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

Eduardo C. Garrido-Merchán

Foundational results in machine learning establish that all human labor may in principle be automatable. Without deliberate intervention, this trajectory risks concentrating productive capacity in a handful of corporations, resulting in techno-feudalism: mass economic redundancy, surveillance-based control and dependence on corporate benevolence for survival. To avert this outcome, this paper introduces anarchist automation, a rigorously defined sociotechnical framework grounded in the 200-year anarchist tradition from Godwin through Kropotkin to Bookchin for ensuring that full automation is decentralized and oriented toward universal care. Specifically, I state five formal hypotheses and six research objectives, present a formal definition through analytical categories of interdependent spheres, and propose the Liberation Stack as a layered technical architecture with explicit preconditions and gate conditions for each layer, incorporating crypto-economic coordination tools appropriated from the crypto-anarchist tradition for commons financing and governance. Furthermore, I introduce Universal Desired Resources as a post-monetary design principle that eliminates the material basis of intersectional oppression, and address the Mises-Hayek economic calculation problem by arguing that AI-based distributed optimization and federated preference elicitation can substitute for market price signals under conditions of material abundance. I develop a framework for progressive state dissolution through incremental, reversible commons-building compatible with existing democratic institutions. Empirical evidence from Linux, Mondragon and contemporary commons initiatives confirms that commons-based systems already operate at scale. Finally, I conclude with a phased roadmap specifying explicit assumptions, hard constraints, gate conditions between phases, and detailed limitations.

Toshinari Kawama, Toshihiro Hatakeyama, Takashi Sano et al.

Objective We investigated the possible association between serum lactate to albumin ratio upon hospital arrival and out-of-hospital cardiac arrest (OHCA) outcome. Methods Records from the Japanese Association for Acute Medicine–Out-of-Hospital Cardiac Arrest (JAAM-OHCA) Registry were used for this multicenter observational study. Enrolled patients were ≥18 years old with OHCA of medical etiology who were hospitalized after spontaneous circulation returned between June 1, 2014, and December 31, 2021. We excluded those with missing data or those who failed to meet predefined inclusion criteria. The primary outcome was 30-day survival with a favorable neurological outcome, defined as a cerebral performance category score of 1 or 2. Patients were divided into quartiles based on serum lactate to albumin ratios: ≤2.23 (quartile 1), >2.23 and ≤3.39 (quartile 2), >3.39 and ≤4.70 (quartile 3), and >4.70 (quartile 4). The multivariable logistic regression analysis included adjustment for multiple factors. Results Data from 4,413 patients were analyzed. A favorable neurological outcome was achieved by 558 of 1,104 patients (50.5%) in the first quartile, 240 of 1,111 patients (21.6%) in the second quartile, 96 of 1,096 patients (8.8%) in the third quartile, and 24 of 1,102 patients (2.2%) in the fourth quartile. Adjusted odds ratios (95% confidence intervals) for the primary outcome in the second, third, and fourth quartile compared with the first quartile were 0.33 (0.26–0.42), 0.19 (0.14–0.26), and 0.07 (0.04–0.11), respectively. Conclusion The study demonstrated that a lower lactate to albumin ratio was significantly associated with favorable neurological outcomes in patients with out-of-hospital cardiac arrest.

Thomas Saliba, Simone Giglioli, Sanjiva Pather et al.

Lumbar paraspinal compartment syndrome is a rare pathology, with only 40 reported cases resulting from an increase in pressure within the muscle compartment. Symptoms typically involve pain and sometimes muscular deficits. The typical patient is a man who has undergone strenuous exercise, with few cases linked to the use of recreational drugs, such as cocaine or ketamine. We report the case of a 25-year-old man presenting to the emergency room with severe diffuse back pain who had recently consumed large amounts of cocaine, ketamine, and alcohol. The patient had diffuse muscular pain, increased serum creatine kinase (CK) levels, and a negative noncontrast abdominal computed tomography (CT), leading to the suspicion of crush syndrome. Over the following days, the patient’s pain became more localized to the right paraspinal region, prompting a contrast-enhanced CT. This revealed signs of muscle swelling and edema of the paraspinal muscle, leading to a suspicion of compartment syndrome, which was confirmed by an intramuscular pressure measurement. The patient underwent a surgical fasciotomy. The patient went on to have an unremarkable recovery. Lumbar paraspinal compartment syndrome is exceedingly rare. Cocaine is known to cause rhabdomyolysis both indirectly, due to behavioral disturbances, and directly due to muscle toxicity. Similarly, ketamine use has also been associated with rhabdomyolysis. The rhabdomyolysis results in greatly increased CK levels, sometimes rising up to 100 00 U/L, which should normalize over the following days. A few cases of compartment syndrome, often localized in extremities, have been reported in patients presenting cocaine or ketamine-induced rhabdomyolysis. In this patient, the muscle swelling of the paraspinal muscle resulted in compartment syndrome. Patients who experience cocaine-related rhabdomyolysis have a tendency for nonspecific symptoms, which would match our patient’s initial presentation. Although radiology’s contribution to the diagnosis is limited, patients suffering from back pain or nonresolving rhabdomyolysis should be submitted to imaging, which may show signs of muscle swelling and edema on CT and magnetic resonance imaging. Diagnosis of compartment syndrome should be confirmed by measurement of muscle pressure, and if elevated, the patient should be proposed for fasciotomy.

Ravi Agarwala, MD

Muhammad Zubair, Muzammil Hussai, Mousa Ahmad Al-Bashrawi et al.

Multi-modal medical image fusion (MMIF) is increasingly recognized as an essential technique for enhancing diagnostic precision and facilitating effective clinical decision-making within computer-aided diagnosis systems. MMIF combines data from X-ray, MRI, CT, PET, SPECT, and ultrasound to create detailed, clinically useful images of patient anatomy and pathology. These integrated representations significantly advance diagnostic accuracy, lesion detection, and segmentation. This comprehensive review meticulously surveys the evolution, methodologies, algorithms, current advancements, and clinical applications of MMIF. We present a critical comparative analysis of traditional fusion approaches, including pixel-, feature-, and decision-level methods, and delves into recent advancements driven by deep learning, generative models, and transformer-based architectures. A critical comparative analysis is presented between these conventional methods and contemporary techniques, highlighting differences in robustness, computational efficiency, and interpretability. The article addresses extensive clinical applications across oncology, neurology, and cardiology, demonstrating MMIF's vital role in precision medicine through improved patient-specific therapeutic outcomes. Moreover, the review thoroughly investigates the persistent challenges affecting MMIF's broad adoption, including issues related to data privacy, heterogeneity, computational complexity, interpretability of AI-driven algorithms, and integration within clinical workflows. It also identifies significant future research avenues, such as the integration of explainable AI, adoption of privacy-preserving federated learning frameworks, development of real-time fusion systems, and standardization efforts for regulatory compliance.

Chang Han Low, Zhu Zhuo, Ziyue Wang et al.

Robotic-assisted surgery (RAS) introduces complex challenges that current surgical error detection methods struggle to address effectively due to limited training data and methodological constraints. Therefore, we construct MERP (Multi-class Error in Robotic Prostatectomy), a comprehensive dataset for error detection in robotic prostatectomy with frame-level annotations featuring six clinically aligned error categories. In addition, we propose CARES (Collaborative Agentic Reasoning for Error Detection in Surgery), a novel zero-shot clinically-informed and risk-stratified agentic reasoning architecture for multi-class surgical error detection. CARES implements adaptive generation of medically informed, error-specific Chain-of-Thought (CoT) prompts across multiple expertise levels. The framework employs risk-aware routing to assign error task to expertise-matched reasoning pathways based on complexity and clinical impact. Subsequently, each pathway decomposes surgical error analysis into three specialized agents with temporal, spatial, and procedural analysis. Each agent analyzes using dynamically selected prompts tailored to the assigned expertise level and error type, generating detailed and transparent reasoning traces. By incorporating clinically informed reasoning from established surgical assessment guidelines, CARES enables zero-shot surgical error detection without prior training. Evaluation demonstrates superior performance with 54.3 mF1 on RARP and 52.0 mF1 on MERP datasets, outperforming existing zero-shot approaches by up to 14% while remaining competitive with trained models. Ablation studies demonstrate the effectiveness of our method. The dataset and code will be publicly available.

Wenjing Lu, Yi Hong, Yang Yang

Vision foundation models have demonstrated strong generalization in medical image segmentation by leveraging large-scale, heterogeneous pretraining. However, they often struggle to generalize to specialized clinical tasks under limited annotations or rare pathological variations, due to a mismatch between general priors and task-specific requirements. To address this, we propose Uncertainty-informed Collaborative Learning (UnCoL), a dual-teacher framework that harmonizes generalization and specialization in semi-supervised medical image segmentation. Specifically, UnCoL distills both visual and semantic representations from a frozen foundation model to transfer general knowledge, while concurrently maintaining a progressively adapting teacher to capture fine-grained and task-specific representations. To balance guidance from both teachers, pseudo-label learning in UnCoL is adaptively regulated by predictive uncertainty, which selectively suppresses unreliable supervision and stabilizes learning in ambiguous regions. Experiments on diverse 2D and 3D segmentation benchmarks show that UnCoL consistently outperforms state-of-the-art semi-supervised methods and foundation model baselines. Moreover, our model delivers near fully supervised performance with markedly reduced annotation requirements.

Rajeshwari Mistri, Harsh Joshi, Nachiket Kapure et al.

Accurate fetal birth weight prediction is a cornerstone of prenatal care, yet traditional methods often rely on imaging technologies that remain inaccessible in resource-limited settings. This study presents a novel machine learning-based framework that circumvents these conventional dependencies, using a diverse set of physiological, environmental, and parental factors to refine birth weight estimation. A multi-stage feature selection pipeline filters the dataset into an optimized subset, demonstrating previously underexplored yet clinically relevant predictors of fetal growth. By integrating advanced regression architectures and ensemble learning strategies, the model captures non-linear relationships often overlooked by traditional approaches, offering a predictive solution that is both interpretable and scalable. Beyond predictive accuracy, this study addresses a question: whether birth weight can be reliably estimated without conventional diagnostic tools. The findings challenge entrenched methodologies by introducing an alternative pathway that enhances accessibility without compromising clinical utility. While limitations exist, the study lays the foundation for a new era in prenatal analytics, one where data-driven inference competes with, and potentially redefines, established medical assessments. By bridging computational intelligence with obstetric science, this research establishes a framework for equitable, technology-driven advancements in maternal-fetal healthcare.

Yuwen Chen, Zafer Yildiz, Qihang Li et al.

Manual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process. Recent advancements in foundation models for video object segmentation, such as Segment Anything Model 2 (SAM 2), offer a potential opportunity to significantly speed up the annotation process by manually annotating one or a few slices and then propagating target masks across the entire volume. However, the performance of SAM 2 in this context varies. Our experiments show that relying on a single memory bank and attention module is prone to error propagation, particularly at boundary regions where the target is present in the previous slice but absent in the current one. To address this problem, we propose Short-Long Memory SAM 2 (SLM-SAM 2), a novel architecture that integrates distinct short-term and long-term memory banks with separate attention modules to improve segmentation accuracy. We evaluate SLM-SAM 2 on four public datasets covering organs, bones, and muscles across MRI, CT, and ultrasound videos. We show that the proposed method markedly outperforms the default SAM 2, achieving an average Dice Similarity Coefficient improvement of 0.14 and 0.10 in the scenarios when 5 volumes and 1 volume are available for the initial adaptation, respectively. SLM-SAM 2 also exhibits stronger resistance to over-propagation, reducing the time required to correct propagated masks by 60.575% per volume compared to SAM 2, making a notable step toward more accurate automated annotation of medical images for segmentation model development.

Sanjay Basu, Sadiq Y. Patel, Parth Sheth et al.

Care coordination and population health management programs serve large Medicaid and safety-net populations and must be auditable, efficient, and adaptable. While clinical risk for outreach modalities is typically low, time and opportunity costs differ substantially across text, phone, video, and in-person visits. We propose a lightweight offline reinforcement learning (RL) approach that augments trained policies with (i) test-time learning via local neighborhood calibration, and (ii) inference-time deliberation via a small Q-ensemble that incorporates predictive uncertainty and time/effort cost. The method exposes transparent dials for neighborhood size and uncertainty/cost penalties and preserves an auditable training pipeline. Evaluated on a de-identified operational dataset, TTL+ITD achieves stable value estimates with predictable efficiency trade-offs and subgroup auditing.

Meredith B. Haag, Catlin H. Dennis, Steven McGaughey et al.

Introduction: The American College of Emergency Physicians supports community- and hospital-based programs that intervene to prevent firearm-related injury. To this end, the distribution of firearm locks or storage devices in the emergency department (ED) may help achieve this target. To inform secure firearm storage programs for households with children and firearms, we examined firearm storage practices, device preferences, and cost tolerance among parents/caregivers of children. Methods: Between April 2018–November 2019, we conducted and analyzed an in-person survey of 294 caregivers, aged ≥18, with both children and firearms in the home. Surveys assessed reasons for firearm ownership, storage practices and device preferences among five storage-device options, and prices participants were willing to pay for devices. Practices and preferences were examined by participant characteristics. We used logistic regression to estimate odds ratios and 95% confidence intervals for associations of interest. Results: Most participants (73%) reported personal protection as a reason for owning firearms, and nearly 80% owned at least one firearm storage device. Over half (55%) owned cable locks, but only 36% of owners reported regularly using them. Rapid-access devices (electronic and biometric lockboxes) were less commonly owned (26%) but more likely to be regularly used (73%). The most highly rated storage device features were the following: the ability to store the firearm unloaded (87.3%); the ability to store the firearm loaded (79.1%); and device affordability (65%). Most participants (78%) preferred rapid-access devices over other options. Participants were willing to pay more for products that afforded rapid access to the firearm. Participants reported they would pay a median of $100 for a pushbutton rapid-access product ($80 retail), and $150 for a biometric lockbox ($210 retail). Conclusion: Understanding the storage practices and preferences among firearm-owning households with children can help inform ED injury-prevention screening and firearm safety practice implementation. Our results suggest that rapid-access devices may be the most preferable firearm storage devices for distribution by secure storage programs, and costs are likely minimal given parental/caregiver willingness to pay.

K. A. Mikaelyan, M. A. Petrova, E. V. Filimonova et al.

The aim of the study was to identify factors associated with hospital mortality in patients with COVID-19associated acute respiratory distress syndrome (ARDS) receiving veno-venous extracorporeal membrane oxygenation (VV-ECMO).Materials and methods. The retrospective study included data from the medical records of 123 patients treated in the intensive care unit (ICU) № 7 of the City Clinical Hospital № 52 of Moscow Department of Health. ECMO was initiated in all patients for respiratory indications according to current recommendations. A number of factors potentially associated with mortality were systematized and analyzed. Statistical processing to identify predictors of death included univariate analysis and calculation of odds ratio (OR), ROC analysis with calculation of area under the ROC curve (AUROC).Results. The resulting mortality rate was 87% (107/123), 11% (14/107) of all deaths occurred after weaning from ECMO. High VV-ECMO flow, delayed initiation of mechanical ventilation and ECMO therapy, and low pH at the time of ECMO initiation were identified as independent predictors of death in the study group. Low median albumin concentration and prolonged use of vasopressors were identified as predictors of death within 28 days of initiation of VV-ECMO. Development of acute kidney injury (AKI) requiring continuous renal replacement therapy (CRRT), septic shock and its recurrences, and the use of extracorporeal blood purification therapy for septic shock were found to be predictors of death during VV-ECMO therapy.Conclusion. High-flow VV-ECMO regimen, delayed initiation of mechanical ventilation and ECMO support, hypoalbuminemia, prolonged need for norepinephrine infusion, development of AKI requiring CRRT, septic shock occurrence and the number of its recurrences requiring extracorporeal blood purification therapy during VV-ECMO support were identified as predictors of death in patients with COVID-19-associated ARDS after initiation of VV-ECMO therapy.

Paolo Gabriel, Peter Rehani, Tyler Troy et al.

This study introduces an AI-driven platform for continuous and passive patient monitoring in hospital settings, developed by LookDeep Health. Leveraging advanced computer vision, the platform provides real-time insights into patient behavior and interactions through video analysis, securely storing inference results in the cloud for retrospective evaluation. The dataset, compiled in collaboration with 11 hospital partners, encompasses over 300 high-risk fall patients and over 1,000 days of inference, enabling applications such as fall detection and safety monitoring for vulnerable patient populations. To foster innovation and reproducibility, an anonymized subset of this dataset is publicly available. The AI system detects key components in hospital rooms, including individual presence and role, furniture location, motion magnitude, and boundary crossings. Performance evaluation demonstrates strong accuracy in object detection (macro F1-score = 0.92) and patient-role classification (F1-score = 0.98), as well as reliable trend analysis for the "patient alone" metric (mean logistic regression accuracy = 0.82 \pm 0.15). These capabilities enable automated detection of patient isolation, wandering, or unsupervised movement-key indicators for fall risk and other adverse events. This work establishes benchmarks for validating AI-driven patient monitoring systems, highlighting the platform's potential to enhance patient safety and care by providing continuous, data-driven insights into patient behavior and interactions.

Ahan Bhatt, Nandan Vaghela

This paper introduces Med-Bot, an AI-powered chatbot designed to provide users with accurate and reliable medical information. Utilizing advanced libraries and frameworks such as PyTorch, Chromadb, Langchain and Autogptq, Med-Bot is built to handle the complexities of natural language understanding in a healthcare context. The integration of llamaassisted data processing and AutoGPT-Q provides enhanced performance in processing and responding to queries based on PDFs of medical literature, ensuring that users receive precise and trustworthy information. This research details the methodologies employed in developing Med-Bot and evaluates its effectiveness in disseminating healthcare information.

Stefano Woerner, Christian F. Baumgartner

Data scarcity is a major limiting factor for applying modern machine learning techniques to clinical tasks. Although sufficient data exists for some well-studied medical tasks, there remains a long tail of clinically relevant tasks with poor data availability. Recently, numerous foundation models have demonstrated high suitability for few-shot learning (FSL) and zero-shot learning (ZSL), potentially making them more accessible to practitioners. However, it remains unclear which foundation model performs best on FSL medical image analysis tasks and what the optimal methods are for learning from limited data. We conducted a comprehensive benchmark study of ZSL and FSL using 16 pretrained foundation models on 19 diverse medical imaging datasets. Our results indicate that BiomedCLIP, a model pretrained exclusively on medical data, performs best on average for very small training set sizes, while very large CLIP models pretrained on LAION-2B perform best with slightly more training samples. However, simply fine-tuning a ResNet-18 pretrained on ImageNet performs similarly with more than five training examples per class. Our findings also highlight the need for further research on foundation models specifically tailored for medical applications and the collection of more datasets to train these models.

Bilash Saha, Md Saiful Islam, Abm Kamrul Riad et al.

Falls among the elderly are a major health concern, frequently resulting in serious injuries and a reduced quality of life. In this paper, we propose "BlockTheFall," a wearable device-based fall detection framework which detects falls in real time by using sensor data from wearable devices. To accurately identify patterns and detect falls, the collected sensor data is analyzed using machine learning algorithms. To ensure data integrity and security, the framework stores and verifies fall event data using blockchain technology. The proposed framework aims to provide an efficient and dependable solution for fall detection with improved emergency response, and elderly individuals' overall well-being. Further experiments and evaluations are being carried out to validate the effectiveness and feasibility of the proposed framework, which has shown promising results in distinguishing genuine falls from simulated falls. By providing timely and accurate fall detection and response, this framework has the potential to substantially boost the quality of elderly care.

Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang

Human anatomy is the foundation of medical imaging and boasts one striking characteristic: its hierarchy in nature, exhibiting two intrinsic properties: (1) locality: each anatomical structure is morphologically distinct from the others; and (2) compositionality: each anatomical structure is an integrated part of a larger whole. We envision a foundation model for medical imaging that is consciously and purposefully developed upon this foundation to gain the capability of "understanding" human anatomy and to possess the fundamental properties of medical imaging. As our first step in realizing this vision towards foundation models in medical imaging, we devise a novel self-supervised learning (SSL) strategy that exploits the hierarchical nature of human anatomy. Our extensive experiments demonstrate that the SSL pretrained model, derived from our training strategy, not only outperforms state-of-the-art (SOTA) fully/self-supervised baselines but also enhances annotation efficiency, offering potential few-shot segmentation capabilities with performance improvements ranging from 9% to 30% for segmentation tasks compared to SSL baselines. This performance is attributed to the significance of anatomy comprehension via our learning strategy, which encapsulates the intrinsic attributes of anatomical structures-locality and compositionality-within the embedding space, yet overlooked in existing SSL methods. All code and pretrained models are available at https://github.com/JLiangLab/Eden.

Revanth Krishna Senthilkumaran, Mridu Prashanth, Hrishikesh Viswanath et al.

Mass casualty incidents (MCIs) pose a significant challenge to emergency medical services by overwhelming available resources and personnel. Effective victim assessment is the key to minimizing casualties during such a crisis. We introduce ARTEMIS, an AI-driven Robotic Triage Labeling and Emergency Medical Information System, to aid first responders in MCI events. It leverages speech processing, natural language processing, and deep learning to help with acuity classification. This is deployed on a quadruped that performs victim localization and preliminary injury severity assessment. First responders access victim information through a Graphical User Interface that is updated in real-time. To validate our proposed algorithmic triage protocol, we used the Unitree Go1 quadruped. The robot identifies humans, interacts with them, gets vitals and information, and assigns an acuity label. Simulations of an MCI in software and a controlled environment outdoors were conducted. The system achieved a triage-level classification precision of over 74% on average and 99% for the most critical victims, i.e. level 1 acuity, outperforming state-of-the-art deep learning-based triage labeling systems. In this paper, we showcase the potential of human-robot interaction in assisting medical personnel in MCI events.

Dmitrijs Sokolovs, Ker Wei Tan

Shelsey W. Johnson, MD, Michael A. Garcia, MD, Emily K. Q. Sisson, MA et al.

OBJECTIVES:. To describe hospital variation in use of “guideline-based care” for acute respiratory distress syndrome (ARDS) due to COVID-19. DESIGN:. Retrospective, observational study. SETTING:. The Society of Critical Care Medicine’s Discovery Viral Infection and RESPIRATORY ILLNESS UNIVERSAL STUDY COVID-19 REGISTRY. PATIENTS:. Adult patients with ARDS due to COVID-19 between February 15, 2020, and April 12, 2021. INTERVENTIONS:. Hospital-level use of “guideline-based care” for ARDS including low-tidal-volume ventilation, plateau pressure less than 30 cm H2O, and prone ventilation for a Pao2/Fio2 ratio less than 100. MEASUREMENTS AND MAIN RESULTS:. Among 1,495 adults with COVID-19 ARDS receiving care across 42 hospitals, 50.4% ever received care consistent with ARDS clinical practice guidelines. After adjusting for patient demographics and severity of illness, hospital characteristics, and pandemic timing, hospital of admission contributed to 14% of the risk-adjusted variation in “guideline-based care.” A patient treated at a randomly selected hospital with higher use of guideline-based care had a median odds ratio of 2.0 (95% CI, 1.1–3.4) for receipt of “guideline-based care” compared with a patient receiving treatment at a randomly selected hospital with low use of recommended therapies. Median-adjusted inhospital mortality was 53% (interquartile range, 47–62%), with a nonsignificantly decreased risk of mortality for patients admitted to hospitals in the highest use “guideline-based care” quartile (49%) compared with the lowest use quartile (60%) (odds ratio, 0.7; 95% CI, 0.3–1.9; p = 0.49). CONCLUSIONS:. During the first year of the COVID-19 pandemic, only half of patients received “guideline-based care” for ARDS management, with wide practice variation across hospitals. Strategies that improve adherence to recommended ARDS management strategies are needed.