Search Results (975)

Heart disease is the leading cause of death across the world. However, such an early prediction of heart attacks can save lives if clinical data are used to predict it accurately. For this, we use four machine learning models: Naive Bayes, Decision Tree, Random Forest and K-Nearest Neighbors (KNN) to predict heart attacks from the data of the patients. Models developed achieved an average accuracy of 65.08%; however, this paper explores the performance of these models in real world healthcare applications. Our focus is on improving model performance by improving the quality of the data, the features and hyperparameter tuning. Future directions indicate combining deep learning techniques and larger dataset for more accurate prediction. Full article

Optimizing in vitro culture conditions for cryopreserved–thawed human ovarian cortical fragments (OCFs) represents a critical step in fertility preservation strategies. OCFs predominantly contain primordial follicles (PMFs), whose survival and integrity are essential for ex vivo folliculogenesis. This study aimed to evaluate the impact of different culture media supplementations on PMF survival and tissue morphology by comparing alpha-Minimum Essential Medium (αMEM) supplemented with Human Serum Albumin (HSA), Human Serum (HS), or Serum Substitute Supplement (SSS). Twenty-nine OCFs were cultured for three days, and follicular density and were morphology assessed. Generalized linear mixed model analysis showed that PMF density was significantly higher in OCFs cultured in medium supplemented with SSS (213 PMFs/mm³) compared to those cultured with HSA (107 PMFs/mm³) or HS (93 PMFs/mm³). Furthermore, SSS supplementation was associated with a significant increase in the number of PMFs showing healthy morphologies. These findings indicate that SSS supplementation to αMEM enhances the survival and preserves better morphologies of the human PMFs in short-term culture, highlighting its potential as a suitable culture supplement for ovarian tissue preservation. Full article

Non-player characters (NPCs) play a crucial role in creating engaging and immersive experiences in role playing games (RPGs). Traditional NPC interactions often rely on scripted dialogues, which can limit their ability to adapt dynamically to player input. This study presents a novel framework that enhances NPC interactions by integrating advanced conversational systems. Utilizing Open AI’s natural language processing capabilities, RPG Maker MZ as the game development platform, and JavaScript for customization, the framework introduces context-aware dialogues that respond intelligently to player queries and actions. By bridging the gap between game AI and conversational systems, this approach enables more lifelike and meaningful NPC behavior. Experimental results indicate that the proposed system significantly improves the narrative depth and overall player experience. These findings demonstrate the potential of combining AI-driven chatbots with game development tools to redefine the role of NPCs in modern gaming. Full article

Indonesian people, especially the younger generation, often overlook the great potential of herbal leaves that are easily found around their homes. These leaves not only offer health benefits but also hold significant economic value. This research developed a system to classify 10 types of herbal leaves (Annona muricata, Anredera cordifolia, Piper betle, Ocimum basilicum, Peperomia pellucida, Psidium guajava, Isotoma longiflora, Coleus scutellarioides, Ageratum conyzoides, and Syzygium polyanthum) using artificial intelligence (AI). The study employed the Convolutional Neural Network (CNN) method and the You Only Look Once (YOLO) v11 algorithm, focusing on evaluating the performance of YOLOv11 in three variants, Nano, Small, and Medium. The results showed that the YOLOv11 Medium variant achieved the best performance, with the highest mAP50-95 value of 0.743 and mAP50 of 0.974 at the last epoch. The YOLOv11 Small variant outperformed Nano in precision (0.947 vs. 0.933) and mAP50 (0.973 vs. 0.972), while YOLOv11 Nano had slightly higher recall (0.921 vs. 0.906). Confusion Matrix results for YOLOv11 Medium showed precision (P) = 0.932, recall (R) = 0.928, mAP50 = 0.974, and mAP50-95 = 0.743. Based on these metrics, YOLOv11 Medium stood out as the best-performing variant, followed by Small and Nano. This research highlights the potential of AI technology to enhance the utilization of herbal leaves, which can provide broader health benefits and support the local economy. Full article

This study evaluated the spatio-temporal dynamics of vegetation cover in the Capellanía wetland (Bogotá, Colombia) between 2013 and 2032 through spectral indices, machine learning, and spatial simulation. A multitemporal Random Forest model (R² = 0.991; RMSE = 0.0214; MAE = 0.0127) was integrated with cellular automata (MOLUSCE) to project vegetation trajectories under different urban growth scenarios. NDVI-based classification revealed a marked transition: degraded classes (bare soil and sparse vegetation) decreased from over 80% in 2013 to less than 10% in 2032, while moderate and dense vegetation surpassed 90%. Cellular automata achieved moderate agreement (Kappa = 0.640) and high internal calibration (pseudo-R² = 1.00); the transition matrix in scenario II, simulating the construction of the Avenida Longitudinal de Occidente (ALO), indicated a conversion 0→1 = 0.414 and persistence 1→1 = 0.709, evidencing intense urbanization pressure in peripheral areas. The Shannon index confirmed recovery but highlighted structural homogenization, underscoring the need to preserve heterogeneity to sustain ecosystem resilience. Scenario analysis showed that the ALO would act as a catalyst for urban expansion, threatening ecological connectivity and increasing pressure on vegetation. Overall, this study provides quantitative, spatial, and prospective evidence to promote preventive, integrated, and data-driven approaches for the conservation of strategic urban wetlands. Full article

(1) Background: Creative self-efficacy is associated with better psychological well-being and academic performance in adolescent and youth samples. Positive youth development is a strength-based model of youth transition to adulthood, which states that this emerges from adaptive regulations between personal strengths and nurturing contexts. The present study aimed to examine the associations between creative self-efficacy, PYD and perceived academic performance in a sample of Spanish youth. (2) Methods: A cross-sectional study was carried out during the spring of 2024. A sample composed of 370 undergraduates (M = 21.29, SD = 3.61) from 10 universities in Andalusia (Spain) filled in an online self-report measure. (3) Results: The results showed positive associations between creative self-efficacy, PYD and academic performance. A mediational analysis indicated that creative self-efficacy presented a positive effect on perceived academic performance through its positive associations with both Confidence and Competence dimensions of PYD. (4) Conclusions: These results may suggest the need to integrate creativity and PYD programs to strengthen academic performance in higher education. Full article

H₂ has become one of the most attractive alternatives to replace fossil fuels in clean energy production, but large-scale production remains a challenge. A key step toward this goal is to develop new efficient electrocatalysts for H₂ production. This work presents a new mixed metal oxides-decorated CNT paste electrode (MMO@C), which is highly electrocatalytic, for use in the hydrogen evolution reaction (HER). MMO@C is synthesized by a solvothermal method and used as an easy-to-prepare paste electrode. XPS and X-ray analysis indicate that the electrocatalyst corresponds to a mixed surface of Ga₂O₃-CuO-Cu₂O-Cu(OH)₂@C. The MMO@C electrocatalyst shows a positive E_o of 0.12 V vs. RHE at −10 mA cm⁻² towards the HER in a neutral medium. In neutral and alkaline media, the presence of Ga₂O₃ facilitates the reduction of CuO to Cu(I) species, which is followed by the formation of Cu(s) active sites. Therefore, the excellent electrocatalytic performance toward the HER in a neutral medium is attributed to the synergistic effect between gallium and copper oxides on the electrode surface. The prominent H₂ production using MMO@C electrocatalyst is 1.31 × 10⁻² mol cm⁻², with a turnover number (TON) of 39,423, a turnover frequency (TOF) of 13,141 h⁻¹, and a faradaic efficiency (FE) of 94.3%. Although the Tafel slope reveals slow reaction kinetics, the outstanding onset potential allows for the coupling of the electrocatalyst to renewable energy production systems, making it an attractive candidate for producing green H₂ and for application in membrane water electrolyzers. Full article

Background/Objectives: MiRNAs have demonstrated promising roles in the diagnosis of pancreatic cancer and in the prognostic assessment of affected patients. Methods: We conducted a prospective pilot study including 23 patients diagnosed with advanced-stage pancreatic cancer and 10 healthy controls, matched by age and sex. In the screening phase, we evaluated the expression of 176 miRNAs in pooled plasma samples from both groups using real-time PCR. Subsequently, we validated the overexpression of selected miRNAs in individual plasma samples using the same technique. Statistical analysis was performed using IBM SPSS Statistics version 29. Results: During the screening phase, 22 miRNAs exhibited differential expression in patients with pancreatic cancer compared to healthy controls. Among these, hsa-miR-100-5p (27.8-fold increase), hsa-miR-122-5p (7.5-fold), hsa-miR-885-5p (7.2-fold), hsa-miR-34a-5p (5.7-fold), and hsa-miR-193a-5p (4.4-fold) showed the most pronounced upregulation. In the validation phase, all five candidates demonstrated significant overexpression in individual plasma samples (p < 0.001). Their circulating levels also showed associations with tumor stage (p < 0.05). Conclusions: Our findings highlight a distinct circulating miRNA signature associated with advanced pancreatic cancer, supporting the potential role of hsa-miR-100-5p, hsa-miR-122-5p, hsa-miR-885-5p, hsa-miR-34a-5p, and hsa-miR-193a-5p as minimally invasive biomarkers for disease detection and staging. Larger, multicenter studies including early-stage patients and disease control groups will be required to validate these biomarkers and determine their clinical utility. Full article

To reduce GHG emissions from food miles and enhance urban food security, this study develops and evaluates an integrated framework combining three strategies: the 15-minute city concept, urban agriculture, and a renewable-energy-powered green transportation (GT) system. The goal is to create a scalable, holistic approach to sustainable food production and distribution within neighborhoods. A Food Production and Transportation Framework is proposed, modeling vegetable cultivation across rooftops, facades, and lot spaces, with optimized allocations based on a tailored Food Production Schedule. The harvested produce is distributed via GT powered by sidewalk-integrated photovoltaics (PVs). Results demonstrate that using 15% of roof, facade, and lot spaces yields an achieved annual food self-sufficiency of 100%. The transportation system operates with a single GT unit powered by 98 m² of sidewalk PVs, reducing CO₂ emissions by 98% from the base case. Economic analysis indicates a payback period of 2.8 years, with the cost of PV-generated electricity estimated at C$0.92/kWh. This framework highlights that 0.19 units of local food production offset one unit of CO₂ emissions. This integrated approach advances multiple UN Sustainable Development Goals (SDGs), including SDG 2 (Zero Hunger), SDG 7 (Affordable and Clean Energy), SDG 11 (Sustainable Cities and Communities), and SDG 13 (Climate Action). Full article

Malware detection has become a critical area of research due to the increasing sophistication of cyberattacks targeting various platforms, including IoT devices, Android systems, and desktop environments. This study employed the systematic literature review (SLR) method, following PRISMA guidelines, to analyze recent advancements in malware detection using machine learning (ML) models. A total of six studies were selected based on strict inclusion and exclusion criteria, focusing on algorithms, datasets, performance metrics, and targeted platforms. The review reveals that ensemble methods like Gradient Boosting and XGBoost achieve high detection accuracy, with several models exceeding 90% on benchmark datasets such as VirusShare and MSCAD. Additionally, IoT platforms emerged as the most commonly targeted environment in malware detection research, emphasizing their vulnerability. Despite these advancements, the review identifies gaps in dataset diversity and platform-specific optimizations. This study provides insights into the current trends, challenges, and future directions for machine learning-based malware detection. Full article

Infection with Burkholderia pseudomallei, the causative agent of melioidosis, is uncommon in the United States (U.S.), leading to delays in pathogen identification and clinical diagnosis which can often lead to laboratory exposures. The indirect hemagglutination assay (IHA) is the primary serological test for confirming exposure to B. pseudomallei. In the U.S., a titer of ≥1:40 suggests exposure to B. pseudomallei or a closely related species, and a 4-fold rise in IHA titer ≥1:40 with clinically compatible illness is considered diagnostically probable. A retrospective analysis of 160 voluntarily reported laboratory exposure events to B. pseudomallei across 29 U.S. jurisdictions and 5 countries between 2008–2024 was conducted. This analysis included post-exposure management data and IHA results for 855 exposed laboratory personnel who had serological monitoring performed at the U.S. Centers for Disease Control and Prevention (CDC). Among exposed laboratory personnel, 105 (12%) had a seropositive titer. Of these, ninety-one (87%) laboratory personnel remained seropositive (≥1:40) at their last IHA test. Five (1%) people had a 4-fold rise in titers, though none developed melioidosis. This report underscores the need for prospective studies to evaluate seropositive laboratory personnel and to update risk guidance for laboratory exposures in non-endemic areas. Full article

Combined radiation exposures—pairings of ionizing and non-ionizing radiation—are increasingly relevant in medical, spaceflight, and environmental contexts. This systematic review evaluates their radiobiological effects and therapeutic applications, focusing on synergistic interactions and underlying biological mechanisms. A comprehensive search of PubMed, Google Scholar, Semantic Scholar, bioRxiv, and Europe PMC identified studies published from the 1960s through 2025. Eligible studies assessed biological responses to different radiation types applied either simultaneously or within 24 h, with minor exceptions. A total of 172 studies were included and categorized into radiobiological, therapeutic, and space radiation domains. Due to the predominance of mechanistic research, no formal risk-of-bias tool was applied; methodological limitations were assessed qualitatively. Findings were synthesized narratively by radiation type and domain. Synergistic and additive effects were frequently observed, with responses influenced by dose, sequence, radiation type, and DNA repair dynamics. Therapeutic combinations often enhanced efficacy, while space radiation studies revealed multifaceted biological damage. This review provides a consolidated reference for advancing research and applications involving combined radiation exposures, emphasizing the need for mechanistic insight and standardized protocols in therapy, radiation protection, and spaceflight. This study was funded by project 21GRD02 BIOSPHERE (European Partnership on Metrology, Horizon Europe) and reported per PRISMA 2020 guidelines; no protocol was registered. Full article

Serious games for children with Autism Spectrum Disorder (ASD) require rigorous evaluation frameworks that capture neurodivergent interaction patterns. This pilot study designed, developed, and evaluated a serious game for children with ASD, focusing on operability assessment aligned with ISO/IEC 25010:2023 standards. A repeated-measures design involved ten children with ASD from the Carlos Garbay Special Education Institute in Riobamba, Ecuador, across 25 gameplay sessions. A bespoke operability algorithm incorporating four weighted components (ease of learning, user control, interface familiarity, and message comprehension) was developed through expert consultation with certified ASD therapists. Statistical study used linear mixed-effects models with Kenward–Roger correction, supplemented by thorough validation including split-half reliability and partial correlations. The operability metric demonstrated excellent internal consistency (split-half reliability = 0.94, 95% CI [0.88, 0.97]) and construct validity through partial correlations controlling for performance (difficulty: r_partial = 0.42, p = 0.037). Eighty percent of sessions achieved moderate-to-high operability levels (M = 45.07, SD = 10.52). In contrast to requirements, operability consistently improved with increasing difficulty level (Easy: M = 37.04; Medium: M = 48.71; Hard: M = 53.87), indicating that individuals with enhanced capabilities advanced to harder levels. Mixed-effects modeling indicated substantial difficulty effects (H = 9.36, p = 0.009, ε² = 0.39). This pilot study establishes preliminary evidence for operability assessment in ASD serious games, requiring larger confirmatory validation studies (n ≥ 30) to establish broader generalizability and standardized instrument integration. The positive difficulty–operability association highlights the importance of adaptive game design in supporting skill progression. Full article

Introduction: Asthma is a chronic airway inflammatory disease characterized by variable airflow limitation and intermittent symptoms. In well-controlled asthma, auscultation and spirometry often appear normal, making diagnosis challenging. Moreover, bronchial provocation tests carry a risk of inducing acute bronchoconstriction. This study aimed to develop a non-invasive, objective, and reproducible diagnostic method using machine learning-based lung sound analysis for the early detection of asthma, even during stable periods. Methods: We designed a machine learning algorithm to classify controlled asthma patients and healthy individuals using respiratory sounds recorded with a digital stethoscope. We enrolled 120 participants (60 asthmatic, 60 healthy). Controlled asthma was defined according to Global Initiative for Asthma (GINA) criteria and was supported by normal spirometry, no pathological auscultation findings, and no exacerbations in the past three months. A total of 3600 respiratory sound segments (each 3 s long) were obtained by dividing 90 s recordings from 120 participants (60 asthmatic, 60 healthy) into non-overlapping clips. The samples were analyzed using Mel-Frequency Cepstral Coefficients (MFCCs) and Tunable Q-Factor Wavelet Transform (TQWT). Significant features selected with ReliefF were used to train Quadratic Support Vector Machine (SVM) and Narrow Neural Network (NNN) models. Results: In 120 participants, pulmonary function test (PFT) results in the asthma group showed lower FEV1 (86.9 ± 5.7%) and FEV1/FVC ratios (86.1 ± 8.8%) compared to controls, but remained within normal ranges. Quadratic SVM achieved 99.86% accuracy, correctly classifying 99.44% of controls and 99.89% of asthma cases. Narrow Neural Network achieved 99.63% accuracy. Sensitivity, specificity, and F1-scores exceeded 99%. Conclusion: This machine learning-based algorithm provides accurate asthma diagnosis, even in patients with normal spirometry and clinical findings, offering a non-invasive and efficient diagnostic tool. Full article

Background/Objectives: Avian influenza represents a major threat to both animal and public health. Our group has tracked avian influenza viruses circulating in wild birds in Peru during the last 20 years. While most of these viruses are low-pathogenic avian influenza strains, some exhibit genetic changes that significantly diverge from common circulating viruses. We selected a highly divergent hemagglutinin H2 gene from a genetically characterized avian influenza virus to develop a recombinant protein using a baculovirus system. Methods: We administered 5 µg and 20 µg doses of the recombinant H2 protein (rH2) into 3-week-old chickens using an abdominal cavity inoculation model to evaluate the activation of innate immune responses. Chickens were euthanized at 24 and 72 h post inoculation and an abdominal lavage was performed to harvest the abdominal cavity content. Results: Infiltrating cells were counted and their cell viability was measured using an Annexin V/PI staining. At 24 h, a large proportion of infiltrating leukocytes were identified as heterophils, monocyte/macrophages and lymphocytes. These proportions changed at 72 h, with a decrease in heterophils and increase in monocyte and lymphocyte pools. We observed strong cellular activity in abdominal leukocytes at 24 h, with a decline in activation levels at 72 h. Cytokine expression suggested a tightly regulated immune response during the 72 h period, while a more sustained response was observed at the 20 µg dose. Antibody levels demonstrated the capacity of the rH2 protein to induce long-term responses. Conclusions: These results revealed that the baculovirus-expressed rH2 protein induces a controlled immune activation, a long-term immune response, holding promise as a potential vaccine candidate for animal health. Full article