning; for example, to evaluate the output quality of image generative models. Currently, metrics used for this task either rely on the (potentially biased) choice of some downstream task, such as segmentation, or adopt task-independent perceptual metrics (e.g., Fréchet Inception Distance/FID) from natural imaging, which we show insufficiently capture anatomical features. To this end, we introduce a new perceptual metric tailored for medical images, FRD (Fréchet Radiomic Distance), which utilizes standardized, clinically meaningful, and interpretable image features. We show that FRD is superior to other image distribution metrics for a range of medical imaging applications, including out-of-domain (OOD) detection, the evaluation of image-to-image translation (by correlating more with downstream task performance as well as anatomical consistency and realism), and the evaluation of unconditional image generation. Moreover, FRD offers additional benefits such as stability and computational efficiency at low sample sizes, sensitivity to image corruptions and adversarial attacks, feature interpretability, and correlation with radiologist-perceived image quality. Additionally, we address key gaps in the literature by presenting an extensive framework for the multifaceted evaluation of image similarity metrics in medical imaging -- including the first large-scale comparative study of generative models for medical image translation -- and release an accessible codebase to facilitate future research. Our results are supported by thorough experiments spanning a variety of datasets, modalities, and downstream tasks, highlighting the broad potential of FRD for medical image analysis.
Silas Ruhrberg Estévez, Alex Grafton, Lynn Thomson
et al.
Neonates in intensive care require continuous monitoring. Current measurement devices are limited for long-term use due to the fragility of newborn skin and the interference of wires with medical care and parental interactions. Camera-based vital sign monitoring has the potential to address these limitations and has become of considerable interest in recent years due to the absence of physical contact between the recording equipment and the neonates, as well as the introduction of low-cost devices. We present a novel system to capture vital signs while offering clinical insights beyond current technologies using a single RGB-D camera. Heart rate and oxygen saturation were measured using colour and infrared signals with mean average errors (MAE) of 7.69 bpm and 3.37%, respectively. Using the depth signals, an MAE of 4.83 breaths per minute was achieved for respiratory rate. Tidal volume measurements were obtained with a MAE of 0.61 mL. Flow-volume loops can also be calculated from camera data, which have applications in respiratory disease diagnosis. Our system demonstrates promising capabilities for neonatal monitoring, augmenting current clinical recording techniques to potentially improve outcomes for neonates.