Search Results (733)

This review provides an overview of existing accident prevention methods by monitoring the persons’ physiological state, observing movements, and physiological parameters. Firstly, different physiological parameters monitoring systems are introduced. Secondly, various systems dealing with position recognition on pressure sensing mats are presented. We conduct an in-depth literature search and quantitative analysis of papers published in this area and focus independently of the application (drivers, office and wheelchair users, etc.). Quantitative information about the number of subjects, investigated scenarios, sensor types, machine learning usage, and laboratory vs. real-world works is extracted. In posture recognition, most works recognize at least forward, backward, left and right movements on a seat. The remaining works use the pressure sensing mat for bedridden people. In physiological parameters measurement, most works detect the heart rate and often also add respiration rate recognition. Machine learning algorithms are used in most cases and are taking on an ever-greater importance for classification and regression problems. Although all solutions use different techniques, returning satisfactory results, none of them try to detect small movements, which can pose challenges in determining the optimal sensor topology and sampling frequency required to detect fine movements. For physiological measurements, there are lots of challenges to overcome in noisy environments, notably the detection of heart rate, blood pressure, and respiratory rate at very low signal-to-noise levels. Full article

In recent years, telecom fraud remains prevalent in many regions, severely impacting people’s daily lives and causing substantial economic losses. However, previous research has mainly relied on expert knowledge for feature engineering, which lags behind and struggles to adapt to the continuously evolving patterns of fraud effectively. In addition, the extreme imbalance in fraud amounts within real communication data hinders the development of deep learning methods. In response, we propose a feature transformation method to represent users’ communication behavior as comprehensively as possible, and develop a convolutional neural network (CNN) with a Focal Loss function to identify rare fraudulent activities in highly imbalanced data. Experimental results on a real-world dataset show that, under conditions of severe class imbalance, the proposed method significantly outperforms existing approaches in two key metrics: recall (0.7850) and AUC (0.8662). Our work provides a new approach for telecommunication fraud detection, enabling the effective identification of fraudulent numbers. Full article

Background: Recent hypotheses suggest that mutations associated with alpha1 antitrypsin (AAT) deficiency (AATD) may influence the clinical presentation and progression of cystic fibrosis (CF). This study employs a longitudinal design to determine the prevalence of AATD mutations and assess their impact on CF. Methods: The study Finding AAT Deficiency in Obstructive Lung Diseases: Cystic Fibrosis (FADO-CF) is a retrospective cohort study evaluating people with CF from November 2020 to February 2024. On the date of inclusion, serum levels of AAT were measured and a genotyping of 14 mutations associated with AATD was performed. Historical information, including data on exacerbations, microbiological sputum isolations, and lung function, was obtained from the medical records, aiming at a temporal lag of 10 years. Results: The sample consisted of 369 people with CF (40.9% pediatrics). Of these, 58 (15.7%) cases presented at least one AATD mutation. The AATD allelic combinations identified were PI*MS in 47 (12.7%) cases, PI*MZ in 5 (1.4%) cases, PI*SS in 3 (0.8%) cases, PI*SZ in 2 (0.5%) cases, and PI*M/P_lowell in 1 (0.3%) case. The optimal cutoff value for AAT levels to detect AATD-associated mutation carriers was 129 mg/dL in the overall cohort (sensitivity of 73.0%; specificity 69.2%) and 99.5 mg/dL when excluding PI*MS cases (sensitivity 98.0%; specificity 90.9%), highlighting the need for lower thresholds in clinically severe genotypes to improve case detection. The number of mild exacerbations during the follow-up appeared to be associated with AATD mutations. Conclusions: AATD mutations are prevalent in CF and may impact certain clinical outcomes. If systematic screening was to be planned, we recommend considering the proposed cut-off points to select the population for genetic studies. Full article

Background/Objectives: Neonatal screening programmes for thyroid function testing, based on thyroid-stimulating hormone (TSH) assessment, detect both Permanent Congenital Hypothyroidism (PCH) and Transient Congenital Hypothyroidism (TCH). Maternal iodine-deficient dietary intake may result in compensatory neonatal TSH elevation; screening for Congenital Hypothyroidism (CH) is used as an indicator of the degree of iodine deficiency and of its control. In Greece, newborn screening for CH, using TSH measurement in dried blood spots (Guthrie card), began in 1979 through the Institute of Child Health (ICH). Although the general Greek population is considered iodine-replete, most pregnant Greek people are mildly iodine deficient according to the stricter WHO criteria. The aim of this retrospective study was to record the cases of TCH and the main causative factors over a 10-year period (2010–2019) in Greece, when the country was deemed to be iodine-replete. Methods: The number of births in Greece between 2010 and 2019 was retrieved from the Hellenic Statistical Authority (ELSTAT) archives: 952,109 births were recorded. The total number of newborns assessed through the ICH was 951,342 (99%). During this period, 22,391 newborns were identified to have TSH > 7 mIU/L after the second check on the initial card. Among those, 17,992 underwent retesting with a serum sample. Out of the retested newborns, 1979 were screened positive for CH and immediately began treatment with levothyroxine. We followed up with families, paediatricians, and paediatric endocrinologists to determine whether L-thyroxine therapy had been successfully discontinued for at least two months after the child’s third birthday. Successful contact was achieved with 889 individuals. From this group, 329 children had successfully discontinued thyroxine, classified as TCH. Demographic data, including gender, gestational age, and birth weight, were collected from the archives of the ICH. Maternal data, including thyroid medication use and the presence of elevated thyroid autoantibodies during pregnancy and childbirth, were also recorded. Results: Logistic regression analysis revealed that, while controlling for all other predictor variables, the odds ratio of transient hypothyroidism was 2.078 (95% CI: 1.530 to 2.821) for prematurely born children compared to those born at term. The effects of other factors on TCH versus PCH were not significant. Conclusions: It seems that prematurity is the main factor contributing to Transient Congenital Hypothyroidism in Greece, a recently iodine-replete country. Full article

With the rapid development of modern industry, people’s living pressures are gradually increasing, and an increasing number of individuals are affected by sleep disorders such as insomnia, hypersomnia, and sleep apnea syndrome. Many cardiovascular and psychiatric diseases are also closely related to sleep. Therefore, the early detection, accurate diagnosis, and treatment of sleep disorders an urgent research priority. Traditional manual sleep staging methods have many problems, such as being time-consuming and cumbersome, relying on expert experience, or being subjective. To address these issues, researchers have proposed multiple algorithmic strategies for sleep staging automation based on deep learning in recent years. This paper studies MASleepNet, a sleep staging neural network model that integrates multimodal deep features. This model takes multi-channel Polysomnography (PSG) signals (including EEG (Fpz-Cz, Pz-Oz), EOG, and EMG) as input and employs a multi-scale convolutional module to extract features at different time scales in parallel. It then adaptively weights and fuses the features from each modality using a channel-wise attention mechanism. The integrated temporal features are integrated into a Bidirectional Long Short-Term Memory (BiLSTM) sequence encoder, where an attention mechanism is introduced to identify key temporal segments. The final classification result is produced by the fully connected layer. The proposed model was experimentally evaluated on the Sleep-EDF dataset (consisting of two subsets, Sleep-EDF-78 and Sleep-EDF-20), achieving classification accuracies of 82.56% and 84.53% on the two subsets, respectively. These results demonstrate that deep models that integrate multimodal signals and an attention mechanism offer the possibility to enhance the efficiency of automatic sleep staging compared to cutting-edge methods. Full article

Background/Objectives: The advent of combination antiretroviral therapy has led to significant reductions in HIV-related morbidity and mortality and, conversely, an increasing incidence of chronic diseases, such as cancer. This study aimed to assess the incidence of skin malignancies in a cohort of people living with HIV (PLWH) compared to HIV-uninfected individuals (HUPs). Methods: Between April 2023 and April 2025, PLWH attending the Infectious Disease Unit at Policlinico of Foggia, Italy, were invited for skin cancer screening (cases). During the same period, patients visiting the Dermatology Unit were asked to undergo skin cancer screening and a rapid HIV test. Those who tested negative were included as controls. Suspicious lesions were surgically excised at the Plastic Surgery University Unit and examined by a dermatopathologist. Results: We enrolled 91 cases and 91 controls. Precancerous and cancerous skin lesions were detected at similar rates in PLWH and HUPs (12% vs. 13.2% and 7.6% vs. 8.7%). The total number of cancerous and precancerous lesions was higher in the PLWH group. In both groups, basal cell carcinoma was the most common tumor. Squamous cell carcinoma, basosquamous carcinoma, and dermatofibrosarcoma protuberans were found only in PLWH. Conclusions: The higher risk of multiple and rare skin cancers in PLWH should be recognized by healthcare providers and patients. PLWH should have regular skin cancer screenings, especially if they have additional risk factors such as a history of extensive ultraviolet radiation exposure. Full article

Glaucoma is an eye disease caused by increased intraocular pressure (IOP) that affects the optic nerve head (ONH), leading to vision problems and irreversible blindness. Background/Objectives: Glaucoma is the second leading cause of blindness worldwide, and the number of people affected is increasing each year, with the number expected to reach 111.8 million by 2040. This escalating trend is alarming due to the lack of ophthalmology specialists relative to the population. This study proposes an explainable end-to-end pipeline for automated glaucoma diagnosis from fundus images. It also evaluates the performance of Vision Transformers (ViTs) relative to traditional CNN-based models. Methods: The proposed system uses three datasets: REFUGE, ORIGA, and G1020. It begins with YOLOv11 for object detection of the optic disc. Then, the optic disc (OD) and optic cup (OC) are segmented using U-Net with ResNet50, VGG16, and MobileNetV2 backbones, as well as MaskFormer with a Swin-Base backbone. Glaucoma is classified based on the vertical cup-to-disc ratio (vCDR). Results: MaskFormer outperforms all models in segmentation in all aspects, including IoU OD, IoU OC, DSC OD, and DSC OC, with scores of 88.29%, 91.09%, 93.83%, and 93.71%. For classification, it achieved accuracy and F1-scores of 84.03% and 84.56%. Conclusions: By relying on the interpretable features of the vCDR, the proposed framework enhances transparency and aligns well with the principles of explainable AI, thus offering a trustworthy solution for glaucoma screening. Our findings show that Vision Transformers offer a promising approach for achieving high segmentation performance with explainable, biomarker-driven diagnosis. Full article

The number of people and applications using the internet has increased substantially in recent years. The increased use of the internet has also resulted in various security issues. As the volume of data increases, cyber-attacks become increasingly sophisticated, exploiting vulnerabilities in network structures. The incorporation of modern technologies, particularly data mining, emerges as an essential method for analyzing huge amounts of data in real time, enabling the proactive detection of anomalies and potential security breaches. This research seeks to identify the most robust machine learning model for exploit detection. It applies five feature selection techniques and eight classification models to the UNSW-NB15 dataset. A comprehensive evaluation is conducted based on classification accuracy, computational efficiency, and execution time. The results demonstrate the efficiency of the Decision Tree model using Random Forest for feature selection in the real-time detection of exploit attacks, exhibiting an accuracy of 87.9%, along with a very short training (0.96 s) and testing time (0.29 ms/record). Full article

This study aims to develop a performance evaluation system specifically for the design phase of high-rise building projects within the architecture, engineering, and construction industry, where performance is often only measured during construction. The research process included three stages: identification of 21 key performance indicators through a literature review and expert validation; development of standardized indicator sheets detailing calculation protocols and data collection procedures; and creation of a functional dashboard-based evaluation system using Excel. The system was validated through expert review and tested with a simulated project generated using an AI-based language model. The evaluation system proved functional, accessible, and effective in detecting performance issues across five core categories: planning, cost, time, quality, and people. The results from the simulated application highlighted strengths in quality and stakeholder collaboration but also revealed significant gaps in cost and time performance. This study addresses a gap in the existing literature by focusing on performance evaluation during the design phase of construction projects, a stage often underrepresented in performance studies. The resulting system offers a structured, practical tool adaptable to real-world projects. The validation relied on a limited number of expert participants and a simulated project. Future research should recommend broader international validation and real-world application. Full article

Alzheimer’s disease (AD) is the most common form of dementia, affecting over 50 million people globally. Since 1906, efforts to understand this neurodegenerative disease and to develop effective treatments have continued to this day. Recognizing docosahexaenoic acid (DHA, 22:6n-3) as a safe, inexpensive and vital nutrient for brain health and cognitive protection due to its key role in brain development and function, this study explores novel, sustainable non-fish sources as potential dietary supplements to prevent or mitigate AD, within a blue biotechnology framework. Forty 5×FAD male mice, five weeks old, were allocated to five body weight-matched dietary groups (n = 8) and fed isocaloric diets based on AIN-93M standard chow for 6 months. Each diet, except the control feed (non-supplemented group), enclosed a modified lipid fraction supplemented with 2% of the following: (1) linseed oil (LSO, rich in alpha-linolenic acid (ALA,18:3n-3)); (2) cod liver oil (fish oil, FO, rich in both DHA and eicosapentaenoic acid (EPA, 20:5n-3)); (3) Schizochytrium sp. microalga oil (Schizo) with 40% of DHA; and (4) commercial DHASCO oil (DHASCO) with 70% of DHA. The different diets did not affect (p > 0.05) growth performance criteria (e.g., final body weight, daily feed intake, and body weight gain) suggesting no effect on the overall caloric balance or mice growth, but n-3 long-chain polyunsaturated-fatty acid (n-3 LCPUFA) supplementation significantly reduced total cholesterol (p < 0.001) and total lipids (p < 0.001). No systemic inflammation was detected in 5×FAD mice. In parallel, a beneficial modulation of lipid metabolism by DHA-enriched diets was observed, with polyunsaturated fatty acid incorporation, particularly DHA, across key metabolic tissues, such as the liver (p < 0.001) and the brain (p < 0.001). No behavioural variations were detected using an open-field test after 6 months of diet (p > 0.05). While mice fed a standard diet or LSO diet showed cognitive deficit, the incorporation of FO, Schizo or DHASCO oils into dietary routine showed promising protective effects on the working memory (p < 0.05) and the last two diets also on the recognition memory (p < 0.05) Increased neuronal count (p < 0.05), reflecting neuronal survival, was clearly observed with the fish oil diet. In turn, the number of TAU-positive cells (p < 0.05) was reduced in the Schizo diet, while β-amyloid deposition (p < 0.01) and the neuroinflammatory marker, IBA1 (p < 0.05), were decreased across all DHA-enriched diets. These promising findings open new avenues for further studies focused on the protective effects of DHA derived from sustainable and underexploited Schizochytrium sp. microalga in the prevention of AD. Full article

Public health in a densely populated city is inextricably linked to the state of the urban environment. The microclimate, the condition of water sources and sanitary well-being are just some of the many environmental factors that have a strong influence on people’s health. The presence of urban green spaces and various birds in cities is extremely important, also to create a more favorable psychological atmosphere for the people who live and/or work there. At the same time, it should not be forgotten that the feces of synanthropic birds are a favorable environment for various potentially pathogenic species of microorganisms, including yeasts of the genus Candida. Here, we investigated the culturable, potentially pathogenic ascomycetous yeast microbiome in the fresh and dry feces of five synanthropic birds (Rock Pigeon, European Starling, White Wagtail, Great Tit and House Sparrow). The samples were collected in spring (May 2024). In total, 48 Rock Pigeon, 47 European Starling, 38 White Wagtail, 32 Great Tit and 30 House Sparrow droppings were collected and analyzed. The selective medium Brilliance Candida Agar was used for cultivation. A total of 638 strains were isolated belonging to 9 yeast species (Arxiozyma bovina, Candida albicans, Nakaseomyces glabratus, Clavispora lusitaniae, C. tropicalis, C. parapsilosis, Pichia kudriavzevii, Debaryomyces hansenii and D. fabryi). All detected yeast species were molecularly identified using the ITS rDNA region. The microbiome of potential pathogens in fresh feces proved to be significantly host-dependent. Most pathogenic yeasts (7 species)—A. bovina, C. albicans, N. glabratus, Cl. lusitaniae, C. tropicalis, C. parapsilosis and P. kudriavzevii—were only detected in fresh feces from pigeons. This list contains five out of six ascomycetous species from the list of critical, high and medium-important yeast pathogens published in the World Health Organization fungal list. Of the potentially pathogenic yeasts, two species were observed in the dry droppings of various birds: C. parapsilosis and P. kudriavzevii. No significant differences in the diversity of culturable pathogens in dry droppings were observed between the different hosts. Fresh droppings from synanthropic birds, especially pigeons (and to a lesser extent dry droppings), therefore pose a health risk. In this study, we did not find any feces from synanthropic birds in which potentially pathogenic ascomycetous yeasts were not detected. To maintain the sanitary safety and well-being of citizens, it is very important to regulate the number of synanthropic birds (primarily pigeons), especially in sensitive areas such as playgrounds, hospital territories, etc. Full article

Background: In patients with familial adenomatous polyposis (FAP), the duodenum is another high-risk region for malignancy after the large bowel. However, endoscopic and surgical management differs for papillary lesions and adenomas located in other parts of the duodenum. The aim of the study was to present the principles of the endoscopic surveillance of extrapapillary polyps based on a single-center 14-year observational study. Methods: The retrospective analysis was carried out in 2010–24 on a group of 45 people enrolled in endoscopic surveillance of the upper gastrointestinal tract due to FAP. The evaluation was aimed at detecting the malignant transformation of extrapapillary duodenal adenomas, with a radical removal of high-risk lesions. The severity of polyposis in the subsequent years of observation as well as the effectiveness of routine polypectomy on downstaging according to the Spiegelmann score were also assessed. Results: Invasive duodenal cancer was not detected in any case; however, high-grade dysplasia (HGD) was confirmed in five patients. The severity of polyposis and the number of polyps with HGD increased in following examinations, but routine polypectomy performed mainly during the 4th and 5th endoscopies allowed for a transient decrease in the Spiegelman score. Finally, progression of duodenal polyposis was observed in 18 patients, another 4 experienced regression (downstaging) and in 23 cases the stage of severity did not change. In addition, five patients were diagnosed with LST-G lesions, which were removed without recurrence. Conclusions: The patient’s age correlates with the severity of polyposis and the risk of malignancy, but routine endoscopic resections eliminate potentially invasive lesions and contribute to disease regression expressed by the Spiegelmann score. The radical endoscopic therapy of extrapapillary duodenal lesions limits the indications for surgical procedures. Full article

Background/Objectives: Diabetic macular edema (DME) is the primary cause of vision loss in people with diabetes, and if untreated, it can result in irreversible macular damage. Both fluorescein angiography (FA), the gold standard, and optical coherence tomography angiography (OCTA) are used for evaluation of this disease. The objective of this study was to compare the diagnostic value of both. Methods: We conducted a comparative analysis of 98 patients aged 18–80 years with significant DME and best-corrected visual acuity ≥0.1 according to the Snellen chart. Participants underwent glycated hemoglobin blood test (HbA1c) and ophthalmological examinations, including OCTA and FA. OCTA 3 × 3 mm scans of superficial (SCP) and deep capillary plexus (DCP) along with FA scans were exported to the Gimp computer program. Size of the foveal avascular zone (FAZ), the number of visible microaneurysms (MAs), and ETDRS report number 11 classification of the images were assessed. Results: FAZ size differed significantly in superficial plexus (0.41 mm²), deep plexus (0.43 mm²) OCTA, and FA (0.38 mm²) (p < 0.001). FAZ size in DCP OCTA closely correlated with that of FA (τ = 0.79, p < 0.001). The total number of MAs visualized in the OCTA was significantly lower than in FA (p < 0.001). ETDRS classification of scans revealed that the level of consistency between the examinations was moderate to very strong. Conclusions: OCTA may be useful in evaluating macular ischemia. It is less sensitive in detecting MAs in DME eyes. FAZ has sharper boundaries and is larger when measured in OCTA. Poor glycemic control results in higher incidence of MAs in macula. Full article

Mansonellosis is a chronic infectious tropical disease that affects hundreds of millions of people worldwide but is not currently targeted for control. In this study, we interviewed 320 residents from Sao Gabriel do Cachoeira (SGC) about their support for soil transmitted helminth (STH) and mansonellosis interventions. Our survey found no significant difference between community support for mansonellosis and STH disease treatment when comparing any equivalent treatment regimen or program, although support for STH treatments was always higher than for mansonellosis treatments. No significant differences were detected when comparing community members’ willingness to participate in treatment programs and their willingness to allow family members to participate in an equivalent program. Our survey did, however, almost always find that significantly more community members were willing to participate in a proposed treatment program if the treatment regimen of that program was shorter than an otherwise equivalent regimen. Although significantly fewer people said they would participate in a curative four-week treatment course for mansonellosis than in a mansonellosis mass drug administration (MDA) program, significantly more community members said they would take a curative mansonellosis treatment course that lasted seven days or less than they would participate in any type of anthelminthic MDA proposed to them. The number of community members who said they would participate in any helminthic treatment program if they knew there was a ≥50% chance that they were infected was significantly higher than the number who said that they would without knowing the regional prevalence rate. Full article

If artificial intelligence (AI) is to be applied in safety-critical domains, its performance needs to be evaluated reliably. The present study investigated how humans evaluate AI systems for person detection in automatic train operation. In three experiments, participants viewed image sequences of people moving in the vicinity of railway tracks. A simulated AI system highlighted all detected people—sometimes correctly and sometimes not. Participants had to provide a numerical rating of the AI’s performance and then verbally explain their rating. The experiments manipulated several factors that might influence human ratings: the types and plausibility of AI mistakes, the number of affected images, the number of people present in an image, the position of people relevant to the tracks, and the methods used to elicit human evaluations. While all these factors influenced human ratings, some effects were unexpected or deviated from normative standards. For instance, the factor with the strongest impact was people’s position relative to the tracks, although participants had explicitly been instructed that the AI could not process such information. Taken together, the results suggest that humans may sometimes evaluate more than the AI’s performance on the assigned task. Such mismatches between AI capabilities and human expectations should be taken into consideration when conducting safety audits of AI systems. Full article