This study presents the design and evaluation of a multi-model artificial intelligence (AI) framework for proactive quality risk management in projects. A dataset comprising 2000 risk records was developed, containing four columns: Risk Description (input), Risk Category, Trigger, and Impact (outputs). Each output variable was modeled using three independent classifiers, forming a multi-step decision-making pipeline where one input is processed by multiple specialized models. Two feature extraction techniques, Term Frequency–Inverse Document Frequency (TF-IDF) and GloVe100 Word Embeddings, were compared in combination with several machine learning algorithms, including Logistic Regression, Support Vector Machines (SVMs), Random Forest, Multinomial Naive Bayes, and XGBoost. Results showed that model performance varied with task complexity and the number of output classes. Trigger prediction (28 classes), Logistic Regression, and SVM achieved the best performance, with a macro-average F1-score of 0.75, while XGBoost with TF-IDF features produced the highest accuracy for Risk Category classification (five classes). In Impact prediction (15 classes), SVM with Word Embeddings demonstrated superior results. The implementation, conducted in Python (v3.9.12, Anaconda), utilized Scikit-learn, XGBoost, SHAP, and Gensim libraries. SHAP visualizations and confusion matrices enhanced model interpretability. The proposed framework contributes to scalable, text-based, predictive, quality risk management, supporting real-time project decision-making.

Background: Breast cancer is the most common malignancy affecting women worldwide and continues to pose significant challenges despite progress in early detection and personalized therapies. While its pathogenesis has traditionally been associated with genetic, hormonal, and environmental factors, recent studies have highlighted the potential role of dysbiosis—an imbalance in gut and systemic microbiota—in breast cancer development and progression. This article aims to examine the mechanisms through which systemic dysbiosis may contribute to breast cancer risk and explore its therapeutic implications. Methods: This study seeks to analyze and compare the fecal microbiota profiles of breast cancer patients and healthy individuals from a single center in Craiova, Romania, in order to identify microbial signatures linked to breast cancer and BRCA mutation status. Special attention is given to the gut–liver axis and its influence on estrogen circulation, a key factor in hormone-sensitive breast cancers. Results: Evidence suggests that dysbiosis can influence breast cancer progression by promoting chronic inflammation, impairing immune regulation, and altering estrogen metabolism through the gut–liver axis. These effects may contribute to tumor development, immune evasion, and therapeutic resistance. Interventions aimed at restoring microbial balance show promise in preclinical studies for mitigating these effects. Conclusions: Systemic dysbiosis represents a potentially modifiable risk factor in breast cancer. Microbiota profiling may serve as a useful biomarker for risk stratification and therapeutic response. Future research into microbiome-based interventions could offer novel approaches for prevention and treatment in breast cancer care.

Nowadays, technology allows people to connect and communicate with each other even from miles away, no matter the distance. With the increased use of social networks that were rapidly adopted in human beings’ lives, they can chat and share different media files. While the intent for which they have been created may be positive, they can be abused and utilized in a negative way. One form in which they can be maliciously used is represented by cyberbullying. This is a form of bullying where an aggressor shares, posts, or sends false, harmful, or negative content about someone else by electronic means. In this paper, we propose a solution for bullying detection in GIFs. We employ a hybrid architecture that comprises a Convolutional Neural Network (CNN) and three Recurrent Neural Networks (RNNs). For the feature extractor, we used the DenseNet-121 model that was pre-trained on the ImageNet-1k dataset. The obtained results give an accuracy of 99%.

Background and Objectives: Fusobacterium nucleatum, an oral anaerobe well-established as an onco-pathogen in colorectal cancer, is increasingly implicated in extra-colonic malignancies, including breast cancer. Despite growing mechanistic evidence, the taxonomic composition of fecal Fusobacterium in breast cancer remains poorly resolved, particularly regarding genus-level signals that may precede Fusobacterium nucleatum enrichment and their relationships with clinicopathological and demographic variables. This study aimed to quantify Fusobacterium (Fs) fecal abundance in a Romanian breast cancer cohort, assess its independence from environmental and demographic factors, and evaluate its association with disease-specific parameters, including TNM staging and BRCA mutational carrier status. Materials and Methods: This retrospective case–control study enrolled 99 women at the University of Medicine and Pharmacy of Craiova between October 2020 and June 2025, comprising 57 breast cancer patients and 42 healthy controls. Fecal samples underwent 16S rRNA gene sequencing targeting the V3–V4 hypervariable regions. Bacterial abundance was encoded ordinally and analyzed using the Mann–Whitney U test, the chi-squared test, Spearman’s Rank Correlation, and Kendall’s Tau test, with stratification by residential environment, age, commensal co-occurrence, and cancer-specific variables. Results: Fs abundance was highly significantly elevated in breast cancer patients relative to controls (Mann–Whitney U: p = 2.433 × 10⁻¹²; chi-squared: p = 1.548 × 10⁻¹³), with no significant associations identified with residential environment or patient age across all stratified groups. No significant correlations were identified with tumor size, lymph node involvement, or metastatic status. A statistically significant differential abundance was observed between BRCA mutation carriers and non-carriers (Mann–Whitney U: p = 0.00029; chi-squared: p = 0.00076). Conclusions: Fecal Fs abundance demonstrates cancer-specific enrichment independent of demographic and environmental determinants and is significantly associated with BRCA mutational status, positioning it as a candidate non-invasive biomarker and mechanistic contributor within the gut–breast dysbiosis axis, warranting prospective multi-center validation.

With the development of high-resolution cameras and enhanced storage devices, image datasets are increasingly captured with higher spatial dimensions. Many modern object detector architectures, such as the YOLO family, typically operate at a 640x640 resolution. When training on high-resolution images, the rescaling process can drastically reduce the region of interest, especially for low- or medium-sized objects far from the camera. To analyze the impact of rescaling, a six-vehicle dataset was constructed from high-resolution images. An automated preprocessing pipeline is built, that crops each car region, enforcing a minimum size of 640x640 by symmetrically expanding the margins. A refactoring process was applied to the new set of images, resulting in a new dataset centered on the region of interest. A YOLOv10 model was trained for each dataset, with the cropped dataset achieving a higher mAP50 of 0.995 compared to the uncropped version's 0.987. A cascading multilevel model employing both YOLO models was further proposed, with the first model analyzing the initial high-resolution image at a coarser level, cropping the vehicle area, and sending it to the second YOLO model for fine-level analysis. This architecture highlights the importance of preserving fine, detailed features that would otherwise be lost during scaling.