Search Results (278)

Arthritis and arthrosis are prevalent joint diseases that cause pain and disability, and their early diagnosis is crucial for preventing irreversible damage. Conventional diagnostic methods such as X-ray, ultrasound, and MRI have limitations in early detection, prompting interest in alternative techniques. This work presents the design and clinical evaluation of a prototype device for non-invasive early diagnosis of arthritis (inflammatory joint disease) and arthrosis (osteoarthritis) using infrared thermography and deep neural networks. The portable prototype integrates a Raspberry Pi 4 microcomputer, an infrared thermal camera, and a touchscreen interface, all housed in a 3D-printed PLA enclosure. A custom Flask-based application enables two operational modes: (1) thermal image acquisition for training data collection, and (2) automated diagnosis using a pre-trained ResNet50 deep learning model. A clinical study was conducted at a university clinic in a temperature-controlled environment with 100 subjects (70% with arthritic conditions and 30% healthy). Thermal images of both hands (four images per hand) were captured for each participant, and all patients provided informed consent. The ResNet50 model was trained to classify three classes (healthy, arthritis, and arthrosis) from these images. Results show that the system can effectively distinguish healthy individuals from those with joint pathologies, achieving an overall test accuracy of approximately 64%. The model identified healthy hands with high confidence (100% sensitivity for the healthy class), but it struggled to differentiate between arthritis and arthrosis, often misclassifying one as the other. The prototype’s multiclass ROC (Receiver Operating Characteristic) analysis further showed excellent discrimination between healthy vs. diseased groups (AUC, Area Under the Curve ~1.00), but lower performance between arthrosis and arthritis classes (AUC ~0.60–0.68). Despite these challenges, the device demonstrates the feasibility of AI-assisted thermographic screening: it is completely non-invasive, radiation-free, and low-cost, providing results in real-time. In the discussion, we compare this thermography-based approach with conventional diagnostic modalities and highlight its advantages, such as early detection of physiological changes, portability, and patient comfort. While not intended to replace established methods, this technology can serve as an early warning and triage tool in clinical settings. In conclusion, the proposed prototype represents an innovative application of infrared thermography and deep learning for joint disease screening. With further improvements in classification accuracy and broader validation, such systems could significantly augment current clinical practice by enabling rapid and non-invasive early diagnosis of arthritis and arthrosis. Full article

Background/Objectives: The COVID-19 pandemic disrupted healthcare systems globally, with dental services significantly limited due to infection control measures. This study investigates the impact of the pandemic on the clinical presentation, management, and outcomes of odontogenic abscesses over three distinct periods. Methods: A retrospective study was conducted at University Clinical Hospital (Poznan, Poland), which included adult patients hospitalised for odontogenic infections between March 2019 and February 2022. The cohort comprised 101 patients (median age: 33 years; 59.41% male), with admissions distributed across pre-pandemic (37.62%), pandemic (19.80%), and post-pandemic (42.57%) periods. Clinical, biochemical, and radiographic data were analysed. Results: No statistically significant differences were found between periods for abscess severity, hospitalisation length, or inflammatory marker levels. Elevated procalcitonin (Rs = 0.289, p = 0.005), C-reactive protein (Rs = 0.385, p < 0.001), and body mass index (Rs = 0.253, p = 0.011) independently predicted longer hospital stays. In regression modelling, procalcitonin (β = 0.464, p = 0.001) and prior outpatient antibiotic use (β = 0.281, p = 0.038) were mainly associated with larger abscess volumes, while comorbidities (β = 0.262, p = 0.025), longer hospitalisation (β = 0.594, p = 0.001) and abscess volume (β = −0.294, p = 0.040) increased the risk of reoperation. Conclusions: The study highlights clinically important findings linked to delayed dental care and increased systemic inflammation related to the pandemic. Elevated procalcitonin and CRP levels provide prognostic information that can guide early triage, risk stratification, and decisions regarding surgical versus outpatient management. These findings emphasise the importance of maintaining essential dental services, implementing preventive strategies, and optimising management protocols to reduce the risk of severe infections and improve patient outcomes during healthcare disruptions. Full article

Background: Incarcerated patients with neurological complaints present substantial diagnostic and care-delivery challenges in emergency departments (EDs). We delineate the clinical spectrum, severity, and outcomes among incarcerated patients managed in an ED with an embedded neuro-emergency expert model. Methods: A retrospective observational study of adult ED visits for neurological symptoms was conducted from September 2018 to June 2025 at a government-designated regional emergency center serving multiple correctional facilities. Incarceration was confirmed in the electronic medical record. Extracted variables included demographics, chief complaint, comorbidities, triage and acuity scale, Glasgow Coma Scale (GCS), neuroimaging, ED diagnoses, and outcomes (hospital admission, ICU care, ED/in-hospital mortality). Results: Sixty-five patients were included (median age 57.0 years [IQR 47.0–64.5]; 95% male). Chief complaints were altered mental status (36.9%), hemiparesis (21.5%), and seizures (13.8%). On arrival, 40.0% had GCS ≤ 12, including 23.1% with severe impairment (GCS 3–8). Non-contrast head CT was obtained in 95.4% and diffusion-weighted MRI in 38.5%. Frequent diagnoses were psychiatric/functional neurological disorder (16.9%), metabolic encephalopathy (15.4%), and acute ischemic stroke (12.3%). Serious conditions (stroke, hypoxic brain injury, central nervous system infection, status epilepticus, and neuroleptic malignant syndrome) were diagnosed in 41.5%. Hospital admission occurred in 63.1% (ICU care in 47.7%); in-hospital mortality was 10.8%. Conclusions: ED visits by incarcerated individuals with neurological complaints were often linked to serious diagnoses, ICU use, and mortality, challenging assumptions of exaggeration. Over two in five had stroke, hypoxic brain injury, central nervous system infection, or status epilepticus. The findings support rapid, systematic, bias-aware evaluation with early neurological involvement, clear imaging triggers, safety protocol, and expedited transfers from correctional facilities. Full article

Anti-amyloid monoclonal antibodies have finally achieved their translational breakthrough after many years of unmet expectations. The FDA granted traditional approval to lecanemab in July 2023, and the European Medicines Agency approved it in late 2024 with specific genetic restrictions; meanwhile, donanemab received FDA approval in July 2024 and EMA marketing authorization just one month ago. These agents consistently clear cerebral amyloid and slow clinical decline modestly in early-stage, biomarker-confirmed Alzheimer’s disease (AD). On the other hand, they also create significant safety risks, including amyloid-related imaging abnormalities (ARIA) and substantial operational requirements for health systems that are already under pressure. Therefore, precise risk management based on APOE genotyping and the presence of cerebral amyloid angiopathy and cerebral microbleeds should be performed before therapy is initiated. The near-term agenda should prioritize the following areas of study: (1) biomarker-driven front-end triage (including emerging plasma assays); (2) ARIA-aware care pathways and shared decision making; (3) outcome-based coverage and rational pricing; (4) clinical trials that layer anti-amyloid therapy into combinatorial strategies targeting tau protein, neuroinflammation, and synaptic resilience. Full article

Background: Shock index (SI) is calculated by dividing heart rate (HR) by systolic blood pressure (sBP) and is a useful tool for predicting the prognosis of trauma patients. This study aimed to determine whether SI is useful in predicting mortality in patients undergoing emergency surgery for trauma. Methods: We analyzed 1657 patients who underwent emergency surgery for trauma. Patients were divided into SI < 1 and SI ≥ 1 groups and the Glasgow Coma Scale (GCS), Injury Severity Score (ISS), revised trauma score (RTS), Korean Triage and Acuity Scale (KTAS), transfusion amount, and mortality were compared. Binary logistic regression analysis was performed to identify factors associated with mortality. Results: There were significant differences in GCS, ISS, RTS, and KTAS in the SI ≥ 1 group compared to the SI < 1 group (all p-values < 0.001). In the SI < 1 cohort, the mortality rate was 11% (144/1283), and in the SI ≥ 1 group the mortality rate was 33% (125/374) (p < 0.001). Age, GCS, ISS, SI ≥ 1, and KTAS were determined to be predictors of mortality by logistic regression analysis. In particular, SI ≥ 1 group members exhibited a high association with elevated mortality (OR, 2.498; 95% CI, 1.708–3.652; p < 0.01). Conclusions: Although SI alone has limitations in predicting the patient’s prognosis, patients with SI ≥ 1 upon arrival at the emergency room are associated with mortality of patients undergoing emergency surgery for trauma, along with already known trauma assessment systems such as GCS, ISS, and KTAS. Full article

Background/Objectives: Intermediate Care Units (IMCUs) provide a level of care between general wards and Intensive Care Units (ICUs). While widely implemented across Europe, their use in the Italian internal medicine remains limited. To review the clinical effectiveness, organizational benefits, and policy relevance of IMCUs in Europe and assess opportunities and barriers to their implementation in the Italian hospital system. Methods: A narrative review of international and Italian literature from the origin of intermediate care models in 2025, with emphasis on patient outcomes, ICU utilization, cost-effectiveness, and governance models for IMCUs. Results: European studies consistently show that IMCUs improve patient flow, reduce ICU burden, and may reduce mortality among selected high-acuity patients. In Italy, respiratory and cardiac IMCUs have demonstrated similar benefits. However, general internal medicine IMCUs remain underdeveloped. The COVID-19 pandemic exposed structural gaps in the capacity for intermediate care. Recent legislative efforts (e.g., Decree-Law 34/2020) have aimed to expand sub-intensive care, but implementation is still heterogeneous. Conclusions: IMCUs are a cost-effective and clinically valuable strategy for managing non-ICU high-acuity patients. Structured integration of IMCUs into internal medicine in Italy could improve care quality and system efficiency. Clear triage protocols, adequate staffing, and strong organizational leadership are essential for success. Full article

Glaucoma remains a leading cause of irreversible blindness. We reviewed more than 150 peer-reviewed studies (January 2019–July 2025) that applied artificial or augmented intelligence (AI/AuI) to glaucoma care. Deep learning systems analyzing fundus photographs or OCT volumes routinely achieved area-under-the-curve values around 0.95 and matched—or exceeded—subspecialists in prospective tests. Sequence-aware models detected visual field worsening up to 1.7 years earlier than conventional linear trends, while a baseline multimodal network integrating OCT, visual field, and clinical data predicted the need for incisional surgery with AUROC 0.92. Offline smartphone triage in community clinics reached sensitivities near 94% and specificities between 86% and 94%, illustrating feasibility in low-resource settings. Large language models answered glaucoma case questions with specialist-level accuracy but still require human oversight. Key obstacles include algorithmic bias, workflow integration, and compliance with emerging regulations, such as the EU AI Act and FDA GMLP. With rigorous validation, bias auditing, and transparent change control, AI/AuI can augment—rather than replace—clinician expertise, enabling earlier intervention, tailored therapy, and more equitable access to glaucoma care worldwide. Full article

Introduction: Paramedics are increasingly being recognized as essential contributors to sports medicine, where their role extends beyond emergency response to prevention, planning, and collaboration with other medical professionals. Yet their scope of practice and effectiveness across sporting levels and regions remain insufficiently synthesized. Methods: This scoping review mapped international evidence on paramedics in sports medicine. Literature published in English between 2013 and 2023 was systematically searched in PubMed, Scopus, and ScienceDirect, and eligible studies were analyzed thematically. Thirty studies were included, spanning professional and amateur sports in North America, Europe, Asia, Oceania, and Africa. Results: The findings demonstrate that paramedics provide critical value across six domains. First, rapid emergency response, supported by innovations such as motorcycle-based ambulances, significantly reduced access times and improved survival rates. Second, preparedness and ongoing training, including physical fitness and interprofessional education, were shown to enhance effectiveness in demanding sporting environments. Third, collaboration with athletic trainers and other professionals improved on-field care and reduced unnecessary hospital transfers. Fourth, paramedics contributed to injury prevention programmes that lowered injury incidence and healthcare costs. Fifth, their involvement at mass gatherings ensured safety, streamlined triage, and reduced pressure on hospitals. Finally, evidence indicates that paramedic-led initiatives are cost-effective, generating both clinical and economic benefits. Conclusions: Paramedics play a multifaceted role in athlete care, emergency response, and injury prevention. Strengthening their integration through targeted training, protocol standardization, and equitable resource allocation can improve both athlete safety and system efficiency. Future research should focus on grassroots contexts and the use of paramedic-generated data to inform prevention and policy. Full article

In the face of growing demand for emergency treatment in mass casualty incidents involving acute hemorrhagic shock, disaster sites often suffer from limited search and rescue manpower and inadequate medical detection capabilities. With the rapid development of robot technology, the deployment of robots provides greater flexibility and reliability in disaster emergency response and search and rescue work, which can effectively address the shortage of search and rescue forces and medical resources at disaster sites. This paper introduces a snake-like robot designed for the rapid triage of casualties with hemorrhagic shock. Through a structural design combining active wheels and orthogonal joints, the robot integrates the advantages of high-speed mobility of wheeled robots with the high flexibility of jointed robots so as to adapt to the complex environments typical of search and rescue scenarios. Meanwhile, the end of the robot is equipped with a visible light camera, an infrared camera and a voice interaction system, which realizes the rapid triage of casualties with hemorrhagic shock by collecting visible light, infrared and voice dialog data of the casualties. Through Webots software simulation and outdoor site simulation experiments, seven indicators of the designed snake-like search and rescue robot are verified, including walking speed, minimum passable hole size, climbing angle, obstacle-surmounting height, passable step size, ditch-crossing width and turning radius, as well as the effectiveness of collecting visible light images, infrared images and voice dialog data of the casualties. Full article

The purpose of this perspective is to present a structured framework for delivering musculoskeletal (MSK) care via telerehabilitation, advocating for a fundamental shift in the mindset of physical therapists. Rather than viewing virtual care as a limited substitute, it is redefined as a clinically valid model that requires deliberate reengineering of traditional assessment and treatment practices. The article addresses three key questions: (1) How can MSK assessment and treatment be effectively delivered in the digital environment? (2) What clinical reasoning pathways can guide patient triage in virtual care? and (3) What value does telerehabilitation offer to both patients and therapists? The article outlines how MSK sessions can be conducted remotely through a systematic approach to preparation, subjective examination, and physical assessment, each adapted to both the constraints and opportunities of the digital environment. Core elements of in-person care are translated into telehealth-compatible formats, including visual observation, patient-guided special tests, and digitally administered patient-reported outcome measures. It further proposes clinical decision pathways that enable therapists to triage patients into three categories: those fully suitable for telehealth, those requiring hybrid care, and those needing referral. The value proposition of MSK telerehabilitation is discussed from both the patient and therapist perspectives, highlighting enhanced accessibility, efficiency, and patient empowerment. The article contrasts the in-person and telerehabilitation models, underscoring the elevated importance of communication, creativity, resourcefulness, and clinical reasoning in virtual contexts. Beyond current challenges such as regulatory ambiguity, reimbursement variability, and digital inequity, the article explores future directions for MSK care. These include integration of wearable technologies, AI-assisted assessments, and an evolving therapist role as a director of care within a digitally enabled system. Ultimately, this article offers not just a model for virtual MSK sessions, but a vision for sustainable, evidence-informed transformation in rehabilitation delivery. Full article

Artificial intelligence (AI) has emerged as a transformative technology in radiology, offering enhanced diagnostic accuracy, improved workflow efficiency and potential risk mitigation. However, its effectiveness in reducing clinical and occupational risks in radiology departments remains underexplored. This systematic review aimed to evaluate the current literature on AI applications in computed tomography (CT) radiology and their contributions to risk reduction. Following the PRISMA 2020 guidelines, a systematic search was conducted in PubMed, Scopus and Web of Science for studies published between 2021 and 2025 (the databases were last accessed on 15 April 2025). Thirty-four studies were included based on their relevance to AI in radiology and reported outcomes. Extracted data included study type, geographic region, AI application and type, role in clinical workflow, use cases, sensitivity and specificity. The majority of studies addressed triage (61.8%) and computer-aided detection (32.4%). AI was most frequently applied in chest imaging (47.1%) and brain haemorrhage detection (29.4%). The mean reported sensitivity was 89.0% and specificity was 93.3%. AI tools demonstrated advantages in image interpretation, automated patient positioning, prioritisation and measurement standardisation. Reported benefits included reduced cognitive workload, improved triage efficiency, decreased manual annotation and shorter exposure times. AI systems in CT radiology show strong potential to enhance diagnostic consistency and reduce occupational risks. The evidence supports the integration of AI-based tools to assist diagnosis, lower human workload and improve overall safety in radiology departments. Full article

Background: As means of addressing ongoing challenges in accessing publicly funded specialist care, new models of care have been trialled. One such approach is using physiotherapists in advance practice roles, who in collaboration with other health professionals, act as an initial orthopedic point of contact and coordinate care. This research investigated the impact of a model of care, the Spinal Virtual Clinic Model, implemented for the first time in South Australia, using advanced practice physiotherapists in a large metropolitan hospital in South Australia. Although formally named the “Spinal Virtual Clinic” by the health service, this model does not involve direct patient contact and differs from traditional virtual or telehealth clinics. Instead, it is best understood as a physiotherapy-led referral triage and management service. Methods: This research was conducted in two stages. Stage 1 was a retrospective clinical audit of sequential patients triaged to the Spinal Virtual Clinic, as well as a follow up audit to capture any subsequent engagement with the Orthopaedic Spinal Service following the initial Spinal Virtual Clinic correspondence. Data were descriptively analysed. In Stage 2, semi-structured interviews were conducted with patients from the Spinal Virtual Clinic to explore their perspectives on this model of care. The interviews were transcribed verbatim and independently analysed using thematic analysis. The sequential use of quantitative and qualitative approaches enabled us to both describe engagement with this model of care and better understand the underlying perspectives. Results: Three hundred and nine referrals were triaged to the physiotherapy-led spinal virtual clinic over a six-month period from 1 January 2021 to 30 June 2021. Majority of referrals were triaged as low acuity did not need formal spinal specialist review and could be managed safely in primary care. Therapist-led active management strategies (80.8%), trial of neuropathic medication (35.6%) closely followed by advice regarding targeted spinal injections (foraminal and epidural), were the most common conservative management strategies recommended. Only a small proportion needed surgical review. Interviews with eleven patients revealed that while many valued the convenience, timely advice, and reassurance offered by the service, others expressed confusion about the referral process and disappointment at not seeing a specialist. A key recommendation identified was improved communication, including providing patients with direct feedback alongside general practitioner correspondence. Conclusions: This research, underpinned by quantitative and qualitative research, has showcased the potential of this model of care, the spinal virtual clinic, to have a positive impact on improving access and reducing the burden on the health system for low acuity patients. As historical models of care become unsustainable and obsolete, alternative models of care can be implemented in health care settings where outpatient demand significantly exceeds capacity. Full article

Background and Objectives: Despite the potential benefits for the patient, aerospace interventions pose significant risks. Pre-hospital triage and patient transport are two essential elements for achieving an organized system of trauma. The advantages and disadvantages of using land transport from the scene of the accident to the trauma centers have been extensively studied, but there are gaps for air transport, and their exact level of efficiency is not known. Materials and Methods: The present study includes a total number of 77 patients, present at SMURD Galați air service for polytraumas caused by various mechanisms, with pluri-regional involvement. The identification of patients, as well as the selection of the most important anamnestic data, was performed after signing a confidentiality agreement; subsequently, all this information was introduced in centralized tables made in the statistical program IBM SPSS Statistics V24. Results: Out of the total of 77 polytraumatized patients who needed air transfer, an average age of 17.3 years will be noted, with a predominance of males in a 2:1 ratio. Most polytraumas are due to road accidents (74%) and patients with minimal tri-regional damage (51.4%). Conclusions: Taking into account the existing statistics in this research, it is important to implement prevention elements, designed based on the profile of the polytraumatized patient. Thus, accessing the most important characteristics of these patients can be an extremely important starting point in reducing the incidence of polytrauma or even patient deaths. Full article

Background: Weekend presentation to the emergency department (ED) has been associated with increased morbidity and mortality in various clinical settings. However, the literature is scant whether such an effect exists for patients presenting with COVID-19 infection. Additionally, comparative analyses of mortality predictors in COVID-19 patients evaluated at the emergency department need further exploration. Methods: This retrospective cohort study examined factors associated with mortality among adult patients (aged ≥ 18 years) who presented with COVID-19 to the emergency departments of five hospitals within the Johns Hopkins Health System (combined capacity: 2513 beds) between March 1 and 4 May 2020. Data were extracted from electronic health records. Multivariable logistic regression was utilized to assess the relationship between mortality and a range of variables, including sociodemographic characteristics, clinical presentation, laboratory parameters, pre-existing comorbidities, and weekend versus weekday presentation. Results: Of the 2767 patients, 685 (25%) presented to the emergency department on weekends. Compared to weekday presenters, weekend patients were more likely to be hospitalized (64%), and these patients had a mean symptom duration of 5 days (SD ± 6). Weekend presenters also exhibited higher rates of clinical frailty, dehydration, hypoxia, and respiratory distress upon arrival. In multivariable logistic regression analysis adjusting for sociodemographic characteristics, clinical risk factors, and laboratory findings, independent predictors of increased mortality included absence of a primary care provider (OR 3.47; 95% CI: 2.37–5.07), peripheral oxygen saturation (SpO₂) < 95% at presentation (OR 1.46; 95% CI: 1.001–2.12), and hyperglycemia (OR 2.13; 95% CI: 1.25–3.65). Notably, the presence of crackles on physical examination demonstrated a trend toward reduced mortality (OR 0.47; 95% CI: 0.24–0.92). Conclusions: While weekend presentation was associated with higher hospitalization rates among patients with COVID-19, it did not independently predict increased mortality. Absence of a primary care provider, hypoxia, and hyperglycemia at presentation emerged as strong, independent predictors of mortality in the ED setting. Race, gender, and obesity were not significantly associated with mortality in this cohort, warranting further investigation. These findings may support more effective triage and risk stratification strategies in current and future public health emergencies. Full article

Background: The emergency medical services (EMS) sector, as a complex system, presents substantial hurdles in providing excellent treatment while operating within limited resources, prompting greater adoption of artificial intelligence (AI) as a tool for improving operational efficiency. While AI models have proved beneficial in healthcare operations, there is limited explainability and interpretability, as well as a lack of data used in their application and technological advancement. Methods: The scoping review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for scoping reviews, using PubMed, IEEE Xplore, and Web of Science, with a procedure of double screening and extraction. The search included articles published from 2018 to the beginning of 2025. Studies were excluded if they did not explicitly identify an artificial intelligence (AI) component, lacked relevance to emergency department (ED) or prehospital contexts, failed to report measurable outcomes or evaluations, or did not exploit real-world data. We analyzed the data source used, clinical subclasses, AI domains, ML algorithms, their performance, as well as potential roles for large language models (LLMs) in future applications. Results: A comprehensive PRISMA-guided methodology was used to search academic databases, finding 1181 papers on prehospital emergency treatment from 2018 to 2025, with 65 articles identified after an extensive screening procedure. The results reveal a significant increase in AI publications. A notable technological advancement in the application of AI in EMS using different types of data was explored. Conclusions: These findings highlighted that AI and ML have emerged as revolutionary innovations with huge potential in the fields of healthcare and medicine. There are several promising AI interventions that can improve prehospital emergency care, particularly for out-of-hospital cardiac arrest and triage prioritization scenarios. Implications for EMS Practice: Integrating AI methods into prehospital care can optimize the use of available resources, as well as triage and dispatch efficiency. LLMs may have the potential to improve understanding and assist in decision-making under pressure in emergency situations by combining various forms of recorded data. However, there is a need to emphasize continued research and strong collaboration between AI experts and EMS physicians to ensure the safe, ethical, and effective integration of AI into EMS practice. Full article