Hereditary cancer syndromes (i.e. BRCA1/2-breast cancer) represent a small portion of around 6% of the population worldwide with genetic diseases, but their histopathological diagnosis is still difficult. In this paper, we present a clinical decision support system that combines an improved XGBoost classifier with SHapley Additive Explanations (SHAP) to provide high predictive accuracy and interpretable AI (XAI) in breast cancer diagnosis based on nuclear morphological features. The proposed approach employs a five-stage framework, namely: (1) Data collection from the Wisconsin Breast Cancer Diagnostic (WDBC) dataset, (2) missing value treatment by using multiple imputation by chained equations (MICE), (3) feature normalization, (4) biomarker selection using recursive feature elimination with cross validation (RFECV), and (5) class imbalance addressing by synthetic minority over-sampling technique (SMOTE). Hyperparameter tuning was done with Optuna using the Tree-structured Parzen Estimator (TPE) for 300 trials. The XGBoost model, evaluated on a test data consisting of 114 samples (20% of the total 569 samples), attained the highest accuracy of 96% and recall of 97% for class malignant, with a close to perfection ROC AUC of 0.99. SHAP results demonstrated that morphological characteristics (convex points and concavity, in particular) were the most important features, which is in line with histopathological understanding of nuclear alterations in hereditary cancer syndromes. Local waterfall plots ensured case-specific interpretability by breaking down single predictions into additive feature contributions. Although the WDBC dataset does not contain direct labels of genotype, the designed framework acts as a reproducible proof-of-concept for transparent, high-performance diagnosis of breast cancer with potential for application to hereditary syndromes, and veterinary histopathology incorporating appropriate species specific validation.

abstract

The present study aimed to assess the knowledge of diabetic patients regarding diabetes-related systemic and oral

complications and to evaluate their attitudes toward maintaining good oral health and their oral hygiene practices,

including regular dental visits. A cross-sectional study was conducted at Gharyan Educational Hospital, Gharyan,

Libya, between November 2025 and January 2026. A total of 134 diabetic patients attending scheduled outpatient

clinics were enrolled. The study found that 60.5% of participants were aware that diabetes increases the risk of

oral disease, with a high awareness of xerostomia (91%). However, knowledge of specific complications was lower;

only 46.2% identified dental caries and 42.6% identified oral fungal infections as related risks. Regarding systemic

health, patients showed higher awareness of diabetic foot and eye complications than of nerve or kidney

complications. While 73.9% of participants reported brushing their teeth, only 41.8% did so twice daily.

Furthermore, 44.8% visited the dentist less than once a year, and 41% could not remember their last visit. The

primary sources of information were diabetologists (52.9%) and various media (50%), with 98.5% of participants

expressing a desire for more education on this topic. Diabetic patients in Gharyan demonstrated a moderate level

of knowledge regarding diabetes-related oral health. While attitudes toward oral hygiene are generally positive,

there are significant gaps in knowledge regarding specific oral complications. The findings suggest an urgent need

to integrate oral health education into routine diabetic care and to strengthen collaboration between physicians and

dentists to improve overall patient outcomes.

Keywords. Diabetes mellitus, Oral Health, Knowledge, Attitude, Practice, Libya.

Abstract

This study investigates applying the artificial intelligence tools in translating culture-specific items in literary works. A heated debate has been initiated among scholars since the beginning of using AI tools in translation; the core of this debate was about the ability of AI translation tools to convey cultural nuances compared to human translators. Furthermore, techniques are usually adopted by AI translators in case of a lack of equivalence. To investigate these queries, fourteen excerpts containing cultural elements have been chosen from three Libyan novels by Ibrahim Al-Koni, The Bleeding of the Stones, Dust Gold and Anubis, are utilized as a case study to compare the human translator's work with AI translation tools, namely, ChatGPT and DeepL. The major results of this study are the performance of AI tools almost the same as human translators. Although AI translation tools outperformed human translators' work in some situations, they still require specialized training on culture-specific items related to specific communities. A collaboration between human and AI tools results in significant translation rather than separating or substituting each other. The mixing between machine and human leads to important progression in the field of translation.

The volume of Arabic text online keeps growing, and with it the need for systems that sort it into meaningful categories. A quieter problem often passes unnoticed: when long documents are split into shorter segments and pieces of the same document fall on both sides of the boundary between training and testing, the reported scores can look far better than the model deserves. This study treats that document level leakage as its central subject. Using a purpose built multidomain Arabic corpus of 1,000 segments drawn from 183 source documents across seven categories, we first measure how much leakage distorts the numbers. Under a naive random split, an optimized Linear SVM appears to reach 0.9800 accuracy; under a grouped split keyed to the document identifier, the same model reaches 0.8528. The gap of about 12.7 accuracy points is attributable to leakage, and across models the inflation ranges from roughly 11.9 to 30.4 points. Leakage also flattens the ranking, so a weak Naive Bayes looks almost as strong as the best model. Under the honest protocol, an ablation shows that character level TF IDF alone matches the combined word and character representation and slightly exceeds it on Macro F1, 0.7801 against 0.7713, while word features mainly refine precision. McNemar tests and a document clustered bootstrap show that the strongest linear models are statistically indistinguishable. A fastText baseline reaches 0.6497 accuracy, and two pretrained Arabic transformers, AraBERT and MARBERT, perform comparably to the linear model rather than surpassing it. A class level analysis exposes the General category as a structural confound whose removal raises accuracy to 0.9349. Overall, leakage aware evaluation paired with subword rich TF IDF and a Linear SVM forms a strong, honest, and practical baseline for Arabic text classification.

This study reports on a collection of spiders from Misallatah Nature Reserve and National Park (MNRNP), north western Libya, including five species recorded for the first time in the country. 75 spider samples (13 adult males, 20 adult females, 42 juveniles), comprising 12 families (Agelenidae; Araneidae; Dysderidae; Gnaphosidae; Lycosidae; Palpimanidae; Pisauridae; Philodromidae; Pholcidae; Salticidae; Thomisidae; Zodariidae), 13 genera (Lycosoides Lucas, 1846; Argiope Audouin, 1826; Dysdera Latreille, 1804; Nomisia Dalmas, 1921; Hogna Simon, 1885; Palpimanus Dufour, 1820; Holocnemus Simon, 1873; Aelurillus Simon, 1885; Menemerus Simon, 1868; Plexippus C. L. Koch, 1846; Phlegra Simon, 1876; Bassaniodes Pocock, 1903; Zodarion Walckenaer, 1826) and 13 species (Argiope lobata Pallas, 1772; Dysdera crocata C. L. Koch, 1838; Nomisia recepta Pavesi, 1880; Palpimanus gibbulus Dufour, 1820; Holocnemus pluchei Scopoli, 1763; Plexippus paykulli Audouin, 1826; Bassaniodes lalandei Audouin, 1826; Zodarion pileolonotatum Denis, 1935; Lycosoides flavomaculata Lucas, 1846; Hogna effera O. Pickard-Cambridge, 1872; Aelurillus blandus Simon, 1871; Menemerus taeniatus L. Koch, 1867; Phlegra yaelae Prószyński, 1998) were collected; the last five species are first records in Libya.

.

This study reports on a collection of spiders from Misallatah Nature Reserve and National Park (MNRNP), north western Libya, including five species recorded for the first time in the country. 75 spider samples (13 adult males, 20 adult females, 42 juveniles), comprising 12 families (Agelenidae; Araneidae; Dysderidae; Gnaphosidae; Lycosidae; Palpimanidae; Pisauridae; Philodromidae; Pholcidae; Salticidae; Thomisidae; Zodariidae), 13 genera (Lycosoides Lucas, 1846; Argiope Audouin, 1826; Dysdera Latreille, 1804; Nomisia Dalmas, 1921; Hogna Simon, 1885; Palpimanus Dufour, 1820; Holocnemus Simon, 1873; Aelurillus Simon, 1885; Menemerus Simon, 1868; Plexippus C. L. Koch, 1846; Phlegra Simon, 1876; Bassaniodes Pocock, 1903; Zodarion Walckenaer, 1826) and 13 species (Argiope lobata Pallas, 1772; Dysdera crocata C. L. Koch, 1838; Nomisia recepta Pavesi, 1880; Palpimanus gibbulus Dufour, 1820; Holocnemus pluchei Scopoli, 1763; Plexippus paykulli Audouin, 1826; Bassaniodes lalandei Audouin, 1826; Zodarion pileolonotatum Denis, 1935; Lycosoides flavomaculata Lucas, 1846; Hogna effera O. Pickard-Cambridge, 1872; Aelurillus blandus Simon, 1871; Menemerus taeniatus L. Koch, 1867; Phlegra yaelae Prószyński, 1998) were collected; the last five species are first records in Libya.