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

Şakir Hakan Aksu, Fikret Bildik, İsa Kılıçaslan et al.

Abstract Background Older adults account for an increasing proportion of emergency department (ED) visits and experience disproportionately high rates of short-term adverse outcomes. Accurate early risk stratification is therefore essential to guide monitoring, disposition, and resource allocation. Physiology-based early warning scores and geriatric risk-screening tools represent distinct approaches to prognostication, yet their comparative performance in older ED populations remains insufficiently defined. This study aimed to directly compare the prognostic accuracy of the Identification of Seniors at Risk (ISAR) questionnaire and the National Early Warning Score (NEWS) for predicting 30-day adverse outcomes in older adults presenting to the ED. Methods This prospective observational cohort study was conducted in a tertiary-care emergency department between January and March 2021. Consecutive patients aged ≥ 65 years were enrolled, with only index visits included. ISAR and NEWS were calculated at ED presentation according to standard definitions. The primary endpoint was a 30-day composite adverse outcome comprising unplanned ED revisits, hospital admission, intensive care unit admission, or all-cause mortality. Receiver operating characteristic (ROC) analyses were performed to assess discriminative performance, with areas under the curve (AUCs) compared using the DeLong test. Binary logistic regression models were used to estimate associations between predefined score thresholds (ISAR ≥ 2; NEWS ≥ 5) and outcomes, reported as odds ratios (ORs) with 95% confidence intervals. Results A total of 498 patients were included, with 48% experiencing at least one component of the composite outcome within 30 days. ISAR demonstrated superior discrimination for the composite endpoint compared with NEWS (AUC 0.747 vs. 0.650; DeLong p < 0.001) and was more accurate for predicting ED readmission, while NEWS demonstrated a higher point estimate for mortality prediction (AUC 0.869 vs. 0.792, DeLong p = 0.058). In logistic regression analyses, ISAR ≥ 2 was associated with a 5.85-fold increase in odds of adverse outcomes, whereas NEWS ≥ 5 conferred a 3.61-fold increase. Conclusions In older adults presenting to the ED, ISAR and NEWS capture different dimensions of risk and demonstrate distinct prognostic strengths. ISAR more effectively identifies broader vulnerability associated with composite adverse outcomes, while NEWS is superior for short-term mortality prediction. These findings highlight the importance of aligning risk stratification tools with the specific outcomes of interest in geriatric emergency care.

Baorong Shi, Bo Cui, Boyuan Jiang et al.

We present MedXIAOHE, a medical vision-language foundation model designed to advance general-purpose medical understanding and reasoning in real-world clinical applications. MedXIAOHE achieves state-of-the-art performance across diverse medical benchmarks and surpasses leading closed-source multimodal systems on multiple capabilities. To achieve this, we propose an entity-aware continual pretraining framework that organizes heterogeneous medical corpora to broaden knowledge coverage and reduce long-tail gaps (e.g., rare diseases). For medical expert-level reasoning and interaction, MedXIAOHE incorporates diverse medical reasoning patterns via reinforcement learning and tool-augmented agentic training, enabling multi-step diagnostic reasoning with verifiable decision traces. To improve reliability in real-world use, MedXIAOHE integrates user-preference rubrics, evidence-grounded reasoning, and low-hallucination long-form report generation, with improved adherence to medical instructions. We release this report to document our practical design choices, scaling insights, and evaluation framework, hoping to inspire further research.

Louise Rose, Peter Spronk, Stacey Skoretz

Ji Eun Kim, Sayul Kang

Alexander Adler, Samy Shelbaya, Sean McCormick

Introduction: Paralysis from hypokalemia commonly presents with generalized weakness; however, in rare cases it may present with unilateral or focal symptoms. Unilateral paralysis in hypokalemia is particularly challenging due to its mimicry of central nervous system (CNS) disorders such as ischemic stroke. Patients often undergo extensive and costly neuroimaging before a metabolic etiology is recognized. Case Report: A 19-year-old male presented to the emergency department reporting an abrupt onset of inability to hold things in his right hand. He denied any precipitating factors but did note that he was fasting for the Muslim holy month of Ramadan. On exam, the patient was seen to have absent grip strength in the right hand. The patient’s metabolic panel showed hypokalemia with a potassium of 2.4 millimoles per liter (mmol/L) (reference range: 3.5 to 5.2 mmol/L). Following neurology consultation, we determined that the patient’s focal weakness was secondary to hypokalemia, possibly triggered by his fasting. The patient was given potassium chloride 120 milliequivalents by mouth, and repeat potassium had increased to 3.2 mmol/L. The patient was re-evaluated and reported that his symptoms had completely resolved. Conclusion: Cases of focal weakness due to hypokalemia can occur. Primary CNS causes should be ruled out prior to making the diagnosis. Treatment should be focused on potassium repletion and avoidance of triggers. If hypokalemic periodic paralysis is a concern, neurology follow-up should be arranged for definitive diagnosis with electromyography.

Julian Hannah, Oluwasemire Adetoro, Adam J. R. Watson et al.

Abstract Background It is recognised that multiple attempts at intubation are associated with harm. However, it remains unclear whether video laryngoscopy (VL) significantly improves pre-hospital tracheal intubation success compared to direct laryngoscopy (DL) in critically ill patients. While operating theatre studies strongly favour VL, some pre-hospital studies suggest it may worsen outcomes. Methods This single-centre retrospective service evaluation included critically ill patients requiring pre-hospital tracheal intubation by a UK-based Helicopter Emergency Medical Service (HEMS) Hampshire & Isle of Wight Air Ambulance between 1st November 2018 and 22nd April 2024. This time period saw the introduction of VL with the option to use it versus DL. Patient demographics, intubation indication, anaesthetic drugs, and intubation technique (type of laryngoscopy, grade of view, number of attempts, and complications) were collated. The primary outcome was first-pass success, comparing VL and DL groups, with significance set at p = < 0.05. Results We included 1,279 patients (median age 56, 69% male), of whom 478 (37%) received VL and 803 (63%) received DL. The most common indication for intubation was low GCS (n = 477 (39%). Overall, First-pass success was 92% (n = 443) in the VL group and 84% (n = 799) in the DL group. Since the introduction of VL in June 2022, both the proportion of VL intubations and first-pass success rates have increased annually. Conclusion Our findings support the routine use of VL for pre-hospital tracheal intubation. Trial registration This project used routinely collected data and was registered with University Hospital Southampton as a service evaluation SEV/0735, date of registration 16/07/2024.

Joy Lai, Kelly Beaton, David Black et al.

Informal caregivers play a central role in enabling people living with dementia (PLwD) to remain at home, yet they face persistent challenges verifying whether daily tasks have been completed. Existing digital reminder systems prompt actions but rarely confirm outcomes, leaving caregivers to double-check tasks manually. This study explores how generative artificial intelligence (AI) might support caregiver-led task verification without displacing human judgment. We combined qualitative interviews with ten caregivers and one PLwD with a speculative simulation probe using a generative large language model to generate follow-up questions and flag responses for verification. Using template analysis, we identified three interrelated patterns of reasoning: detecting anomalies, constructing trustworthy evidence, and calibrating trust and control. These insights informed the Caregiver-in-the-Loop Task Verification (CLTV) framework, which models verification as a collaborative cycle of anomaly detection, evidence triangulation, AI-assisted summarization, and accountability circulation centered on caregiver oversight. CLTV advances human-AI collaboration theory by situating interpretability, trust, and control within the relational and emotional realities of dementia care and by offering design principles for transparent, adjustable, and context-aware AI support. We contribute a care-centered extension of human-AI collaboration theory, demonstrating how interpretability and trust can be operationalized through caregiver oversight.

Caner Özer, Patryk Rygiel, Bram de Wilde et al.

Artifacts pose a significant challenge in medical imaging, impacting diagnostic accuracy and downstream analysis. While image-based approaches for detecting artifacts can be effective, they often rely on preprocessing methods that can lead to information loss and high-memory-demand medical images, thereby limiting the scalability of classification models. In this work, we propose the use of implicit neural representations (INRs) for image quality assessment. INRs provide a compact and continuous representation of medical images, naturally handling variations in resolution and image size while reducing memory overhead. We develop deep weight space networks, graph neural networks, and relational attention transformers that operate on INRs to achieve image quality assessment. Our method is evaluated on the ACDC dataset with synthetically generated artifact patterns, demonstrating its effectiveness in assessing image quality while achieving similar performance with fewer parameters.

Jingyu Guo, Christos Matsoukas, Fredrik Strand et al.

In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on view-specific features, which can lead to trivial solutions. In this work, we introduce Random Token Fusion (RTF), a novel technique designed to enhance multi-view medical image analysis using vision transformers. By integrating randomness into the feature fusion process during training, RTF addresses the issue of overfitting and enhances the robustness and accuracy of diagnostic models without incurring any additional cost at inference. We validate our approach on standard mammography and chest X-ray benchmark datasets. Through extensive experiments, we demonstrate that RTF consistently improves the performance of existing fusion methods, paving the way for a new generation of multi-view medical foundation models.

Zhikai Wei, Wenhui Dong, Peilin Zhou et al.

Deep learning based methods often suffer from performance degradation caused by domain shift. In recent years, many sophisticated network structures have been designed to tackle this problem. However, the advent of large model trained on massive data, with its exceptional segmentation capability, introduces a new perspective for solving medical segmentation problems. In this paper, we propose a novel Domain-Adaptive Prompt framework for fine-tuning the Segment Anything Model (termed as DAPSAM) to address single-source domain generalization (SDG) in segmenting medical images. DAPSAM not only utilizes a more generalization-friendly adapter to fine-tune the large model, but also introduces a self-learning prototype-based prompt generator to enhance model's generalization ability. Specifically, we first merge the important low-level features into intermediate features before feeding to each adapter, followed by an attention filter to remove redundant information. This yields more robust image embeddings. Then, we propose using a learnable memory bank to construct domain-adaptive prototypes for prompt generation, helping to achieve generalizable medical image segmentation. Extensive experimental results demonstrate that our DAPSAM achieves state-of-the-art performance on two SDG medical image segmentation tasks with different modalities. The code is available at https://github.com/wkklavis/DAPSAM.

Satvik Tripathi, Liam Mutter, Meghana Muppuri et al.

This study introduces and evaluates the PRECISE framework, utilizing OpenAI's GPT-4 to enhance patient engagement by providing clearer and more accessible chest X-ray reports at a sixth-grade reading level. The framework was tested on 500 reports, demonstrating significant improvements in readability, reliability, and understandability. Statistical analyses confirmed the effectiveness of the PRECISE approach, highlighting its potential to foster patient-centric care delivery in healthcare decision-making.

Eric Xia, Yuling Yan, Martin J. Wainwright

Panel data consists of a collection of $N$ units that are observed over $T$ units of time. A policy or treatment is subject to staggered adoption if different units take on treatment at different times and remains treated (or never at all). Assessing the effectiveness of such a policy requires estimating the treatment effect, corresponding to the difference between outcomes for treated versus untreated units. We develop inference procedures that build upon a computationally efficient matrix estimator for treatment effects in panel data. Our routines return confidence intervals (CIs) both for individual treatment effects, as well as for more general bilinear functionals of treatment effects, with prescribed coverage guarantees. We apply these inferential methods to analyze the effectiveness of Medicaid expansion portion of the Affordable Care Act. Based on our analysis, Medicaid expansion has led to substantial reductions in uninsurance rates, has reduced infant mortality rates, and has had no significant effects on healthcare expenditures.

Anna Reithmeir, Veronika Spieker, Vasiliki Sideri-Lampretsa et al.

Image registration is fundamental in medical imaging applications, such as disease progression analysis or radiation therapy planning. The primary objective of image registration is to precisely capture the deformation between two or more images, typically achieved by minimizing an optimization problem. Due to its inherent ill-posedness, regularization is a key component in driving the solution toward anatomically meaningful deformations. A wide range of regularization methods has been proposed for both conventional and deep learning-based registration. However, the appropriate application of regularization techniques often depends on the specific registration problem, and no one-fits-all method exists. Despite its importance, regularization is often overlooked or addressed with default approaches, assuming existing methods are sufficient. A comprehensive and structured review remains missing. This review addresses this gap by introducing a novel taxonomy that systematically categorizes the diverse range of proposed regularization methods. It highlights the emerging field of learned regularization, which leverages data-driven techniques to automatically derive deformation properties from the data. Moreover, this review examines the transfer of regularization methods from conventional to learning-based registration, identifies open challenges, and outlines future research directions. By emphasizing the critical role of regularization in image registration, we hope to inspire the research community to reconsider regularization strategies in modern registration algorithms and to explore this rapidly evolving field further.

Cui Yuan, Yanyan Xiao, Fang Wang et al.

Gonçalo Guerreiro, Pedro Póvoa

Miguel Saro- Buendía, Pedro Suárez Urquiza, Judit Amigo González et al.

The lingual abscess is rare due to several protective mechanisms against infection in this location. Concretely, the abscess in the base of the tongue (posterior lingual abscess) is even more exceptional. Its prompt detection is crucial to avoid potentially fatal airway complications. To familiarize physicians with this condition, we report 2 cases of posterior lingual abscess. Both were referred to our emergency department due to minor oropharyngeal complaints. Finally, both were diagnosed and required surgical drainage. The clinical evolution was successful: both were discharged in less than 72 hours and follow-up one week later confirmed clinical recovery.

John Kristoffer Manicani Japzon, Halima O Mokamad-Romancap

Background An improvised air gun with marble bullets, locally known as “Jolen Gun”, is a type of home-made gun using Polyvinyl chloride (PVC) pipes and compressed air. It is mainly being used as a hunting tool in Central Mindanao. This “non-lethal” weapon has the potential in causing serious harm. There has been several incidents of minor injuries from this type of weapon in our institution but this is the first documented case of an improvised marble air-gun causing significant injury to the patient.Case report A child was brought to a rural tertiary center after being shot in the chest using an improvised gun with marble as bullet. On evaluation, the patient had a single gunshot wound approximately 2cm x 2cm in size on the posterior chest at the right paravertebral area of the 4th thoracic vertebra. There was no exit wound noted. Chest CT done showed a rounded radiopaque foreign body seen in the right upper lung field with gunshot fracture involving the posterior aspect of the 4th rib. There was also pulmonary contusion of the right upper lobe and a fluid density at the right posterior pleural space attributed to a hemothorax. Open thoracotomy, removal of foreign body, repair of lung injury and debridement was done. Patient had an unremarkable post-operative course and was subsequently discharged.Conclusion After extensive search of both local and international literatures, this appears to be the first case involving a penetrating chest injury from an improvised marble air-gun which has been treated successfully. Although this is a low-energy type of weapon, it still has the potential to cause significant harm to the body. Relevant laws should be made to against the use of this type of weapon to prevent similar injuries in the future.

Tania Johnston, Roxane Beaumont-Boileau, Joe Acker et al.

Introduction British Columbia Emergency Health Service trialled the use of intranasal (IN) ketamine given by Primary Care Paramedics (PCPs). Prior to this practice change, the PCPs had not performed weight-based drug calculations, given medications intranasally, nor been responsible for controlled and targeted substances. This study aimed to use the Capability, Opportunity, Motivation and Behaviour (COM-B) model and Theoretical Domain Framework (TDF) to identify enablers and barriers to implementing IN paramedic administered ketamine analgesia (iPAKA) for PCPs. Methods This was a parallel convergent mixed methods study with two phases. The quantitative phase consisted of longitudinal staff surveys to assess PCP knowledge and perceptions of ketamine and controlled and targeted substances policies. The qualitative phase involved staff focus groups on programme implementation. Descriptive statistics of survey results were integrated with coded focus group data and analysed using the COM-B model and TDF. Evidence-based behavioural change techniques were mapped to each TDF domain. Findings Our analysis revealed barriers and enablers across several TDF domains. Implementing ketamine was enabled by quality education, strong organisational support and the availability of cognitive aides. Trial success was attributed in part to participant's feelings of optimism and their increased job satisfaction. Key barriers included a knowledge gap involving drug dosage calculations, negative emotions associated with performance anxiety and a lack of field education and supervision to monitor paramedic practice. Conclusion The use of theoretical frameworks and models like COM-B/TDF serves to improve the sustainable implementation of behaviour and clinical practice change in paramedicine. When project teams use theory to guide design and implementation, they can systematically identify and target individual and organisational enablers and barriers to adopting routine practices. The iPAKA study reveals key barriers and facilitators in several TDF domains and presents theory-linked targeted behavioural techniques to support on-going implementation of PCP-administered IN ketamine for analgesia.

Mingchen Li, Rui Zhang

Recent advancements in language models (LMs) have led to the emergence of powerful models such as Small LMs (e.g., T5) and Large LMs (e.g., GPT-4). These models have demonstrated exceptional capabilities across a wide range of tasks, such as name entity recognition (NER) in the general domain. (We define SLMs as pre-trained models with fewer parameters compared to models like GPT-3/3.5/4, such as T5, BERT, and others.) Nevertheless, their efficacy in the medical section remains uncertain and the performance of medical NER always needs high accuracy because of the particularity of the field. This paper aims to provide a thorough investigation to compare the performance of LMs in medical few-shot NER and answer How far is LMs from 100\% Few-shot NER in Medical Domain, and moreover to explore an effective entity recognizer to help improve the NER performance. Based on our extensive experiments conducted on 16 NER models spanning from 2018 to 2023, our findings clearly indicate that LLMs outperform SLMs in few-shot medical NER tasks, given the presence of suitable examples and appropriate logical frameworks. Despite the overall superiority of LLMs in few-shot medical NER tasks, it is important to note that they still encounter some challenges, such as misidentification, wrong template prediction, etc. Building on previous findings, we introduce a simple and effective method called \textsc{RT} (Retrieving and Thinking), which serves as retrievers, finding relevant examples, and as thinkers, employing a step-by-step reasoning process. Experimental results show that our proposed \textsc{RT} framework significantly outperforms the strong open baselines on the two open medical benchmark datasets

Zhaoshuang Lu, Peng Qian, Dan Bi et al.

The application of artificial intelligence (AI) technology in the medical field has experienced a long history of development. In turn, some long-standing points and challenges in the medical field have also prompted diverse research teams to continue to explore AI in depth. With the development of advanced technologies such as the Internet of Things (IoT), cloud computing, big data, and 5G mobile networks, AI technology has been more widely adopted in the medical field. In addition, the in-depth integration of AI and IoT technology enables the gradual improvement of medical diagnosis and treatment capabilities so as to provide services to the public in a more effective way. In this work, we examine the technical basis of IoT, cloud computing, big data analysis and machine learning involved in clinical medicine, combined with concepts of specific algorithms such as activity recognition, behavior recognition, anomaly detection, assistant decision-making system, to describe the scenario-based applications of remote diagnosis and treatment collaboration, neonatal intensive care unit, cardiology intensive care unit, emergency first aid, venous thromboembolism, monitoring nursing, image-assisted diagnosis, etc. We also systematically summarize the application of AI and IoT in clinical medicine, analyze the main challenges thereof, and comment on the trends and future developments in this field.