Background. Ovarian cancer is one of the most lethal gynecological malignancies. Primary cytoreductive surgery remains the standard treatment, but in high-risk patients the complication rate is substantial. Multimodal prehabilitation within ERAS protocols is a promising approach to optimize patients’ condition before surgery. The purpose was to evaluate the impact of multimodal prehabilitation on perioperative outcomes in patients with advanced ovarian cancer undergoing primary cytoreduction. Materials and methods. In this prospective observational study (2022–2024), 150 patients with FIGO stage IIIC–IV ovarian cancer and ASA III–IV status were included. Seventy-five patients completed a 7–14-day prehabilitation program (nutritional support, anemia correction, exercise, psychological counseling), while 75 historical controls received standard ERAS care only. Primary endpoints were postoperative complications; secondary endpoints included hospital stay and time to chemotherapy initiation. Results. Prehabilitation significantly improved nutritional and functional parameters, reduced hospital stay (8 vs. 14 days; p < 0.005), accelerated chemotherapy initiation (8 vs. 15 days; p < 0.005), lowered the incidence of severe complications and 30-day mortality (1 vs. 10 %). Optimal benefit was achieved with ~ 10-day programs. Conclusions. Multimodal prehabilitation improves functional status, reduces morbidity, and shortens recovery in patients with advanced ovarian cancer, supporting its integration into ERAS pathways.
Medical emergencies. Critical care. Intensive care. First aid
Introduction: Anti-neutrophil cytoplasmic antibody (ANCA)- associated vasculitis (AAV) is a rare group of systemic autoimmune diseases that primarily target small blood vessels. Renal manifestations often present as pauci-immune focal and segmental necrotizing crescentic glomerulonephritis (PI-NCGN), which can progress to acute or chronic kidney failure and multiorgan involvement. It is frequently associated with poor outcomes.
We report a case of PR3-positive ANCA-associated vasculitis complicated by rapidly progressive glomerulonephritis, acute kidney injury, and diffuse alveolar hemorrhage during the COVID-19 pandemic. This case highlights the diagnostic challenges of differentiating AAV from conditions associated with SARS-CoV-2 infection, as the clinical and radiological presentations of pulmonary-renal syndromes may overlap.
The findings underscore the importance of maintaining a comprehensive differential diagnosis in patients with pulmonary and renal involvement, particularly in the post-COVID-19 era, to ensure timely and accurate management of rare autoimmune conditions such as AAV.
Conclusion: ANCA-associated vasculitis (AAV) remains a diagnostic and therapeutic challenge, particularly in the post-COVID-19 era, where overlapping clinical and radiological features with SARS-CoV-2 complications can obscure timely identification. This case highlights the critical importance of maintaining a broad differential diagnosis in patients presenting with pulmonary-renal syndromes to differentiate AAV from more common conditions associated with COVID-19.
Surgery, Medical emergencies. Critical care. Intensive care. First aid
Zongliang Ji, Andre Carlos Kajdacsy-Balla Amaral, Anna Goldenberg
et al.
Ordering a minimal subset of lab tests for patients in the intensive care unit (ICU) can be challenging. Care teams must balance between ensuring the availability of the right information and reducing the clinical burden and costs associated with each lab test order. Most in-patient settings experience frequent over-ordering of lab tests, but are now aiming to reduce this burden on both hospital resources and the environment. This paper develops a novel method that combines off-policy learning with privileged information to identify the optimal set of ICU lab tests to order. Our approach, EXplainable Off-policy learning with Side Information for ICU blood Test Orders (ExOSITO) creates an interpretable assistive tool for clinicians to order lab tests by considering both the observed and predicted future status of each patient. We pose this problem as a causal bandit trained using offline data and a reward function derived from clinically-approved rules; we introduce a novel learning framework that integrates clinical knowledge with observational data to bridge the gap between the optimal and logging policies. The learned policy function provides interpretable clinical information and reduces costs without omitting any vital lab orders, outperforming both a physician's policy and prior approaches to this practical problem.
Kruthika Gangaraju, Tanmayi Inaparthy, Jiaqi Yang
et al.
People living with dementia (PLWDs) face progressively declining abilities in medication management-from simple forgetfulness to complete task breakdown-yet most assistive technologies fail to adapt to these changing needs. This one-size-fits-all approach undermines autonomy, accelerates dependence, and increases caregiver burden. Occupational therapy principles emphasize matching assistance levels to individual capabilities: minimal reminders for those who merely forget, spatial guidance for those who misplace items, and comprehensive multimodal support for those requiring step-by-step instruction. However, existing robotic systems lack this adaptive, graduated response framework essential for maintaining PLWD independence. We present an adaptive multimodal robotic framework using the Pepper robot that dynamically adjusts assistance based on real-time assessment of user needs. Our system implements a hierarchical intervention model progressing from (1) simple verbal reminders, to (2) verbal + gestural cues, to (3) full multimodal guidance combining physical navigation to medication locations with step-by-step verbal and gestural instructions. Powered by LLM-driven interaction strategies and multimodal sensing, the system continuously evaluates task states to provide just-enough assistance-preserving autonomy while ensuring medication adherence. We conducted a preliminary study with healthy adults and dementia care stakeholders in a controlled lab setting, evaluating the system's usability, comprehensibility, and appropriateness of adaptive feedback mechanisms. This work contributes: (1) a theoretically grounded adaptive assistance framework translating occupational therapy principles into HRI design, (2) a multimodal robotic implementation that preserves PLWD dignity through graduated support, and (3) empirical insights into stakeholder perceptions of adaptive robotic care.
In the much-celebrated book Deep Medicine, Eric Topol argues that the development of artificial intelligence for health care will lead to a dramatic shift in the culture and practice of medicine. In the next several decades, he suggests, AI will become sophisticated enough that many of the everyday tasks of physicians could be delegated to it. Topol is perhaps the most articulate advocate of the benefits of AI in medicine, but he is hardly alone in spruiking its potential to allow physicians to dedicate more of their time and attention to providing empathetic care for their patients in the future. Unfortunately, several factors suggest a radically different picture for the future of health care. Far from facilitating a return to a time of closer doctor-patient relationships, the use of medical AI seems likely to further erode therapeutic relationships and threaten professional and patient satisfaction.
Background Predicting mortality and resource utilization from electronic health records (EHRs) is challenging yet crucial for optimizing patient outcomes and managing costs in intensive care unit (ICU). Existing approaches predominantly focus on structured EHRs, often ignoring the valuable clinical insights in free-text notes. Additionally, the potential of textual information within structured data is not fully leveraged. This study aimed to introduce and assess a deep learning framework using natural language processing techniques that integrates multimodal EHRs to predict mortality and resource utilization in critical care settings. Methods Utilizing two real-world EHR datasets, we developed and evaluated our model on three clinical tasks with leading existing methods. We also performed an ablation study on three key components in our framework: medical prompts, free-texts, and pre-trained sentence encoder. Furthermore, we assessed the model's robustness against the corruption in structured EHRs. Results Our experiments on two real-world datasets across three clinical tasks showed that our proposed model improved performance metrics by 1.6\%/0.8\% on BACC/AUROC for mortality prediction, 0.5%/2.2% on RMSE/MAE for LOS prediction, 10.9%/11.0% on RMSE/MAE for surgical duration estimation compared to the best existing methods. It consistently demonstrated superior performance compared to other baselines across three tasks at different corruption rates. Conclusions The proposed framework is an effective and accurate deep learning approach for predicting mortality and resource utilization in critical care. The study also highlights the success of using prompt learning with a transformer encoder in analyzing multimodal EHRs. Importantly, the model showed strong resilience to data corruption within structured data, especially at high corruption levels.
Frailty, a condition that was first defined 20 years ago, is now assessed via multiple different tools. The Frailty Phenotype was initially used to identify a population of “pre-frail” and “frail” older adults, so as to prevent falls, loss of mobility, and hospitalizations. A different definition of frailty, via the Clinical Frailty Scale, is now actively used in critical care situations to evaluate over 65 year-old patients, whether it be for Intensive Care Unit (ICU) admissions, limitation of life-sustaining treatments or prognostication. Confusion remains when mentioning “frailty” in older adults, as to which tools are used, and what the impact or the bias of using these tools might be. In addition, it is essential to clarify which tools are appropriate in medical emergencies. In this review, we clarify various concepts and differences between frailty, functional autonomy and comorbidities; then focus on the current use of frailty scales in critically ill older adults. Finally, we discuss the benefits and risks of using standardized scales to describe patients, and suggest ways to maintain a complex, three-dimensional, patient evaluation, despite time constraints. Frailty in the ICU is common, involving around 40% of patients over 75. The most commonly used scale is the Clinical Frailty Scale (CFS), a rapid substitute for Comprehensive Geriatric Assessment (CGA). Significant associations exist between the CFS-scale and both short and long-term mortality, as well as long-term outcomes, such as loss of functional ability and being discharged home. The CFS became a mainstream tool newly used for triage during the Covid-19 pandemic, in response to the pressure on healthcare systems. It was found to be significantly associated with in-hospital mortality. The improper use of scales may lead to hastened decision-making, especially when there are strains on healthcare resources or time-constraints. Being aware of theses biases is essential to facilitate older adults’ access to equitable decision-making regarding critical care. The aim is to help counteract assessments which may be abridged by time and organisational constraints.
Current research is mostly focused on the impact of fertilizers on human health when they are ingested through food; the main form of this is chronic damage. Intoxication through oral ingestion of fertilizer is an extremely rare situation. We report a case of a 38-year-old man that attempted to commit suicide by ingesting only 20 mL of a water-soluble fertilizer. Acute kidney injury occurred early, which showed that the toxicity could not be ignored. It was necessary to seek medical attention as soon as possible. In addition, the patient experienced gastrointestinal dysfunction and a severe inflammatory response; inflammatory markers increased rapidly. Physicians implemented antimicrobial stewardship to reduce antimicrobial drug resistance and the risk of hospital infection, and the patient’s inflammatory response was well controlled. Although the damage was severe, the patient quickly recovered to normal after appropriate treatment. The prognosis is very good. This successful case provides guidance for clinical treatment.
Medical emergencies. Critical care. Intensive care. First aid
Ichiro Okada, Toru Hifumi, Hisashi Yoneyama
et al.
Abstract Background A team approach is essential for effective trauma management. Close collaboration between interventional radiologists and surgeons during the initial management of trauma patients is important for prompt and accurate trauma care. This study aimed to determine whether trauma patients benefit from close collaboration between interventional radiology (IR) and surgical teams during the primary trauma survey. Methods A retrospective observational study was conducted between 2014 and 2021 at a single institution. Patients were assigned to an embolization group (EG), a surgery group (SG), or a combination group (CG) according to their treatment. The primary and secondary outcomes were survival at hospital discharge compared with the probability of survival (Ps) and the time course of treatment. Results The analysis included 197 patients, consisting of 135 men and 62 women, with a median age of 56 [IQR, 38–72] years and an injury severity score of 20 [10–29]. The EG, SG, and CG included 114, 48, and 35 patients, respectively. Differences in organ injury patterns were observed between the three groups. In-hospital survival rates in all three groups were higher than the Ps. In particular, the survival rate in the CG was 15.5% higher than the Ps (95% CI: 7.5–23.6%; p < 0.001). In the CG, the median time for starting the initial procedure was 53 [37–79] min and the procedure times for IR and surgery were 48 [29–72] min and 63 [35–94] min, respectively. Those times were significantly shorter among three groups. Conclusion Close collaboration between IR and surgical teams, including the primary survey, improves the survival of severe trauma patients who require both IR procedures and surgeries by improving appropriate treatment selection and reducing the time process.
Special situations and conditions, Medical emergencies. Critical care. Intensive care. First aid
INTRODUCTION: Over 70,000 cases of Proximal Femoral Fracture (PFF) occur annually in the United Kingdom (UK), primarily affecting the elderly. These injuries are associated with high morbidity and mortality, and often see inadequate pain management in the prehospital setting. The Fascia Iliaca Compartment Block (FICB), a regional anaesthesia technique, is the gold standard of care in Emergency Departments (ED). This review aims to assess the literature on paramedic-performed FICB for suspected PFF in the prehospital setting, highlighting benefits and challenges to guide future practice and policy in the ambulance sector. MATERIALS AND METHODS: A rapid scoping review was conducted following the Joanna Briggs Institute (JBI) methodology, with modifications for this project’s limitations. A systematic search of the databases CINHAL, PubMed, EMBASE, and Medline was performed. A synthesis matrix was created to extrapolate data from the included studies and allow for a coherent interpretation of results. Each included study was subject to a critical appraisal conducted using the Mixed Methods Appraisal Tool (MMAT). RESULTS: Data was extracted from three studies and two reports which identified four key themes emerged: paramedic competency in performing FICB, patient perspectives, adverse events, and training and governance. Studies showed paramedics can competently perform FICBs in prehospital settings. Verbal pain scores were lower following an FICB compared to standard care with IV morphine, which required more supplementary morphine for break-out pain. Concern for causing harm was a consistent theme among the paramedics performing FICB, particularly in precipitating an adverse event sequela. Adverse events were more common in non-FICB groups, with only one case of local anaesthetic toxicity in the FICB group, which was correctly managed by the paramedic. CONCLUSIONS: Paramedics can competently perform FICB in the prehospital setting, showing promising results in pain relief compared to intravenous morphine. However, higher-level research is needed for confirmation. Patients generally tolerated paramedic-led FICB well, with minimal concerns. Training and governance remain significant barriers to implementing FICB in local ambulance services.
Medical emergencies. Critical care. Intensive care. First aid
Barbara Sienkiewicz, Zuzanna Radosz-Knawa, Bipin Indurkhya
We present our ongoing research on applying a participatory design approach to using social robots for elderly care. Our approach involves four different groups of stakeholders: the elderly, (non-professional) caregivers, medical professionals, and psychologists. We focus on card sorting and storyboarding techniques to elicit the concerns of the stakeholders towards deploying social robots for elderly care. This is followed by semi-structured interviews to assess their attitudes towards social robots individually. Then we are conducting two-stage workshops with different elderly groups to understand how to engage them with the technology and to identify the challenges in this task.
Medical image classification plays a crucial role in computer-aided clinical diagnosis. While deep learning techniques have significantly enhanced efficiency and reduced costs, the privacy-sensitive nature of medical imaging data complicates centralized storage and model training. Furthermore, low-resource healthcare organizations face challenges related to communication overhead and efficiency due to increasing data and model scales. This paper proposes a novel privacy-preserving medical image classification framework based on federated learning to address these issues, named FedMIC. The framework enables healthcare organizations to learn from both global and local knowledge, enhancing local representation of private data despite statistical heterogeneity. It provides customized models for organizations with diverse data distributions while minimizing communication overhead and improving efficiency without compromising performance. Our FedMIC enhances robustness and practical applicability under resource-constrained conditions. We demonstrate FedMIC's effectiveness using four public medical image datasets for classical medical image classification tasks.
A. Rousseau, Laurence Dams, Quentin Massart
et al.
Background So far, the few prospective studies on near-death experience (NDE) were carried out only in intensive care unit (ICU) patients with homogeneous aetiologies, such as cardiac arrest or trauma survivors. The aims of this 1-year prospective and monocentric study were to investigate the incidence of NDE in ICU survivors (all aetiologies) as well as factors that may affect its frequency, and to assess quality of life up to 1 year after enrolment. Methods We enrolled adults with a prolonged ICU stay (> 7 days). During the first 7 days after discharge, all eligible patients were assessed in a face-to-face interview for NDE using the Greyson NDE scale, dissociative experiences using the Dissociative Experience Scale, and spirituality beliefs using the WHOQOL-SRPB. Medical parameters were prospectively collected. At 1-year after inclusion, patients were contacted by phone to measure quality of life using the EuroQol five-dimensional questionnaire. Results Out of the 126 included patients, 19 patients (15%) reported having experienced a NDE as identified by the Greyson NDE scale (i.e. cut-off score ≥ 7/32). In univariate analyses, mechanical ventilation, sedation, analgesia, reason for admission, primary organ dysfunction, dissociative and spiritual propensities were associated with the emergence of NDE. In multivariate logistic regression analysis, only the dissociative and spiritual propensity strongly predicted the emergence of NDE. One year later (n = 61), the NDE was not significantly associated with quality of life. Conclusions The recall of NDE is not so rare in the ICU. In our cohort, cognitive and spiritual factors outweighed medical parameters as predictors of the emergence of NDE. Trial registration This trial was registered in Clinicaltrials.gov in February 2020 ( NCT04279171 ).
Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units.
Transforming raw EHR data into machine learning model-ready inputs requires considerable effort. One widely used EHR database is Medical Information Mart for Intensive Care (MIMIC). Prior work on MIMIC-III cannot query the updated and improved MIMIC-IV version. Besides, the need to use multicenter datasets further highlights the challenge of EHR data extraction. Therefore, we developed an extraction pipeline that works on both MIMIC-IV and eICU Collaborative Research Database and allows for model cross validation using these 2 databases. Under the default choices, the pipeline extracted 38766 and 126448 ICU records for MIMIC-IV and eICU, respectively. Using the extracted time-dependent variables, we compared the Area Under the Curve (AUC) performance with prior works on clinically relevant tasks such as in-hospital mortality prediction. METRE achieved comparable performance with AUC 0.723- 0.888 across all tasks. Additionally, when we evaluated the model directly on MIMIC-IV data using a model trained on eICU, we observed that the AUC change can be as small as +0.019 or -0.015. Our open-source pipeline transforms MIMIC-IV and eICU into structured data frames and allows researchers to perform model training and testing using data collected from different institutions, which is of critical importance for model deployment under clinical contexts.
Objective. Levofloxacin has been widely used in clinical anti-infection treatment; however, its adverse reactions to levofloxacin were also obvious in patients. Herein we aimed to systematically evaluate the clinical efficacy and safety of systemic administration of levofloxacin in the prevention of postoperative infection after traumatic osteoarthrosis and internal fixation. Methods. PubMed, Cochrane Library, OVID, EBSCO, CNKI, VIP database, and Wanfang Database were searched from December 1993 to December 2021. Meanwhile, China ADR Information Bulletin and WHO Pharmaceutical were searched manually. Newsletter and FDA Drug Safety Newsletter, also to retrieve the Websites of Chinese, Chinese, and drug regulatory authorities; To obtain data on adverse events in children with systemic administration of levofloxacin. The literature was screened according to inclusion and exclusion criteria. The risk of bias was evaluated for the included RCT literature. Results. There was a statistical difference in the comparison of the incidence of fever between the experimental group and the control group (OR = 2.29, 95% CI (1.75,2.98),P<0.00001, I2 = 0%, Z = 6.11); elevated white blood cell count (OR = 1.82, 95% CI (1.31,2.52),P=0.0003, I2 = 0%, Z = 3.60); incidence of wound infection (OR = 2.11, 95% CI (1.54,2.90),P<0.00001, I2 = 0%, Z = 4.64); adverse drug reaction (OR = 1.82, 95% CI (1.21,2.74),P=0.004, I2 = 0%, Z = 2.86). Conclusion. In the clinical use of levofloxacin, adverse drug reactions including fever, elevated white blood cell count, and wound infection should be concerned.
Medical emergencies. Critical care. Intensive care. First aid