Hasil untuk "Medical emergencies. Critical care. Intensive care. First aid"

G. Hermans, G. Van den Berghe

A substantial number of patients admitted to the ICU because of an acute illness, complicated surgery, severe trauma, or burn injury will develop a de novo form of muscle weakness during the ICU stay that is referred to as “intensive care unit acquired weakness” (ICUAW). This ICUAW evoked by critical illness can be due to axonal neuropathy, primary myopathy, or both. Underlying pathophysiological mechanisms comprise microvascular, electrical, metabolic, and bioenergetic alterations, interacting in a complex way and culminating in loss of muscle strength and/or muscle atrophy. ICUAW is typically symmetrical and affects predominantly proximal limb muscles and respiratory muscles, whereas facial and ocular muscles are often spared. The main risk factors for ICUAW include high severity of illness upon admission, sepsis, multiple organ failure, prolonged immobilization, and hyperglycemia, and also older patients have a higher risk. The role of corticosteroids and neuromuscular blocking agents remains unclear. ICUAW is diagnosed in awake and cooperative patients by bedside manual testing of muscle strength and the severity is scored by the Medical Research Council sum score. In cases of atypical clinical presentation or evolution, additional electrophysiological testing may be required for differential diagnosis. The cornerstones of prevention are aggressive treatment of sepsis, early mobilization, preventing hyperglycemia with insulin, and avoiding the use parenteral nutrition during the first week of critical illness. Weak patients clearly have worse acute outcomes and consume more healthcare resources. Recovery usually occurs within weeks or months, although it may be incomplete with weakness persisting up to 2 years after ICU discharge. Prognosis appears compromised when the cause of ICUAW involves critical illness polyneuropathy, whereas isolated critical illness myopathy may have a better prognosis. In addition, ICUAW has shown to contribute to the risk of 1-year mortality. Future research should focus on new preventive and/or therapeutic strategies for this detrimental complication of critical illness and on clarifying how ICUAW contributes to poor longer-term prognosis.

Jennifer Hartwell, Stepheny Berry, Craig Follette

Babandina Muhammad Musa 1, Ocheme Julius Okojokwu 2, Musa Saleh Makeri 3, Khadijat Toyi Musa 4, Amos Dangana 5, Maryam Aladodo 6, Saheed Adekola 7, Nura Muhammad Bunza 8, Zainab Usman-kanfani9, Clara Obiegue 10, Abbas M Babandina11 Musa Abidemi Muhibi 12,

The signature of occult hepatitis B virus is in its ability to escape detection by hepatitis surface antigen (HBsAg) rapid kit which is the only kit certified across Nigerian health institutions. This phenomenon is a measure set back to haemotherapuetics with increased risk of transfusion with the hidden virus. This study aimed to determine the prevalence of occult HBV infection among blood donors. In this cross-sectional study, 250 well-screened HB-vaccinated and unvaccinated blood donors were enrolled at some selected secondary health facilities across the six Abuja District hospitals. A well-structured questionnaire was administered to obtain donor biodata and socio-demographic characteristics, CLIA, HB-5 panel check (Arial), HBV DNA analysis, and viral load was performed to ascertain the OBI. Serological confirmation using CLIA technique reveals 8 (3.2%), 11 (4.4%) HCV, 5 (2.0%) VDRL and 30 (12.0%) HBV detection among blood donors already certified free to donate with overall 54 (9.6%) positive blood unit out of 250 sample assayed. Virologic markers reveals 28 (11.2%) HBsAb, 1 (0.4%) HBeAg, 5 (2.0%) HBeAb and 5 (1.6%) HBcAb with 1 detectable viral of 37.0 (IU/ml) among HB-vaccinated blood donors. Similarly, a corresponding 51 (20.4%) HBsAb, 17 (6.8%) HBeAg, 27 (10.8%) HBeAb and 19 (7.6%) HBcAb with mean viral load of 129.8 ±11.3 (IU/ml) among HB-unvaccinated blood donors. Our finding reports the prevalence of occult HBV DNA of 5.2% with the highest in male blood donors with post-secondary school educational status at mean age of 39.5 ± 15.9 years of age. This result underscores the need to urgent intervention in the area of improving diagnostic sensitivity and to design new blood donor screening protocol to enhance transfusion safety.

Oliver Normand, Esther Borsi, Mitch Fruin et al.

Large language models (LLMs) often match or exceed clinician-level performance on medical benchmarks, yet very few are evaluated on real clinical data or examined beyond headline metrics. We present, to our knowledge, the first evaluation of an LLM-based medication safety review system on real NHS primary care data, with detailed characterisation of key failure behaviours across varying levels of clinical complexity. In a retrospective study using a population-scale EHR spanning 2,125,549 adults in NHS Cheshire and Merseyside, we strategically sampled patients to capture a broad range of clinical complexity and medication safety risk, yielding 277 patients after data-quality exclusions. An expert clinician reviewed these patients and graded system-identified issues and proposed interventions. Our primary LLM system showed strong performance in recognising when a clinical issue is present (sensitivity 100\% [95\% CI 98.2--100], specificity 83.1\% [95\% CI 72.7--90.1]), yet correctly identified all issues and interventions in only 46.9\% [95\% CI 41.1--52.8] of patients. Failure analysis reveals that, in this setting, the dominant failure mechanism is contextual reasoning rather than missing medication knowledge, with five primary patterns: overconfidence in uncertainty, applying standard guidelines without adjusting for patient context, misunderstanding how healthcare is delivered in practice, factual errors, and process blindness. These patterns persisted across patient complexity and demographic strata, and across a range of state-of-the-art models and configurations. We provide 45 detailed vignettes that comprehensively cover all identified failure cases. This work highlights shortcomings that must be addressed before LLM-based clinical AI can be safely deployed. It also begs larger-scale, prospective evaluations and deeper study of LLM behaviours in clinical contexts.

Javad M Alizadeh, Mukesh K Patel, Huanmei Wu

Digital Twin (DT) technology has emerged as a transformative approach in healthcare, but its application in personalized patient care remains limited. This paper aims to present a practical implementation of DT in the management of chronic diseases. We introduce a general DT framework for personalized care planning (DT4PCP), with the core components being a real-time virtual representation of a patient's health and emerging predictive models to enable adaptive, personalized care. We implemented the DT4PCP framework for managing Type 2 Diabetes (DT4PCP-T2D), enabling real-time collection of behavioral data from patients with T2D, predicting emergency department (ED) risks, simulating the effects of different interventions, and personalizing care strategies to reduce ED visits. The DT4PCP-T2D also integrates social determinants of health (SDoH) and other contextual data, offering a comprehensive view of the patient's health to ensure that care recommendations are tailored to individual needs. Through retrospective simulations, we demonstrate that integrating DTs in T2D management can lead to significant advancements in personalized medicine. This study underscores the potential of DT technology to revolutionize chronic disease care.

Rhiannon Owen, Jonathan C. Roberts

Dementia care requires healthcare professionals to balance a patient's medical needs with a deep understanding of their personal needs, preferences, and emotional cues. However, current digital tools prioritise quantitative metrics over empathetic engagement,limiting caregivers ability to develop a deeper personal understanding of their patients. This paper presents an empathy centred visualisation framework, developed through a design study, to address this gap. The framework integrates established principles of person centred care with empathy mapping methodologies to encourage deeper engagement. Our methodology provides a structured approach to designing for indirect end users, patients whose experience is shaped by a tool they may not directly interact with. To validate the framework, we conducted evaluations with healthcare professinals, including usability testing of a working prototype and a User Experience Questionnaire study. Results suggest the feasibility of the framework, with participants highlighting its potential to support a more personal and empathetic relationship between medical staff and patients. The work starts to explore how empathy could be systematically embedded into visualisation design, as we contribute to ongoing efforts in the data visualisation community to support human centred, interpretable, and ethically aligned clinical care, addressing the urgent need to improve dementia patients experiences in hospital settings.

Ye Du, Nanxi Yu, Shujun Wang

Vision-language foundation models (VLMs) have shown great potential in feature transfer and generalization across a wide spectrum of medical-related downstream tasks. However, fine-tuning these models is resource-intensive due to their large number of parameters. Prompt tuning has emerged as a viable solution to mitigate memory usage and reduce training time while maintaining competitive performance. Nevertheless, the challenge is that existing prompt tuning methods cannot precisely distinguish different kinds of medical concepts, which miss essentially specific disease-related features across various medical imaging modalities in medical image classification tasks. We find that Large Language Models (LLMs), trained on extensive text corpora, are particularly adept at providing this specialized medical knowledge. Motivated by this, we propose incorporating LLMs into the prompt tuning process. Specifically, we introduce the CILMP, Conditional Intervention of Large Language Models for Prompt Tuning, a method that bridges LLMs and VLMs to facilitate the transfer of medical knowledge into VLM prompts. CILMP extracts disease-specific representations from LLMs, intervenes within a low-rank linear subspace, and utilizes them to create disease-specific prompts. Additionally, a conditional mechanism is incorporated to condition the intervention process on each individual medical image, generating instance-adaptive prompts and thus enhancing adaptability. Extensive experiments across diverse medical image datasets demonstrate that CILMP consistently outperforms state-of-the-art prompt tuning methods, demonstrating its effectiveness. Code is available at https://github.com/usr922/cilmp.

Sarah Nassar, Nooshin Maghsoodi, Sophia Mannina et al.

Objective: Atrial fibrillation (AF) is the most common cardiac arrhythmia experienced by intensive care unit (ICU) patients and can cause adverse health effects. In this study, we publish a labelled ICU dataset and benchmarks for AF detection. Methods: We compared machine learning models across three data-driven artificial intelligence (AI) approaches: feature-based classifiers, deep learning (DL), and ECG foundation models (FMs). This comparison addresses a critical gap in the literature and aims to pinpoint which AI approach is best for accurate AF detection. Electrocardiograms (ECGs) from a Canadian ICU and the 2021 PhysioNet/Computing in Cardiology Challenge were used to conduct the experiments. Multiple training configurations were tested, ranging from zero-shot inference to transfer learning. Results: On average and across both datasets, ECG FMs performed best, followed by DL, then feature-based classifiers. The model that achieved the top F1 score on our ICU test set was ECG-FM through a transfer learning strategy (F1=0.89). Conclusion: This study demonstrates promising potential for using AI to build an automatic patient monitoring system. Significance: By publishing our labelled ICU dataset (LinkToBeAdded) and performance benchmarks, this work enables the research community to continue advancing the state-of-the-art in AF detection in the ICU.

Sejeong Jang, Joo Heung Yoon, Hyo Kyung Lee

Intensive care unit (ICU) data are highly irregular, heterogeneous, and temporally fragmented, posing challenges for generalizable clinical prediction. We present PULSE-ICU, a self-supervised foundation model that learns event-level ICU representations from large-scale EHR sequences without resampling or manual feature engineering. A unified embedding module encodes event identity, continuous values, units, and temporal attributes, while a Longformer-based encoder enables efficient modeling of long trajectories. PULSE-ICU was fine-tuned across 18 prediction tasks, including mortality, intervention forecasting, and phenotype identification, achieving strong performance across task types. External validation on eICU, HiRID, and P12 showed substantial improvements with minimal fine-tuning, demonstrating robustness to domain shift and variable constraints. These findings suggest that foundation-style modeling can improve data efficiency and adaptability, providing a scalable framework for ICU decision support across diverse clinical environments.

Glenn Larsson, Sanna Larsson, Viktoria Strand et al.

Abstract Background Pediatric trauma patients constitute a significant portion of the trauma population treated by Swedish Emergency Medical Services (EMS), and trauma remains a notable cause of death among Swedish children. Previous research has identified potential challenges in prehospital assessments and interventions for pediatric patients. In Sweden, there is limited information available regarding pediatric trauma patients in the EMS. The aim of this study was to investigate the prevalence of pediatric trauma patients within the Swedish EMS and describe the prehospital assessments, interventions, and clinical outcomes. Methods This retrospective observational study was conducted in a region of Southwestern Sweden. A random sample from ambulance and hospital records from the year 2019 was selected. Inclusion criteria were children aged 0–16 years who were involved in trauma and assessed by EMS clinicians. Results A total of 440 children were included in the study, representing 8.4% of the overall trauma cases. The median age was 9 years (IQR 3–12), and 60.5% were male. The leading causes of injury were low (34.8%) and high energy falls (21%), followed by traffic accidents. The children were assessed as severely injured in 4.5% of cases. A quarter of the children remained at the scene after assessment. Complete vital signs were assessed in 29.3% of children, and 81.8% of children were assessed according to the ABCDE structure. The most common intervention performed by prehospital professionals was the administration of medication. The mortality rate was 0.2%. Conclusions Pediatric trauma cases accounted for 8.4% of the overall trauma population with a variations in injury mechanisms and types. Vital sign assessments were incomplete for a significant proportion of children. The adherence to the ABCDE structure, however, was higher. The children remained at the scene after assessment requires further investigation for patient safety.

Viviane Donner, Mathieu Affaticati, Elodie Izydorczyk et al.

Abstract This case illustrates chest scars after piston-based chest compression device resuscitation and raises the awareness of the potential benefits of following up survivors of critical illness.

Daniel Mercader, Rebecca G. Theophanous

Background: Prostate abscess differs from prostatitis as a complicated infection requiring appropriate early treatment. It typically presents with urinary symptoms plus rectal or pelvic pain in middle-aged or older men. Diabetic, immunosuppressed, or patients with urological procedures are at higher risk for serious infection. If untreated, prostate abscess can progress to critical illness including sepsis and death, thus early diagnosis and treatment is key. Case report: A middle-aged male with diabetes, hypertension, emphysema, and hypothyroidism presented with severe constipation for one week but no urinary symptoms, fever, or vomiting. On examination, he had mild abdominal distension without tenderness, decreased bowel sounds, and a normal external rectal exam. Computed tomography scan demonstrated prostatomegaly and a large 5.2cm prostate abscess with multiple lobulations causing mass effect on the distal colon, thus blood cultures were sent, intravenous antibiotics started, and urology consulted. The patient was admitted for continued antibiotic treatment and underwent surgical transurethral resection with urology the next day. A foley catheter was maintained for seven days, with improvement until hospital discharge 3 days later, with oral antibiotics and close urology clinic follow up. Why should an emergency medicine physician be aware of this?: Prostate abscess is difficult to diagnose clinically and can lead to severe illness without early recognition and treatment. Patients may present with pelvic or rectal pain plus fever or urinary symptoms. Urgent antibiotic therapy is key, and many patients require urology consultation for surgical or procedural management.

Walter S. Mathis, Maria Ferrara, John Cahill et al.

This paper presents TimelinePTC, a web-based tool developed to improve the collection and analysis of Pathways to Care (PTC) data in first episode psychosis (FEP) research. Accurately measuring the duration of untreated psychosis (DUP) is essential for effective FEP treatment, requiring detailed understanding of the patient's journey to care. However, traditional PTC data collection methods, mainly manual and paper-based, are time-consuming and often fail to capture the full complexity of care pathways. TimelinePTC addresses these limitations by providing a digital platform for collaborative, real-time data entry and visualization, thereby enhancing data accuracy and collection efficiency. Initially created for the Specialized Treatment Early in Psychosis (STEP) program in New Haven, Connecticut, its design allows for straightforward adaptation to other healthcare contexts, facilitated by its open-source codebase. The tool significantly simplifies the data collection process, making it more efficient and user-friendly. It automates the conversion of collected data into a format ready for analysis, reducing manual transcription errors and saving time. By enabling more detailed and consistent data collection, TimelinePTC has the potential to improve healthcare access research, supporting the development of targeted interventions to reduce DUP and improve patient outcomes.

Maria Petrillo, Daniel Valdenegro, Charles Rahal et al.

Informal carers provide the majority of care for people living with challenges related to older age, long-term illness, or disability. However, the care they provide often results in a significant income penalty for carers, a factor largely overlooked in the economics literature and policy discourse. Leveraging data from the UK Household Longitudinal Study, this paper provides the first robust causal estimates of the caring income penalty using a novel individual synthetic control based method that accounts for unit-level heterogeneity in post-treatment trajectories over time. Our baseline estimates identify an average relative income gap of up to 45%, with an average decrease of £162 in monthly income, peaking at £192 per month after 4 years, based on the difference between informal carers providing the highest-intensity of care and their synthetic counterparts. We find that the income penalty is more pronounced for women than for men, and varies by ethnicity and age.

Muyan Jiang, Ying Chen, Xin Chen et al.

A large fraction of total healthcare expenditure occurs due to end-of-life (EOL) care, which means it is important to study the problem of more carefully incentivizing necessary versus unnecessary EOL care because this has the potential to reduce overall healthcare spending. This paper introduces a principal-agent model that integrates a mixed payment system of fee-for-service and pay-for-performance in order to analyze whether it is possible to better align healthcare provider incentives with patient outcomes and cost-efficiency in EOL care. The primary contributions are to derive optimal contracts for EOL care payments using a principal-agent framework under three separate models for the healthcare provider, where each model considers a different level of risk tolerance for the provider. We derive these optimal contracts by converting the underlying principal-agent models from a bilevel optimization problem into a single-level optimization problem that can be analytically solved. Our results are demonstrated using a simulation where an optimal contract is used to price intracranial pressure monitoring for traumatic brain injuries.

Auke Elfrink, Iacopo Vagliano, Ameen Abu-Hanna et al.

We investigate different natural language processing (NLP) approaches based on contextualised word representations for the problem of early prediction of lung cancer using free-text patient medical notes of Dutch primary care physicians. Because lung cancer has a low prevalence in primary care, we also address the problem of classification under highly imbalanced classes. Specifically, we use large Transformer-based pretrained language models (PLMs) and investigate: 1) how \textit{soft prompt-tuning} -- an NLP technique used to adapt PLMs using small amounts of training data -- compares to standard model fine-tuning; 2) whether simpler static word embedding models (WEMs) can be more robust compared to PLMs in highly imbalanced settings; and 3) how models fare when trained on notes from a small number of patients. We find that 1) soft-prompt tuning is an efficient alternative to standard model fine-tuning; 2) PLMs show better discrimination but worse calibration compared to simpler static word embedding models as the classification problem becomes more imbalanced; and 3) results when training models on small number of patients are mixed and show no clear differences between PLMs and WEMs. All our code is available open source in \url{https://bitbucket.org/aumc-kik/prompt_tuning_cancer_prediction/}.

Kelsey Cotton, Kıvanç Tatar

The ethics of AI as both material and medium for interaction remains in murky waters within the context of musical and artistic practice. The interdisciplinarity of the field is revealing matters of concern and care, which necessitate interdisciplinary methodologies for evaluation to trouble and critique the inheritance of "residue-laden" AI-tools in musical applications. Seeking to unsettle these murky waters, this paper critically examines the example of Holly+, a deep neural network that generates raw audio in the likeness of its creator Holly Herndon. Drawing from theoretical concerns and considerations from speculative feminism and care ethics, we care-fully trouble the structures, frameworks and assumptions that oscillate within and around Holly+. We contribute with several considerations and contemplate future directions for integrating speculative feminism and care into musical-AI agent and system design, derived from our critical feminist examination.

Md. Zihad Bin Jahangir, Ruksat Hossain, Riadul Islam et al.

Medical imaging informatics is a rapidly growing field that combines the principles of medical imaging and informatics to improve the acquisition, management, and interpretation of medical images. This chapter introduces the basic concepts of medical imaging informatics, including image processing, feature engineering, and machine learning. It also discusses the recent advancements in computer vision and deep learning technologies and how they are used to develop new quantitative image markers and prediction models for disease detection, diagnosis, and prognosis prediction. By covering the basic knowledge of medical imaging informatics, this chapter provides a foundation for understanding the role of informatics in medicine and its potential impact on patient care.

Emma Chen, Aman Kansal, Julie Chen et al.

We propose the Multimodal Clinical Benchmark for Emergency Care (MC-BEC), a comprehensive benchmark for evaluating foundation models in Emergency Medicine using a dataset of 100K+ continuously monitored Emergency Department visits from 2020-2022. MC-BEC focuses on clinically relevant prediction tasks at timescales from minutes to days, including predicting patient decompensation, disposition, and emergency department (ED) revisit, and includes a standardized evaluation framework with train-test splits and evaluation metrics. The multimodal dataset includes a wide range of detailed clinical data, including triage information, prior diagnoses and medications, continuously measured vital signs, electrocardiogram and photoplethysmograph waveforms, orders placed and medications administered throughout the visit, free-text reports of imaging studies, and information on ED diagnosis, disposition, and subsequent revisits. We provide performance baselines for each prediction task to enable the evaluation of multimodal, multitask models. We believe that MC-BEC will encourage researchers to develop more effective, generalizable, and accessible foundation models for multimodal clinical data.

Şükrü Yorulmaz, Anıl Gökçe

Aim:Air transport is very useful for transporting patients between hospitals in the case of a trauma or illness that requires special care. Transporting trauma patients who require early intervention to large centers for effective treatment ensures both effective treatment and a reduction in mortality.Materials and Methods:In our study, a retrospective review was performed using data collected for cases transported by airway organized by the Ministry of Health between January 2020 and May 2021. Patients transported by plane and helicopter due to trauma were included in the study. The patients were examined in terms of reason for transport, gender, age, medical condition, cities of transport, route of transport, transport vehicle.Results:Two hundred and eighty-seven trauma patients were transferred, 125 by air ambulance and 162 by helicopter ambulance. Of the patients transported by plane, 103 were male and 22 were female. Among the number of patients transported by helicopter, 120 patients were male and 42 patients were female. The pediatric patients were 23 in patients transported by plane and 34 in helicopter. When the transported patients were evaluated in terms of indication; the most common indication for transportation of patients is multitrauma (blunt thoracic trauma, fracture) patients with 78 patients. Considering the major centers where patients were transferred, Ankara was in the first place with 107 patients. Considering the flight times, the average flight time for air transport was 77 minutes, and the average flight time for a helicopter ambulance was 69 minutes.Conclusion:Transporting patients by air is critical in countries such as Turkey, which has a large area and difficult geographical conditions. Transporting trauma patients who require early intervention to large centers for effective treatment ensures both effective treatment and a reduction in mortality. We think that our country’s successful air transport system plays a major role in the effective treatment of patients, thanks to its short average flight time and successful transport procedure.