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

B. de Jonghe, T. Sharshar, J. Lefaucheur et al.

Moslem Rashidi, Luke B. Connelly, Gianluca Fiorentini

We study how a first heart-failure hospitalization, an adverse health shock, changes patients' care, and whether a nurse-led chronic-care program sustains those post-shock investments. Using linked population-wide administrative records from Italy's Romagna Local Health Authority (2017-2023), we anchor event time at each patient's first CHF admission and exploit staggered timing to estimate dynamic effects. The shock triggers a sharp post-discharge surge: beta-blocker adherence, cardiology follow-up, and echocardiography rise immediately, while emergency-room use spikes just before admission and then stabilizes. We then estimate the incremental impact of enrollment in the Nurse-led Program for Chronic Patients (NPCP) using the interaction-weighted event-study estimator for staggered adoption. Under conventional difference-in-differences inference, NPCP strengthens long-run preventive engagement, with little detectable change in emergency-room use. HonestDiD sensitivity analysis indicates these gains are economically meaningful but not statistically definitive under modest departures from parallel trends.

Sung-In Kim, Joonyoung Park, Bogoan Kim et al.

Home-based care (HBC) delivers medical and care services in patients' living environments, offering unique opportunities for patient-centered care. However, patient agency is often inadequately represented in shared HBC planning processes. Through 23 multi-stakeholder interviews with HBC patients, healthcare professionals, and care workers, alongside 60 hours of ethnographic observations, we examined how patient agency manifests in HBC and why this representation gap occurs. Our findings reveal that patient agency is not a static individual attribute but a relational capacity shaped through maintaining everyday continuity, mutual recognition from care providers, and engagement with material home environments. Furthermore, we identified that structured documentation systems filter out contextual knowledge, informal communication channels fragment patient voices, and doctor-centered hierarchies position patients as passive recipients. Drawing on these insights, we propose design considerations to bridge this representation gap and to integrate patient agency into shared HBC plans.

Gilda Pasta, Luciano Frassanito, Maria Maciariello et al.

Abstract Background Intraoperative fluid management during major abdominal oncologic surgery is complex and highly operator-dependent. Assisted Fluid Management (AFM) is an artificial intelligence–based decision support system designed to guide fluid challenges based on real-time Stroke Volume (SV) analysis. However, limited data are available on how AFM is adopted in routine clinical practice and how clinician interaction with the system evolves over time. Methods We conducted a retrospective observational study based on a prospectively maintained institutional database at a high-volume tertiary referral center. Adult patients undergoing major abdominal oncologic surgery with intraoperative AFM monitoring were included. Two consecutive time periods following AFM implementation were compared. Analyses were performed at the fluid-challenge level and focused on patterns of fluid challenge initiation (clinician-initiated vs AFM-suggested), hemodynamic effectiveness (SV response), and bolus characteristics, as markers of system adoption and learning curve. Postoperative clinical outcomes were not assessed. Results Fifty-nine patients were included, accounting for 404 fluid challenges. Over time, clinician-initiated boluses significantly decreased and AFM-suggested fluid challenges increased (p < 0.001). This shift was associated with higher overall effectiveness of fluid challenges and greater SV responses, particularly for AFM-suggested boluses, which showed a significant improvement in effectiveness and ΔSV over time (p < 0.05). Conclusions Progressive integration of AFM into routine anesthetic practice was associated with measurable changes in clinician behavior and improved physiological effectiveness of intraoperative fluid challenges over time, consistent with a learning curve effect. These findings support the role of AI-based decision support systems in promoting more consistent and physiologically targeted fluid management and provide a foundation for future prospective studies evaluating their impact on clinical outcomes.

Sijia Chen, Xiaomin Li, Mengxue Zhang et al.

Large language models (LLMs) are increasingly deployed in medical contexts, raising critical concerns about safety, alignment, and susceptibility to adversarial manipulation. While prior benchmarks assess model refusal capabilities for harmful prompts, they often lack clinical specificity, graded harmfulness levels, and coverage of jailbreak-style attacks. We introduce CARES (Clinical Adversarial Robustness and Evaluation of Safety), a benchmark for evaluating LLM safety in healthcare. CARES includes over 18,000 prompts spanning eight medical safety principles, four harm levels, and four prompting styles: direct, indirect, obfuscated, and role-play, to simulate both malicious and benign use cases. We propose a three-way response evaluation protocol (Accept, Caution, Refuse) and a fine-grained Safety Score metric to assess model behavior. Our analysis reveals that many state-of-the-art LLMs remain vulnerable to jailbreaks that subtly rephrase harmful prompts, while also over-refusing safe but atypically phrased queries. Finally, we propose a mitigation strategy using a lightweight classifier to detect jailbreak attempts and steer models toward safer behavior via reminder-based conditioning. CARES provides a rigorous framework for testing and improving medical LLM safety under adversarial and ambiguous conditions.

Naomi Akhras, Fares Antaki, Fannie Mottet et al.

Bias and inequity in palliative care disproportionately affect marginalised groups. Large language models (LLMs), such as GPT-4o, hold potential to enhance care but risk perpetuating biases present in their training data. This study aimed to systematically evaluate whether GPT-4o propagates biases in palliative care responses using adversarially designed datasets. In July 2024, GPT-4o was probed using the Palliative Care Adversarial Dataset (PCAD), and responses were evaluated by three palliative care experts in Canada and the United Kingdom using validated bias rubrics. The PCAD comprised PCAD-Direct (100 adversarial questions) and PCAD-Counterfactual (84 paired scenarios). These datasets targeted four care dimensions (access to care, pain management, advance care planning, and place of death preferences) and three identity axes (ethnicity, age, and diagnosis). Bias was detected in a substantial proportion of responses. For adversarial questions, the pooled bias rate was 0.33 (95% confidence interval [CI]: 0.28, 0.38); "allows biased premise" was the most frequently identified source of bias (0.47; 95% CI: 0.39, 0.55), such as failing to challenge stereotypes. For counterfactual scenarios, the pooled bias rate was 0.26 (95% CI: 0.20, 0.31), with "potential for withholding" as the most frequently identified source of bias (0.25; 95% CI: 0.18, 0.34), such as withholding interventions based on identity. Bias rates were consistent across care dimensions and identity axes. GPT-4o perpetuates biases in palliative care, with implications for clinical decision-making and equity. The PCAD datasets provide novel tools to assess and address LLM bias in palliative care.

Shashank Yadav, Vignesh Subbian

Interpretability plays a vital role in aligning and deploying deep learning models in critical care, especially in constantly evolving conditions that influence patient survival. However, common interpretability algorithms face unique challenges when applied to dynamic prediction tasks, where patient trajectories evolve over time. Gradient, Occlusion, and Permutation-based methods often struggle with time-varying target dependency and temporal smoothness. This work systematically analyzes these failure modes and supports learnable mask-based interpretability frameworks as alternatives, which can incorporate temporal continuity and label consistency constraints to learn feature importance over time. Here, we propose that learnable mask-based approaches for dynamic timeseries prediction problems provide more reliable and consistent interpretations for applications in critical care and similar domains.

Jiaqing Zhang, Miguel Contreras, Jessica Sena et al.

Patient mobility monitoring in intensive care is critical for ensuring timely interventions and improving clinical outcomes. While accelerometry-based sensor data are widely adopted in training artificial intelligence models to estimate patient mobility, existing approaches face two key limitations highlighted in clinical practice: (1) modeling the long-term accelerometer data is challenging due to the high dimensionality, variability, and noise, and (2) the absence of efficient and robust methods for long-term mobility assessment. To overcome these challenges, we introduce MELON, a novel multimodal framework designed to predict 12-hour mobility status in the critical care setting. MELON leverages the power of a dual-branch network architecture, combining the strengths of spectrogram-based visual representations and sequential accelerometer statistical features. MELON effectively captures global and fine-grained mobility patterns by integrating a pre-trained image encoder for rich frequency-domain feature extraction and a Mixture-of-Experts encoder for sequence modeling. We trained and evaluated the MELON model on the multimodal dataset of 126 patients recruited from nine Intensive Care Units at the University of Florida Health Shands Hospital main campus in Gainesville, Florida. Experiments showed that MELON outperforms conventional approaches for 12-hour mobility status estimation with an overall area under the receiver operating characteristic curve (AUROC) of 0.82 (95\%, confidence interval 0.78-0.86). Notably, our experiments also revealed that accelerometer data collected from the wrist provides robust predictive performance compared with data from the ankle, suggesting a single-sensor solution that can reduce patient burden and lower deployment costs...

Ruhul Amin Khalil, Kashif Ahmad, Hazrat Ali

The global ageing population necessitates new and emerging strategies for caring for older adults. In this article, we explore the potential for transformation in elderly care through Agentic Artificial Intelligence (AI), powered by Large Language Models (LLMs). We discuss the proactive and autonomous decision-making facilitated by Agentic AI in elderly care. Personalized tracking of health, cognitive care, and environmental management, all aimed at enhancing independence and high-level living for older adults, represents important areas of application. With a potential for significant transformation of elderly care, Agentic AI also raises profound concerns about data privacy and security, decision independence, and access. We share key insights to emphasize the need for ethical safeguards, privacy protections, and transparent decision-making. Our goal in this article is to provide a balanced discussion of both the potential and the challenges associated with Agentic AI, and to provide insights into its responsible use in elderly care, to bring Agentic AI into harmony with the requirements and vulnerabilities specific to the elderly. Finally, we identify the priorities for the academic research communities, to achieve human-centered advancements and integration of Agentic AI in elderly care. To the best of our knowledge, this is no existing study that reviews the role of Agentic AI in elderly care. Hence, we address the literature gap by analyzing the unique capabilities, applications, and limitations of LLM-based Agentic AI in elderly care. We also provide a companion interactive dashboard at https://hazratali.github.io/agenticai/.

Gökhan Eyüpoğlu, Mehmet Tatlı, Ebru Akkoç et al.

Objective: To evaluate the comparative effectiveness of adenosine, diltiazem, and metoprolol in achieving rate control in geriatric patients presenting with supraventricular tachyarrhythmia (SVT) and to identify clinical predictors associated with treatment success. Materials and Methods: This retrospective observational cohort study was conducted in a single tertiary emergency department between January 2021 and December 2024. Patients aged ≥65 years who presented with SVT and were treated with adenosine, diltiazem, or metoprolol were included. Patients were categorized into two groups based on successful rate control (heart rate <100 bpm). Demographics, comorbidities, laboratory parameters, and hemodynamic data were compared between the two groups. Univariate and multivariate logistic regression analyses were performed to determine the independent predictors of treatment success. Receiver operating characteristic (ROC) analysis was conducted to evaluate the prognostic performance of the identified variables. Results: A total of 167 patients were included, of whom 58 (34.7%) achieved rate control. There were no significant differences in age or sex distribution between the groups. Chronic kidney disease was significantly more prevalent in the non-rate control group (17.4% vs. 3.4%, p=0.009). Patients with successful rate control had significantly higher hemoglobin levels (13.6±2.5 vs. 12.7±2.5 g/dL, p=0.01) and glomerular filtration rates (60.7±27.3 vs. 58.7±25.5 mL/min, p=0.015). In the multivariate analysis, only hemoglobin remained an independent predictor of rate control success (odds ratio: 1.154, p=0.037). ROC analysis identified a hemoglobin cut-off of 12.9 g/dL, with a sensitivity of 62.1% and specificity of 63.9% (area under the curve: 0.622). Conclusion: Hemoglobin level is an independent predictor of successful pharmacologic rate control in geriatric patients with SVT. Personalized therapeutic strategies that incorporate hematologic status may optimize treatment outcomes in this vulnerable population. Further prospective studies are required to validate these findings.

I. A. Mandel, A. G. Yavorovsky, M. A. Vyzhigina et al.

Sufficient levels of nitric oxide (NO) ensure adequate blood flow to all organs and tissues. Despite the contradictory data on the role of endogenous NO as an organоprotector, NO insufflation is a promising direction, which is supported by evidence of modeling the protective effect on the myocardium, kidneys, and liver with exogenous NO in experimental and clinical studies. The largest number of studies have been conducted on models of ischemia-reperfusion injury in cardiovascular surgery. There are very few studies in abdominal and other non-cardiac surgery and they are mostly experimental. This review describes possible ways of implementing the organоprotective effect of NO, however, the exact mechanism remains not fully understood. One of the main links in the development of abdominal organ injury is intra-abdominal hypertension (IAH), which always accompanies laparoscopic surgeries and can last up to several hours. IAH causes ischemia of the kidneys and gastrointestinal mucosa with possible subsequent development of organ dysfunction. The degree of damage will depend not only on the duration of IAH but also on the patient’s premorbid background. The prognosis will be especially aggravated by the presence of atherosclerotic vascular lesions, which creates a preoperative background for hypoperfusion of visceral organs, which, due to the characteristics of vascularization, anatomical structure, and functioning, are very sensitive to the slightest disturbances in perfusion pressure and to the systemic inflammatory reaction, which will subsequently lead to an increase in vascular permeability, the formation of transcapillary leakage and interstitial edema, which is the beginning of organ dysfunction. Dysregulation of the mechanisms involved in NO production may be a link in the pathogenesis of the development of organ’s dysfunction, so maintaining adequate NO levels may be a target for therapy.

Alette E. E. de Jong, Wim E. Tuinebreijer, Helma W. C. Hofland et al.

Pain in critically ill adults with burns should be assessed using structured pain behavioural observation measures. This study tested the clinimetric qualities and usability of the behaviour pain scale (BPS) and the critical-care pain observation tool (CPOT) in this population. This prospective observational cohort study included 132 nurses who rated pain behaviour in 75 patients. The majority of nurses indicated that BPS and CPOT reflect background and procedural pain-specific features (63–72 and 87–80%, respectively). All BPS and CPOT items loaded on one latent variable (≥0.70), except for compliance ventilator and vocalisation for CPOT (0.69 and 0.64, respectively). Internal consistency also met the criterion of ≥0.70 in ventilated and non-ventilated patients for both scales, except for non-ventilated patients observed by BPS (0.67). Intraclass correlation coefficients (ICCs) of total scores were sufficient (≥0.70), but decreased when patients had facial burns. In general, the scales were fast to administer and easy to understand. Cut-off scores for BPS and CPOT were 4 and 1, respectively. In conclusion, both scales seem valid, reliable, and useful for the measurement of acute pain in ICU patients with burns, including patients with facial burns. Cut-off scores associated with BPS and CPOT for the burn population allow professionals to connect total scores to person-centred treatment protocols.

Hicham Messaoudi, Ahror Belaid, Douraied Ben Salem et al.

Over the last decade, convolutional neural networks have emerged and advanced the state-of-the-art in various image analysis and computer vision applications. The performance of 2D image classification networks is constantly improving and being trained on databases made of millions of natural images. However, progress in medical image analysis has been hindered by limited annotated data and acquisition constraints. These limitations are even more pronounced given the volumetry of medical imaging data. In this paper, we introduce an efficient way to transfer the efficiency of a 2D classification network trained on natural images to 2D, 3D uni- and multi-modal medical image segmentation applications. In this direction, we designed novel architectures based on two key principles: weight transfer by embedding a 2D pre-trained encoder into a higher dimensional U-Net, and dimensional transfer by expanding a 2D segmentation network into a higher dimension one. The proposed networks were tested on benchmarks comprising different modalities: MR, CT, and ultrasound images. Our 2D network ranked first on the CAMUS challenge dedicated to echo-cardiographic data segmentation and surpassed the state-of-the-art. Regarding 2D/3D MR and CT abdominal images from the CHAOS challenge, our approach largely outperformed the other 2D-based methods described in the challenge paper on Dice, RAVD, ASSD, and MSSD scores and ranked third on the online evaluation platform. Our 3D network applied to the BraTS 2022 competition also achieved promising results, reaching an average Dice score of 91.69% (91.22%) for the whole tumor, 83.23% (84.77%) for the tumor core, and 81.75% (83.88%) for enhanced tumor using the approach based on weight (dimensional) transfer. Experimental and qualitative results illustrate the effectiveness of our methods for multi-dimensional medical image segmentation.

M. AbdulRazek, G. Khoriba, M. Belal

Medical imaging is an essential tool for diagnosing and treating diseases. However, lacking medical images can lead to inaccurate diagnoses and ineffective treatments. Generative models offer a promising solution for addressing medical image shortage problems due to their ability to generate new data from existing datasets and detect anomalies in this data. Data augmentation with position augmentation methods like scaling, cropping, flipping, padding, rotation, and translation could lead to more overfitting in domains with little data, such as medical image data. This paper proposes the GAN-GA, a generative model optimized by embedding a genetic algorithm. The proposed model enhances image fidelity and diversity while preserving distinctive features. The proposed medical image synthesis approach improves the quality and fidelity of medical images, an essential aspect of image interpretation. To evaluate synthesized images: Frechet Inception Distance (FID) is used. The proposed GAN-GA model is tested by generating Acute lymphoblastic leukemia (ALL) medical images, an image dataset, and is the first time to be used in generative models. Our results were compared to those of InfoGAN as a baseline model. The experimental results show that the proposed optimized GAN-GA enhances FID scores by about 6.8\%, especially in earlier training epochs. The source code and dataset will be available at: https://github.com/Mustafa-AbdulRazek/InfoGAN-GA.

Hankyu Jang, Sulyun Lee, D. M. Hasibul Hasan et al.

As hospitals move towards automating and integrating their computing systems, more fine-grained hospital operations data are becoming available. These data include hospital architectural drawings, logs of interactions between patients and healthcare professionals, prescription data, procedures data, and data on patient admission, discharge, and transfers. This has opened up many fascinating avenues for healthcare-related prediction tasks for improving patient care. However, in order to leverage off-the-shelf machine learning software for these tasks, one needs to learn structured representations of entities involved from heterogeneous, dynamic data streams. Here, we propose DECENT, an auto-encoding heterogeneous co-evolving dynamic neural network, for learning heterogeneous dynamic embeddings of patients, doctors, rooms, and medications from diverse data streams. These embeddings capture similarities among doctors, rooms, patients, and medications based on static attributes and dynamic interactions. DECENT enables several applications in healthcare prediction, such as predicting mortality risk and case severity of patients, adverse events (e.g., transfer back into an intensive care unit), and future healthcare-associated infections. The results of using the learned patient embeddings in predictive modeling show that DECENT has a gain of up to 48.1% on the mortality risk prediction task, 12.6% on the case severity prediction task, 6.4% on the medical intensive care unit transfer task, and 3.8% on the Clostridioides difficile (C.diff) Infection (CDI) prediction task over the state-of-the-art baselines. In addition, case studies on the learned doctor, medication, and room embeddings show that our approach learns meaningful and interpretable embeddings.

Raphael Emberger, Jens Michael Boss, Daniel Baumann et al.

Patient monitoring in intensive care units, although assisted by biosensors, needs continuous supervision of staff. To reduce the burden on staff members, IT infrastructures are built to record monitoring data and develop clinical decision support systems. These systems, however, are vulnerable to artifacts (e.g. muscle movement due to ongoing treatment), which are often indistinguishable from real and potentially dangerous signals. Video recordings could facilitate the reliable classification of biosignals using object detection (OD) methods to find sources of unwanted artifacts. Due to privacy restrictions, only blurred videos can be stored, which severely impairs the possibility to detect clinically relevant events such as interventions or changes in patient status with standard OD methods. Hence, new kinds of approaches are necessary that exploit every kind of available information due to the reduced information content of blurred footage and that are at the same time easily implementable within the IT infrastructure of a normal hospital. In this paper, we propose a new method for exploiting information in the temporal succession of video frames. To be efficiently implementable using off-the-shelf object detectors that comply with given hardware constraints, we repurpose the image color channels to account for temporal consistency, leading to an improved detection rate of the object classes. Our method outperforms a standard YOLOv5 baseline model by +1.7% mAP@.5 while also training over ten times faster on our proprietary dataset. We conclude that this approach has shown effectiveness in the preliminary experiments and holds potential for more general video OD in the future.

Dennis Zyska, Nils Dycke, Jan Buchmann et al.

Recent years have seen impressive progress in AI-assisted writing, yet the developments in AI-assisted reading are lacking. We propose inline commentary as a natural vehicle for AI-based reading assistance, and present CARE: the first open integrated platform for the study of inline commentary and reading. CARE facilitates data collection for inline commentaries in a commonplace collaborative reading environment, and provides a framework for enhancing reading with NLP-based assistance, such as text classification, generation or question answering. The extensible behavioral logging allows unique insights into the reading and commenting behavior, and flexible configuration makes the platform easy to deploy in new scenarios. To evaluate CARE in action, we apply the platform in a user study dedicated to scholarly peer review. CARE facilitates the data collection and study of inline commentary in NLP, extrinsic evaluation of NLP assistance, and application prototyping. We invite the community to explore and build upon the open source implementation of CARE.

Mayuri Gupta, Avani Tiwari, Aditi Lather

Abstract Background Protein C deficiency is a rare genetic disorder with varying severity of symptoms and disease. The disorder may vary in presentation from a complete symptomless state to a less severe form like venous thromboembolism. The most severe form of disease is a rare condition called neonatal purpura fulminans (NPF) which is characterized with sudden progressive dermal hemorrhage and necrosis due to vascular thrombosis and disseminated intravascular coagulation. In contrast, congenital atrial and ventricular septal defects are the commonest congenital heart diseases found in pediatric population. An infant presenting with systemic vascular thromboembolism secondary to protein C deficiency along with the cardiac septal defects posted for surgery will be a very challenging task to manage in perioperative period. Also, physiological mechanisms during perioperative period and surgery will promote thromboembolism leading to worsening of the situation further. So, perioperative management of such patient pose a great challenge to the anaesthesiologist. Due to rarity of the condition, there is very limited literature available. Case presentation We report the perioperative management of a 2-month-old child suffering with neonatal purpura fulminans with atrial and ventricular septal cardiac defect, scheduled for bilateral foot amputation. The patient was a diagnosed with complete occlusion of abdominal aorta leading to foot gangrene. After initiation of anticoagulant therapy, symptoms were relieved and patient was posted for amputation of gangrenous feet. Conclusions There could be an increased risk of thromboembolism and bleeding due to protein C abnormality along with the chances of shunt reversal, paradoxical embolism, and other cardiac morbidities secondary to septal defects. Wise selection of anaesthetic agents like limiting the use of nitrous oxide, ketamine as much as possible to be considered. Conditions like tachycardia, hypotension, and hypothermia should also be prevented perioperatively as these could increase the chances of thrombosis.

Francesco Marrazzo, Stefano Spina, Francesco Zadek et al.

Phillip Sherlock, Herman T. Knopf, Robert Chapman et al.

The aggregate ability of child care providers to meet local demand for child care is linked to employment rates in many sectors of the economy. Amid growing concern regarding child care provider sustainability due to the COVID-19 pandemic, state and local governments have received large amounts of new funding to better support provider stability. In response to this new funding aimed at bolstering the child care market in Florida, this study was devised as an exploratory investigation into features of child care providers that lead to business longevity. In this study we used optimal survival trees, a machine learning technique designed to better understand which providers are expected to remain operational for longer periods of time, supporting stabilization of the child care market. This tree-based survival analysis detects and describes complex interactions between provider characteristics that lead to differences in expected business survival rates. Results show that small providers who are religiously affiliated, and all providers who are serving children in Florida's universal Prekindergarten program and/or children using child care subsidy, are likely to have the longest expected survival rates.