Search Results (482)

Data classification tasks based on deep neural networks and machine learning are increasingly used in different fields, such as medicine, finance, and data circulation. However, in these applications, the accuracy of predictions must be guaranteed, and the privacy and security of prediction data and models must be guaranteed. In an unsafe cloud environment, cloud users are reluctant to use the classification prediction tasks provided by the cloud. To solve these problems, this paper researches the data oversampling method and proposes the G-MSMOTE method, which can solve the oversampling problem of multiple minority classes in the data set, generate more diverse data, and solve the data imbalance problem. By improving the traditional FV and using CRT technology to improve coding efficiency, the cloud receives the user’s encrypted ciphertext, and the neural network completes the data prediction task in the ciphertext, thereby providing confidentiality for user data and model parameters under the semi-honest adversarial model, assuming the security of the underlying fully homomorphic encryption scheme and accepting the leakage of model architecture and ciphertext sizes. The feasibility of our method was demonstrated through experimental comparative analysis. We created unbalanced cases based on the MNIST dataset and performed comparative analysis in plain and ciphertext. In the balanced dataset, the model’s prediction accuracy in ciphertext reached 93.44%. In the unbalanced case, after preprocessing with our improved G-MSMOTE algorithm, the model’s prediction accuracy in ciphertext increased by at least 10%. These results show that our scheme can efficiently, accurately, and securely (under the semi-honest model) complete the data classification prediction task. Full article

Ophiocordyceps sinensis is a precious medicinal material with significant pharmacological and economic value. However, the visual similarity between its wild and cultivated forms poses a challenge for authentication. This study investigates the influence of specimen orientation on the accuracy of hyperspectral identification. Hyperspectral data were systematically acquired from four standard specimen orientations (left lateral, right lateral, dorsal, and ventral) for each sample. Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), and Fully Connected Neural Network (FCNN) models were trained and evaluated using both single-orientation and multi-orientation fused data. Results indicate that the LR model achieved superior and stable performance, with an average identification accuracy exceeding 98%. Crucially, for all tested models, no statistically significant difference in identification accuracy was observed across the different specimen orientations. This finding demonstrates that specimen orientation does not significantly influence identification accuracy. The conclusion was further corroborated in experiments using randomly orientation-fused datasets, in which model performance remained consistent and reliable. It is therefore concluded that precise specimen orientation control is unnecessary for the hyperspectral identification of Ophiocordyceps sinensis. This insight substantially simplifies the hardware design of dedicated identification devices by eliminating the need for complex orientation-fixing mechanisms and facilitating the standardization of operational protocols. The study provides a practical theoretical foundation for developing cost-effective, user-friendly, and widely applicable identification instruments for Ophiocordyceps sinensis and offers a reference for similar non-destructive testing applications involving anisotropic medicinal materials. Full article

Point-of-care ultrasound (POCUS) is an essential component of emergency medicine, enabling rapid bedside assessment across a wide spectrum of acute conditions. Its effectiveness, however, remains constrained by operator dependency, variable image quality, and time-critical decision-making. Recent advances in artificial intelligence (AI) offer opportunities to augment POCUS by supporting image acquisition, interpretation, and quantitative analysis. This narrative review synthesizes current evidence on AI-enhanced POCUS applications in emergency care, encompassing trauma, non-traumatic emergencies, integrated workflows, resource-limited settings, and education and training. Across trauma settings, AI-assisted POCUS has demonstrated promising performance for automated detection of pneumothorax, hemothorax, and free intraperitoneal fluid, supporting standardized eFAST examinations and rapid triage. In non-traumatic emergencies, AI-enabled cardiovascular, pulmonary, and abdominal applications provide automated measurements and pattern recognition that can approach expert-level performance when image quality is adequate. Integrated AI–POCUS systems and educational tools further highlight the potential to expand ultrasound access, support non-expert users, and standardize training. Nevertheless, important limitations persist, including limited generalizability, dataset bias, device heterogeneity, and uncertain impact on clinical decision-making and patient outcomes. In conclusion, AI-enhanced POCUS is transitioning from proof-of-concept toward early clinical integration in emergency medicine. While current evidence supports its role as a decision-support tool that may enhance consistency and efficiency, widespread adoption will require prospective multicentre validation, development of representative POCUS-specific datasets, vendor-agnostic solutions, and alignment with clinical, ethical, and regulatory frameworks. Full article

Background: Cigarette smoking remains one of the most important preventable causes of respiratory morbidity, exerting detrimental effects even in young adults. Medical students represent a particularly relevant population, as the lifestyle habits they adopt during their training years may influence both their personal health and professional credibility. Methods: We conducted a cross-sectional analysis of 264 medical students from the University of Medicine, Pharmacology, Science and Technology of Târgu-Mures, aged 18–30 years, stratified according to smoking status, type of tobacco product used, and lifestyle characteristics (athletic vs. sedentary). Standardized spirometry was performed to assess FVC, FEV₁, FEV₁/FVC ratio, PEF, and small airway flow parameters (MEF₂₅, MEF₅₀, MEF₇₅). Statistical comparisons between groups were performed using t-tests, Mann–Whitney U tests, chi-square tests, and correlation analyses, with p < 0.05 considered statistically significant. Results: Smokers demonstrated significantly lower values for FEV₁, PEF, and MEF parameters compared with non-smokers, confirming early functional impairment of both large and small airways. Within the smoking group, users of e-cigarettes or heated tobacco products exhibited more favorable FEV₁ and small airway flow values than conventional cigarette smokers. However, differences in FVC were less pronounced. Significantly, athletes consistently outperformed their sedentary peers across all respiratory parameters, regardless of smoking status, with markedly higher FEV₁, FVC, and MEF values and a lower prevalence of obstructive patterns. Cumulative smoking exposure (pack-years) was inversely associated with small airway function, whereas higher levels of physical activity were independently linked to a pronounced protective effect. Conclusions: Even in early adulthood, smoking is related to measurable declines in lung function, particularly affecting small airway dynamics. Although alternative products may appear less harmful than conventional cigarettes, they cannot be considered risk-free. Conversely, regular physical activity demonstrated a protective association in the case–control analysis, attenuating functional decline and supporting the preservation of long-term respiratory health. These findings underscore the importance of integrated prevention strategies in medical universities, combining smoking cessation initiatives with the systematic promotion of physical activity to safeguard the health of future physicians and reinforce their role as credible health advocates. Full article

Background/Objectives: Effective screening for oral cancer (OC) remains challenging. Inaccuracies contribute to delayed diagnosis and poor outcomes. Tobacco-related changes in oral mucosa may compromise the accuracy of oral screening approaches, and, in emerging “smart” screening modalities, they may overshadow the influence of other predictive variables. The objective of this study was to evaluate the screening accuracy of an imaging- and risk factor-based OC screening platform in individuals practicing different types of tobacco usage. Methods: 318 subjects who had previously screened positive for increased OC risk were recruited and sorted into “tobacco smoker”, “tobacco vaper”, “tobacco chewer”, “hookah user”, “multiple tobacco usage”, or “tobacco non-user” groups. Next, demographic information, risk factors, outcome of clinical examination, as well as AFI and pWLI were recorded using a prototype OC screening platform. The OC risk assessment outcome from the OC screening platform was compared to that from an oral medicine specialist. Results: The screening platform demonstrated high sensitivity in tobacco chewers and hookah users, and it also exceeded 90% in smokers, vapers, and multi-product users. In tobacco non-users, 80% screening sensitivity was recorded. Screening specificity was considerably better in tobacco non-users than in the tobacco-user groups, and low in tobacco chewers (33.3%), vapers (55.6%), and smokers (62.5%). Across all groups, agreement between the screening platform outcome and specialist evaluation exceeded 80%. Significant differences in probe accuracy were noted between tobacco non-users and users (p < 0.05), except for tobacco vapers. Conclusions: These findings highlight the need to consider the effects of type of tobacco use on the OC screening approach, and to integrate these variables into imaging-and risk-factor-based algorithms for OC screening. Full article

In clinical medicine it is of interest to know vitamin C blood levels. There are numerous variations in published sample preparation methods for quantifying vitamin C using HPLC. For the determination of vitamin C in human probes, the method needs to be simple, fast, and accurate. A systematic search in Pubmed was carried out to identify the methods for the quantification of vitamin C with HPLC in combination with a UV detector in human plasma. A total of 83 reports were screened, from which seven methods were selected and examined in detail. Tabular overviews compare the different sample preparation options, HPLC parameters, and validation criteria. Different reagents for protein precipitation and extraction are discussed. By allowing the user to see the criteria of interest at a glance, it can be used as a tool for the rapid development and establishment of a vitamin C determination method using HPLC. Full article

Honeybee products (HBPs), including honey, bee pollen, bee bread, royal jelly, propolis, beeswax, and bee brood, are increasingly used in food, nutraceutical, and cosmetic contexts. Because of their natural origin, HBPs can provoke allergic reactions ranging from localised dermatitis to life-threatening, systemic anaphylaxis. As the use of bee products for health purposes grows in apitherapy (a branch of alternative medicine), raising public awareness of their potential risks is essential. This narrative review synthesises the clinical manifestations of HBP allergy, culprit allergens present in each product, immunological mechanisms, diagnostic approaches, at-risk populations, and knowledge gaps. The analysis of the available literature suggests that, although relatively rarely, HPB may trigger allergic reactions, including anaphylactic shock. The sensitisation mechanism may be associated with both primary sensitisation and cross-reactivity and can be classified into type I (IgE-mediated) and type IV (T-cell-mediated). However, bee bread appears less allergenic than other HBPs, potentially due to lactic fermentation that can degrade allergenic proteins. Severe reactions following intake of bee bread have not been reported to date. Management of HBP allergic reactions centres on avoiding the products, educating about the risks, and providing more precise product labelling, specifying the allergen content. Individuals with atopy and beekeepers are at heightened risk of developing anaphylaxis; therefore, they should be particularly aware of the potential dangerous consequences of HPB use. Further research is needed to clarify the mechanisms of HBP allergies and improve safety for all users. Full article

Background: Vulnerable road users (VRUs), including children and older adults, face a high risk of fatal road traffic accidents (RTAs) due to limited protection and greater injury susceptibility. Romania reports some of the highest child and elderly RTA mortality rates in the European Union. This study analyzed medico-legal autopsies from the Timisoara Institute of Legal Medicine (TILM) between 2017 and 2021 to compare fatalities in these two groups and identify key risk factors. Methods: A retrospective analysis was conducted on autopsy records of children (0–17 years) and older adults (>70 years) who died in RTAs during the study period. Data on demographics, type of road user, traumatic injuries, cause of death, and accident circumstances were extracted and supplemented by police reports. Comparative statistical analyses were performed for categorical and continuous variables. Results: Among 395 RTA autopsies, 23 (5.8%) involved children and 51 (12.9%) older adults. Most child victims were passengers (56.5%), whereas elderly fatalities occurred mainly among pedestrians (33.3%) and cyclists (25.5%), with statistically significant differences between age groups. Polytrauma was the leading cause of death in both categories, though isolated cranio-cerebral trauma was proportionally more frequent in children. Crash circumstances also showed age-related patterns, with children more involved in high-energy collisions and older adults more frequently struck as pedestrians. Survival intervals showed a similar distribution across groups. Conclusions: Child and elderly RTA fatalities in Romania share common determinants, primarily driver-related behaviors and insufficient safety measures, while also exhibiting distinct age-related vulnerabilities. Autopsy-based data highlights these patterns and can guide targeted interventions such as stricter law enforcement, public education, and infrastructure improvements. Full article

Obesity affects approximately 40% of U.S. adults and is associated with increased cardiometabolic risk. While lifestyle interventions remain fundamental, pharmacologic therapies such as Semaglutide and tirzepatide have demonstrated significant weight reduction in clinical trials when titrated to maintenance doses. However, real-world adherence to recommended titration schedules remains unclear. This retrospective observational study evaluated adults prescribed Semaglutide (Wegovy^®) or Tirzepatide (Zepbound^®) for weight management between January 2021 and April 2025 through ICUBAcares, a pharmacist-led call center. Primary outcomes included the proportion of patients reaching the recommended maintenance dose and time required to do so. Secondary outcomes examined prescriber specialty patterns and monthly plan costs for non-optimized dosing. Among 739 medication courses, 52.9% of Semaglutide users reached the 2.4 mg dose versus 77.6% of tirzepatide users reaching 15 mg (p < 0.001). Median time to maintenance was significantly shorter for tirzepatide (32 days) than Semaglutide (143 days) (p < 0.001). Endocrinologists had the highest success rate for Tirzepatide (88.2%), while family medicine had the highest volume for both. Non-optimized dosing was associated with higher estimated monthly plan costs. These findings underscore the importance of improving adherence to titration protocols in real-world settings to maximize both clinical and economic outcomes in obesity pharmacotherapy. Full article

The Cutting Development Chamber (CDC) design is presented as an innovative solution to crucial human challenges, such as food and plant medicinal production. Unlike conventional propagation chambers, the CDC is a much more comprehensive research tool, specifically designed to optimize plant reproduction from cuttings. It maintains precise control over humidity, temperature, and lighting, which are essential parameters for plant development, thus maximizing the success rate, even in difficult-to-propagate species. Its modular design is one of its main strengths, allowing users to adapt the chamber to their specific needs, whether for research studies or for larger-scale propagation. The most distinctive feature of this chamber is its ability to collect detailed, labeled data, such as images of plant growth and environmental parameters that can be used in artificial intelligence tasks, which differentiate it from chambers that are solely used for propagation. A study that validated and calibrated the chamber design using cuttings of various species demonstrated its effectiveness through descriptive statistics, confirming that CDC is a powerful tool for research and optimization of plant growth. In validation experiments (Aloysia citrodora and Stevia rebaudiana), the system generated 6579 labeled images and 67,919 environmental records, providing a robust dataset that confirmed stable control of temperature and humidity while documenting cutting development. Full article

AI-based educational chatbots can expand access to learning, but many remain limited to text-only interfaces and fixed infrastructures, while purely generative responses raise concerns of reliability and consistency. In this context, we present ROboMC, a portable and multimodal system that combines a validated knowledge base with generative responses (OpenAI) and voice–text interaction, designed to enable both text and voice interaction, ensuring reliability and flexibility in diverse educational scenarios. The system, developed in Django, integrates two response pipelines: local search using normalized keywords and fuzzy matching in the LocalQuestion database, and fallback to the generative model GPT-3.5-Turbo (OpenAI, San Francisco, CA, USA) with a prompt adapted exclusively for Romanian and an explicit disclaimer. All interactions are logged in AutomaticQuestion for later analysis, supported by a semantic encoder (SentenceTransformer—paraphrase-multilingual-MiniLM-L12-v2’, Hugging Face Inc., New York, NY, USA) that ensures search tolerance to variations in phrasing. Voice interaction is managed through gTTS (Google LLC, Mountain View, CA, USA) with integrated audio playback, while portability is achieved through deployment on a Raspberry Pi 4B (Raspberry Pi Foundation, Cambridge, UK) with microphone, speaker, and battery power. Voice input is enabled through a cloud-based speech-to-text component (Google Web Speech API accessed via the Python SpeechRecognition library, (Anthony Zhang, open-source project, USA) using the Google Web Speech API (Google LLC, Mountain View, CA, USA; language = “ro-RO”)), allowing users to interact by speaking. Preliminary tests showed average latencies of 120–180 ms for validated responses on laptop and 250–350 ms on Raspberry Pi, respectively, 2.5–3.5 s on laptop and 4–6 s on Raspberry Pi for generative responses, timings considered acceptable for real educational scenarios. A small-scale usability study (N ≈ 35) indicated good acceptability (SUS ~80/100), with participants valuing the balance between validated and generative responses, the voice integration, and the hardware portability. Although system validation was carried out in the eHealth context, its architecture allows extension to any educational field: depending on the content introduced into the validated database, ROboMC can be adapted to medicine, engineering, social sciences, or other disciplines, relying on ChatGPT only when no clear match is found in the local base, making it a scalable and interdisciplinary solution. Full article

This review explores the transformative potential of graphene-based, non-invasive biochemical sensors in the context of real-time health monitoring and personalised medicine. Traditional diagnostic methods often involve invasive procedures that can be uncomfortable, pose risks, and limit the frequency of monitoring. In contrast, wearable sensors incorporating graphene offer a compelling alternative by enabling continuous, real-time tracking of physiological and biochemical signals with minimal intrusion. Graphene’s exceptional electrical conductivity, mechanical flexibility, biocompatibility, and high surface-area-to-volume ratio make it ideally suited for integration into skin-conformal sensor platforms. These properties not only enhance sensitivity and signal fidelity but also promote user comfort and long-term wearability, critical factors for the adoption of wearable health technologies. The discussion evaluates current developments in the design and deployment of graphene-based biosensors, with particular attention given to their role in managing chronic conditions, supporting preventative healthcare, and facilitating decentralised diagnostics. By bridging materials science and biomedical engineering, this review positions graphene as a key enabler in the shift towards more proactive, patient-centred healthcare models. The text also identifies ongoing challenges and future directions in sensor design, aiming to inform researchers working at the intersection of advanced materials and medical technology. Full article

Gastric diseases represent a significant challenge to global health. A comprehensive understanding of their complex molecular mechanisms, particularly the pathways of molecular progression in precancerous lesions, is essential for enhancing diagnosis and treatment. StomachDB, the first comprehensive multi-omics database dedicated to gastric diseases, has been developed to address these research needs. This database integrates 6 types of biological data: genomics, transcriptomics, emerging single-cell and spatial transcriptomics, proteomics, metabolomics, and therapeutic-related information. It encompasses 44 gastric-related pathologies, including various forms of gastric cancer, gastric ulcers, and gastritis, primarily involving humans and mice as model organisms. The database compiles approximately 2.5 million curated and standardized profiles, along with 268,394 disease-gene associations. The user-friendly analytics platform provides tools for browsing, querying, visualizing, and downloading data, facilitating systematic exploration of multi-omics features. This integrative approach addresses the limitations of single-omics analyses, such as data heterogeneity and insufficient analytical dimensions. Researchers can investigate the clinical significance of target genes (e.g., CDH1) across different omics levels and explore potential regulatory mechanisms. Furthermore, StomachDB emphasizes the discovery of therapeutic targets by cataloging interactions among chemical drugs, traditional herbal medicines, and probiotics. As an open-access resource, it serves as a powerful tool for studying complex biological interactions and regulatory mechanisms. Full article

The remarkable progress of artificial intelligence (AI) in recent years has significantly extended its application possibilities within the healthcare domain. AI has become more accessible to a wider range of healthcare personnel and service users, in particular due to the proliferation of Generative AI (GenAI). This study presents a bibliometric analysis of GenAI in healthcare. By analysing the Scopus database academic literature, our study explores the knowledge structure, emerging trends, and challenges of GenAI in healthcare. The results showed that GenAI is increasingly being adoption in developed countries, with major US institutions leading the way, and a large number of papers are being published on the topic in top-level academic venues. Our findings also show that there is a focus on particular areas of healthcare, with medical education and clinical decision-making showing active research, while areas such as emergency medicine remain poorly explored. Our results also show that while there is a focus on the benefits of GenAI for the healthcare industry, its limitations need to be acknowledged and addressed to facilitate its integration in clinical settings. The findings of this study can serve as a foundation for understanding the field, allowing academics, healthcare practitioners, educators, and policymakers to better understand the current focus within GenAI for healthcare, as well as highlighting potential application areas and challenges around accuracy, privacy, and ethics that must be taken into account when developing healthcare-focused GenAI applications. Full article

The deterioration of the global climate and accelerated urbanization have led to intense pressure on surface space resources. As a strategic development field, deep underground space has become a crucial direction for alleviating human habitation pressure. However, current research on deep underground space mostly focuses on fields such as geology and medicine, while the design of habitable environments lacks interdisciplinary integration and systematic approaches. Taking deep underground space as the research object, this study first clarifies the interdisciplinary research context through bibliometric analysis. Then, combined with geological data (ground temperature, groundwater, and ground stress, etc.) from major cities in China, it defines the characteristics of the in situ environment and the characteristics of the development and utilization of deep underground space. By comparing the habitable design experiences of extreme environments, such as space stations, Moon habitats, and desert survival modules, the study extracts five categories of design elements: natural conditions, construction status, social economy, users, and existing resources. Ultimately, it establishes a demand-oriented, five-dimensional habitable design methodology covering in situ environment adaptation, living support, medical and health services, resilience and flexibility, and existing space renovation. This research clarifies the differentiated design strategies for hundred-meter-level and kilometer-level deep underground spaces, providing theoretical support for the scientific development of deep underground space and serving as a reference for habitable design in other extreme environments. Full article