Search Results (231)

Ovarian cancer’s high mortality is primarily due to late-stage diagnosis, underscoring the critical need for improved early detection tools. This study develops and validates explainable artificial intelligence (XAI) models to discriminate malignant from benign ovarian masses using readily available demographic and laboratory data. A dataset of 309 patients (140 malignant, 169 benign) with 47 clinical parameters was analyzed. The Boruta algorithm selected 19 significant features, including tumor markers (CA125, HE4, CEA, CA19-9, AFP), hematological indices, liver function tests, and electrolytes. Five ensemble machine learning algorithms were optimized and evaluated using repeated stratified 5-fold cross-validation. The Gradient Boosting model achieved the highest performance with 88.99% (±3.2%) accuracy, 0.934 AUC-ROC, and 0.782 Matthews correlation coefficient. SHAP analysis identified HE4, CEA, globulin, CA125, and age as the most globally important features. Unlike black-box approaches, our XAI framework provides clinically interpretable decision pathways through LIME and SHAP visualizations, revealing how feature values push predictions toward malignancy or benignity. Partial dependence plots illustrated non-linear risk relationships, such as a sharp increase in malignancy probability with CA125 > 35 U/mL. This explainable approach demonstrates that ensemble models can achieve high diagnostic accuracy using routine lab data alone, performing comparably to established clinical indices while ensuring transparency and clinical plausibility. The integration of state-of-the-art XAI techniques highlights established biomarkers and reveals potential novel contributors like inflammatory and hepatic indices, offering a pragmatic, scalable triage tool to augment existing diagnostic pathways, particularly in resource-constrained settings. Full article

Prediabetes increases oxidative stress and the risk of type 2 diabetes and related cardiovascular diseases. Previous trials have shown antioxidant-rich strawberries improve this risk, but effects on antioxidant markers are inconclusive. This 28-week randomized controlled crossover trial evaluated the effects of freeze-dried strawberries (FDS) on fasting glucose, serum antioxidant status, and vascular inflammation in adults with prediabetes not on glucose-lowering medications. Participants were assigned to FDS (32 g/day ~ 2.5 servings of whole strawberries) or control (usual diet, no strawberries) for 12 weeks each, separated by a 4-week washout (n = 25/treatment period). Biomarkers were measured at baseline, 12, 16 (baseline 2), and 28 weeks. A mixed-model analysis of variance detected differences between groups, adjusting for covariates. Compared to control, FDS significantly improved serum superoxide dismutase (0.08 ± 0.04 U/mL), glutathione [(GSH): 1.8 ± 0.96 µmol/L], antioxidant capacity [(AC): 5.9 ± 3.2 µmol/L], β-carotene (113.9 ± 15.8 nmol/L), fasting glucose (97 ± 12 mg/dL), intercellular adhesion molecule [(ICAM): 56.0 ± 21.8 ng/mL], and vascular cell adhesion molecule [(VCAM): 440 ± 163 ng/mL] (all p < 0.05). ICAM was inversely correlated with GSH (r = −0.21), AC (r = −0.15), and β-carotene (r = −0.13) (all p < 0.05). VCAM was inversely correlated with AC (r = −0.12) (p < 0.05). Catalase, glutathione reductase, glutathione peroxidase, α-carotene, P-selectin, and E-selectin were unaffected. Our findings support strawberry intake as a dietary intervention for improving blood glucose control and antioxidant status in adults with prediabetes. Full article

This paper presents a modular hybrid mathematical model of bacterial fermentation developed by integrating a detailed kinetic model for the central carbon metabolism of Escherichia coli with a simplified four-compartment model of a large stirred bioreactor. The model describes the growth dynamics of E. coli, taking into account the hydrodynamic characteristics of the cultivation environment and spatial concentration gradients. The first module simulates liquid exchange flows between neighboring reactor zones and tracks the spatial distribution of substrate, acetate, dissolved oxygen, and biomass, while the second one, which is a kinetic model, includes main metabolic pathways such as glycolysis, the tricarboxylic acid cycle, and oxidative phosphorylation. Compared to most previous hybrid approaches relying on simplified kinetics, the present model integrates a detailed kinetic representation of E. coli central metabolism and is openly implemented on the BioUML platform, which ensures its reproducibility and extensibility. Numerical simulations reveal how mixing intensity affects concentration gradients and metabolic regimes across the reactor. Additionally, the model was used to identify an optimal mixing regime corresponding to the state where the system first enters the regime of complete aerobic substrate oxidation. The proposed model is applicable for numerical analysis of industrial-scale bioreactors and for predicting metabolic dynamics under various hydrodynamic conditions. Full article

Background and objectives: Early recurrence (ER) following curative-intent surgery for pancreatic ductal adenocarcinoma (PDAC) is associated with poor prognosis. Identifying preoperative risk factors for ER is essential for optimizing perioperative strategies. This study aimed to investigate perioperative predictors of ER, with a specific focus on tumor localization. Methods: We retrospectively analyzed 163 patients who underwent R0 or R1 resection for PDAC. ER was defined as recurrence within 6 months postoperatively. Two separate multivariate logistic regression analyses were conducted: one including only preoperative variables, and one including both pre- and postoperative factors. Results: ER occurred in 35.6% of patients and was associated with significantly worse overall survival (median 9 vs. 21 months, p < 0.001) and post-recurrence survival (5 vs. 8 months, p = 0.008). Preoperative ECOG performance status > 0 (OR 3.31, p = 0.013) and CA 19-9 > 208 U/mL (OR 3.18, p = 0.022) were identified as independent predictors of ER. In the postoperative model, tumor localization in the body/tail (OR 3.23, p = 0.035), tumor size > 3.25 cm, lymph node ratio > 0.13, and absence of adjuvant therapy were also significant. Notably, tumor location did not influence overall survival. Conclusions: Tumor localization in the body/tail of the pancreas is independently associated with early recurrence but not overall survival. These findings highlight the importance of incorporating tumor site into preoperative risk stratification and support the consideration of neoadjuvant therapy in select anatomically resectable patients, particularly those with left-sided tumors. Full article

A significant quantity of agro-industrial waste is generated globally across various agricultural sectors and food industries. Composed primarily of cellulose, hemicellulose, and lignin—known as lignocellulosic materials—this waste holds significant potential and can be repurposed as a nutrient-rich substrate for mushroom cultivation. Therefore, mushroom cultivation can be regarded as a promising biotechnological approach for the reduction and valorization of agro-industrial waste. This investigation is the first to explore the utilization of agro-industrial waste- and by-products for the cultivation of Epicoccum nigrum for the production of extracts with valuable biological activities. The logistic curve and autocatalytic growth models were applied to study the kinetics of the growth process on wheat bran, sunflower cake, wheat straw, pine sawdust, and steam-distilled lavender straw substrates. Through mathematical modeling, the optimal composition of a nutrient medium containing the selected substrates was determined and successfully validated in experimental conditions. Biologically active water extracts were obtained after solid-state cultivation with α-amylase and cellulase activity up to 10.6 ± 0.6 U/mL and 0.52 ± 0.03 U/g, respectively. The extracts exhibited antimicrobial activity against fungal strains from six different species, and the most susceptible was the phytopathogen Sclerotinia sclerotiorum, with a minimum inhibitory concentration of 0.156–0.313 mg/mL. Full article

Context: Modern software systems have become increasingly complex, making it difficult to interpret raw requirements and effectively utilize traditional tools for software design and analysis. Unified Modeling Language (UML) class diagrams are widely used to visualize and understand system architecture, but analyzing them manually, especially for large-scale systems, poses significant challenges. Objectives: This study aims to automate the analysis of UML class diagrams by assessing their complexity using a machine learning approach. The goal is to support software developers in identifying potential design issues early in the development process and to improve overall software quality. Methodology: To achieve this, this research introduces a Visual Question Answering (VQA)-based framework that integrates both computer vision and natural language processing. Vision Transformers (ViTs) are employed to extract global visual features from UML class diagrams, while the BERT language model processes natural language queries. By combining these two models, the system can accurately respond to questions related to software complexity, such as class coupling and inheritance depth. Results: The proposed method demonstrated strong performance in experimental trials. The ViT model achieved an accuracy of 0.8800, with both the F1 score and recall reaching 0.8985. These metrics highlight the effectiveness of the approach in automatically evaluating UML class diagrams. Conclusions: The findings confirm that advanced machine learning techniques can be successfully applied to automate software design analysis. This approach can help developers detect design flaws early and enhance software maintainability. Future work will explore advanced fusion strategies, novel data augmentation techniques, and lightweight model adaptations suitable for environments with limited computational resources. Full article

Clinical notes often contain unstructured text filled with abbreviations, non-standard terminology, and inconsistent phrasing, which pose significant challenges for automated medical information extraction. Named Entity Recognition (NER) plays a crucial role in structuring this data by identifying and categorizing key clinical entities such as symptoms, medications, and diagnoses. However, traditional and even transformer-based NER models often struggle with ambiguity and fail to produce clinically interpretable outputs. In this study, we present a hybrid two-stage framework that enhances medical NER by integrating a fine-tuned BERT model for initial entity extraction with a Dictionary-Infused Retrieval-Augmented Generation (DiRAG) module for terminology normalization. Our approach addresses two critical limitations in current clinical NER systems: lack of contextual clarity and inconsistent standardization of medical terms. The DiRAG module combines semantic retrieval from a UMLS-based vector database with lexical matching and prompt-based generation using a large language model, ensuring precise and explainable normalization of ambiguous entities. The fine-tuned BERT model achieved an F1 score of 0.708 on the MACCROBAT dataset, outperforming several domain-specific baselines, including BioBERT and ClinicalBERT. The integration of the DiRAG module further improved the interpretability and clinical relevance of the extracted entities. Through qualitative case studies, we demonstrate that our framework not only enhances clarity but also mitigates common issues such as abbreviation ambiguity and terminology inconsistency. Full article

Background/Objectives: Wheat bran is known for its anti-aging effects, primarily due to its antioxidant properties. Our previous study identified novel antioxidants in wheat bran (xylo-oligosaccharides and protein hydrolysates) using an innovative extraction method. However, the anti-aging potential of these wheat bran extracts (WBEs) remains unclear. Methods: This study evaluated the anti-aging effects of WBE in a D-galactose-induced aging model using Wistar rats. Animals were divided into four groups: (1) saline-injected control, (2) D-galactose-injected control, (3) D-galactose + 5% WBE, and (4) D-galactose + 10% WBE. After six weeks, body weight, food intake, body fat percentage, erythrocyte superoxide dismutase (SOD) activity, and liver senescence-associated β-galactosidase (SA-β-gal) levels were assessed. Results: D-galactose significantly reduced food intake in positive control 87 ± 21%/weekly (negative control; p < 0.05, 107 ± 20%/weekly for 10%WBE; p < 0.01. Body fat percentage (positive control: 84 ± 19% vs. 5% WBE: 110 ± 20%, p < 0.05 in 100% convert). It also lowered erythrocyte SOD activity; 68.6 ± 9%, p < 0.01 in 100% conversion). WBE supplementation restored SOD activity in a dose-dependent manner (5% WBE: 32,479 ± 12,773 U/mL; 10% WBE: 42,368 ± 20,281 U/mL. Although D-galactose did not elevate significantly SA-β-gal activity in the liver, WBE supplementation still led to a dose-dependent reduction in baseline SA-β-gal levels (294 ± 84 nmol/min/mg protein vs. 5% WBE: 181 ± 65 nmol/min/mg protein, and 10% WBE: 146 ± 40 nmol/min/mg protein. p < 0.001). No significant group differences were found in hepatic SOD2, catalase (liver and skin), or telomerase reverse transcriptase expression. Conclusions: These findings suggest that wheat bran extracts mitigate D-galactose-induced oxidative stress in circulation, indicating potential anti-aging benefits. However, their effects at the tissue level remain inconclusive. Further studies are needed to explore molecular mechanisms and refine intervention duration. Full article

Agroforestry landscape has undergone changes, namely land abandonment, which when combined with negative attitudes towards fire, is associated with the eradication of agroforestry leftovers and acts towards the proliferation of fires, threatening sustainability concerns. Agroforestry leftovers recovery presents high potential to act on this problem; however, the logistical costs associated with the recovery chain make it unfeasible. The lack of coordination/transparency between stakeholders is one of the main explanations for these costs. This study develops a digital tool to enhance the residual biomass supply chain for energy recovery and fire risk mitigation. In addition to this concept, this work also proposes conceptual models and a prototype, two essential contributions to software development. Methodologically, this study consulted 10 experts to validate a concept previously presented in the literature, supplemented with UML modeling and prototyping with Figma^®. The main results point to the creation of a disruptive concept that will allow access to information/transparency about agroforestry services, with the goal that this will improve the functioning of the RBSC, resulting in a reduction in fire risk and, consequently, improvements in sustainability concerns associated with this hazard. Full article

Inflammation and congestion are key pathophysiological processes in heart failure (HF). Our aim was to evaluate the potential modulatory effect of carbohydrate antigen 125 (CA125) on inflammation, assessed by high-sensitivity C-reactive protein (hs-CRP). We analyzed a cohort of 4043 consecutive patients in whom hs-CRP and CA125 levels were measured during a hospitalization for acute HF. Multivariate Cox regression models were applied to assess the association between the biomarkers and all-cause mortality and death/HF rehospitalization at 6 months. In multivariable analysis, a significant interaction between hs-CRP and CA125 was observed for both outcomes (p-value for interaction = 0.036 and <0.001, respectively). hs-CRP was significantly associated with an increased risk of death (HR = 1.27; 95% CI 1.16–1.41; p < 0.001) and death/HF rehospitalization (HR = 1.18; 95% CI 1.09–1.28; p < 0.001) if CA125 > 35 U/mL. In contrast, hs-CRP was not predictive of events when CA125 ≤ 35 U/mL. In conclusion, in patients with acute HF, the association between hs-CRP and clinical outcomes was modulated by CA125 levels. hs-CRP was associated with a higher risk of events only in patients with elevated CA125. These findings support a potential modulatory and amplifying role for CA125 in the inflammatory response in HF. Full article

In this study, oyster fermentation broth (OFB) was prepared by fermenting oysters with yeast, and its effects on oxidative stress and reproductive damage induced by tripterygium glycosides (TG) in male rats were investigated. Component analysis revealed that OFB contained bioactive substances including proteins (1.19 g/L), taurine (0.76 g/L), organic acids (2.30 mg/mL), polyphenols (123.00 mg GAE/L), flavonoids (1.97 mg RE/L), and zinc (1.10 mg/L). In vitro study revealed that OFB exhibited notable antioxidant activity, with a total antioxidant capacity of 1.28 U/mL, and DPPH, ABTS, and hydroxyl radical scavenging rates of 55.80%, 69.54%, and 48.36%, respectively. Animal experiments showed that, compared with the TG-induced model group, rats administered both low-dose (5 mL/kg) and high-dose (10 mL/kg) OFB showed significantly increased testis and seminal vesicle + prostate indices, sperm count, and serum testosterone (T) levels and decreased sperm malformation rate (p < 0.01 for all). Histological analysis of the testis revealed an increased number of spermatogenic cells and sperm within the seminiferous tubules, along with ameliorated pathological conditions compared to the model group. Potential mechanisms might be related to OFB increasing the activities of catalase (CAT), superoxide dismutase (SOD), and glutathione peroxidase (GSH-PX) enzymes and reducing levels of malondialdehyde (MDA) in testis (p < 0.01). The findings demonstrated that OFB successfully alleviated TG-induced reproductive damage in male rats, which might be attributed to its excellent antioxidant effect. The study offers valuable insights for producing functional foods from oysters and further validates OFB’s efficacy in promoting reproductive function. Full article

Aircraft design and development is complex and regulated by increasingly stringent regulatory documentation. While many disciplines manage design complexity with well-established digital tools, digital transformation of the certification process remains in the early stages of implementation. Models are often used to provide explicit structures to facilitate digital transformation. While several modeling approaches have been applied to regulatory documentation, a gap remains for an established list of requirements for developing effective models in the context of digital transformation. This paper proposes a list of requirements using a requirements elicitation framework adapted from the International Council on Systems Engineering (INCOSE) Needs and Requirements Manual. The adapted research methodology includes problem identification, needs assessment, and requirements development processes. The resulting requirements are validated against needs statements and verified against selected INCOSE requirement statement criteria. Four requirements are selected for a detailed feasibility assessment, which compares the efficacy of process mapping, Unified Modeling Language (UML), and ontological modeling methods to realize the requirements. Full article

Coffee cherry pulp (CCP), a coffee by-product rich in pectin and phenolic compounds, serves as a valuable substrate for microbial enzyme production, improving the nutritional and antioxidant properties of poultry feed. This study evaluated the potential of Kluyveromyces marxianus ST5 to produce pectin-degrading enzymes using CCP. Under unoptimized conditions, the pectin lyase (PL) and polygalacturonase (PG) activities were 3.29 ± 0.22 and 6.32 ± 0.13 U/mL, respectively. Optimization using a central composite design (CCD) identified optimal conditions at 16.81% (w/v) CCP, 5.87% (v/v) inoculum size, pH 5.24, and 30 °C for 48 h, resulting in PL and PG activities of 9.17 ± 0.20 and 15.78 ± 0.14 U/mL, representing increases of 178.7% and 149.7% over unoptimized conditions. Fermented CCP was further evaluated using an in vitro chicken gastrointestinal digestion model. Peptide release increased by 66.2% compared with unfermented CCP. Antioxidant capacity also improved, with significant increases observed in DPPH (32.4%), ABTS (45.0%), and FRAP (42.3%) assays, along with an 11.1% increase in total phenolic content. These results demonstrate that CCP bioconversion by K. marxianus ST5 enhances digestibility and antioxidant properties, supporting its potential as a sustainable poultry feed additive and contributing to the valorization of agro-industrial waste. Full article

The demand for land monitoring information continues to increase, but the range and diversity of the available products to date have made their integrated use challenging and, at times, counterproductive. There has therefore been a growing need to enhance and harmonise the practice of land monitoring on a pan-European level with the formulation of a more consistent and standardised set of modelling criteria. The outcome has been a paradigm shift away from a “paper map”-based world where features are given a single, fixed label to one where features have a rich characterisation which is more informative, flexible and powerful. The approach allows the characteristics to be dynamic so that, over time, a feature may only change part of its description (i.e., a forest can be felled, but it may remain as forestry if replanted) or it can have multiple descriptors (i.e., a forest may be used for both timber production and recreation). The concept proposed by the authors has evolved since 2008 from first drafts to a comprehensive and powerful tool adopted by the European Union’s Copernicus programme. It provides for the semantic decomposition of existing nomenclatures, as well as supports a descriptive approach to the mapping of all landscape features in a flexible and object-oriented manner. In this way, the key move away from classification towards the characterisation of the Earth’s surface represents a novel and innovate approach to handling complex land surface information more suited to the age of distributed databases, cloud computing and object-oriented data modelling. In this paper, the motivation for and technical approach of the EAGLE concept with its matrix and UML model implementation are explained. This is followed by an update of the latest developments and the presentation of a number of experimental and operational use cases at national and European levels, and it then concludes with thoughts on the future outlook. Full article

Background/Objectives: Hypertension is a pathological condition characterized by elevated systolic and/or diastolic blood pressure. A range of pharmacotherapeutic agents are available to treat this condition and prevent complications, including the angiotensin II AT1-receptor blocker losartan. Following oral administration, losartan is exposed to a variety of enzymes that facilitate its metabolism or transportation. The structural characteristics of the genes that encode the enzymes may potentially impact the pharmacokinetics and pharmacodynamics of losartan, thereby modulating its effects on the treatment process. Methods: In this study, a computational model of losartan pharmacokinetics was developed, taking into account the influence of different alleles of the CYP2C9 gene, which plays a pivotal role in losartan metabolism, and the ABCB1 gene, which is responsible for losartan transport. Results: Alterations in the modeled activities of the enzymes encoded by CYP2C9 and ABCB1 result in changes in the losartan and its metabolite profiles that are consistent with known experimental data in real patients with different CYP2C9 and ABCB1 genotypes. Conclusions: The findings of the modeling can potentially be used to personalize drug therapy for arterial hypertension. Full article