Asian Pacific Journal of Cancer Prevention · مجلد 27 (8) · 2853-2860
BACKGROUND: Retinoblastoma (Rb) represents the most frequent primary intraocular cancer in the pediatric population; yet comprehensive national data are limited in Saudi Arabia due to incomplete cancer registry coverage and underreporting. The present study systematically investigates the incidence, distribution, and trends of retinoblastoma across Saudi Arabia over two decades, utilizing robust data from the Saudi National Cancer Registry (SCR), a nationwide surveillance system overseen by the Ministry of Health. METHODS: This retrospective population-based analysis included all children diagnosed with Rb in Saudi Arabia between January 1, 2000, and December 31, 2019. The study examined incidence rates and temporal patterns by age, regional location, and tumor histology. RESULTS: Out of 542 documented cases (258 females, 284 males), the age-standardized incidence rate (ASIR) for children aged 0-4 years demonstrated an initial increase, peaking at 1.26 per 100,000 in 2003, followed by a gradual decline to 0.93 per 100,000 by 2019. Higher incidence rates were detected in major urban centers, especially Riyadh and Makkah, likely reflecting demographic density, enhanced diagnostic practices, and more accessible specialized care. Most tumors were either undifferentiated (Grade IV) or not otherwise specified (NOS, 63%), while diffuse retinoblastoma was rare (2%). Diagnosis was predominantly confirmed by histopathological evaluation (88.3%). CONCLUSION: This study offers the most comprehensive picture to date of retinoblastoma incidence and patterns in Saudi Arabia. The observed rising incidence, together with regional disparities, emphasizes the need for more refined cancer surveillance, equitable resource allocation, and accelerated early detection strategies, particularly in underserved areas. These findings provide essential baseline metrics to inform national cancer control policies and optimize equitable resource distribution.
retinoblastomapediatric cancer incidenceSaudi Arabiaage-standardized incidence rate
Early and precise recognition of developmental disabilities (DDs) is essential for the timely intervention of preschool-age children. Although various predictive models have been developed in the past, they cannot provide accurate detections and face challenges like high false prediction, limited generalization, etc. To address these issues, a novel artificial intelligence (AI)-based algorithm was proposed for accurate DD detection. The proposed system integrates digital biomarkers from speech and behavioral domains for predicting DDs. Consequently, an Enhanced Gaussian-Based Noise Filtering (EGNF) is applied to speech data, and Z-score normalization is applied to behavioral data for preprocessing, which makes the raw data reliable for subsequent analysis. Further, feature extraction is performed using Convolutional-Bidirectional Long Short-Term Memory (Conv-BiLSTM) for speech data and Graph Attention Network (GAT) for behavioral data. Subsequently, a Hybrid Feature Selection (HFS) method was developed by combining the Harmony Search Algorithm (HSA) and ReliefF ranking for selecting informative and relevant attributes for model training. Finally, a hybrid classification model named DeepSTNet has been developed by integrating MnasNet and Independently Recurrent Neural Networks (IndRNN), which allows the capture of spatial and temporal long-term dependencies within the data, resulting in high detection performances. The proposed framework was implemented in Python and validated using comprehensive data formed by combining the Dysarthria Detection dataset and the Autism Dataset for Toddlers. The execution outcomes highlighted that the developed framework achieved an accuracy of 99.46%, a precision of 97.74%, and a recall of 98.05%, illustrating that this AI-centric system can be equipped by end users, including healthcare professionals and caregivers, with tools for early screening and detection of DDs.
Background Breast cancer is the most prevalent female malignancy in Saudi Arabia and globally, with early detection being the cornerstone of improved survival. This study assesses breast cancer screening awareness, knowledge of risk factors and signs, and screening practices among non-medical female university students in Riyadh, Saudi Arabia. Methods A cross-sectional study (July-September 2025) enrolled 679 non-medical female students aged 18 years and above from four Riyadh universities using multistage sampling. Data were collected using a structured, bilingual 58-item questionnaire adapted from previous studies, culturally modified, pilot-tested, and reviewed by experts. Knowledge and practice domains were classified as sufficient when scores exceeded 60% and insufficient when scores were ≤60%. Knowledge scores were analyzed using Mann-Whitney U and Kruskal-Wallis tests with Bonferroni correction; chi-square tests and multivariate logistic regression identified significant predictors. Results Despite 85% (n = 578) demonstrating sufficient attitudes toward screening, only 44% (n = 299) had adequate general awareness, 19% (n = 132) had sufficient knowledge of risk factors and signs, and 23% (n = 158) achieved sufficient screening practice. The median knowledge score was 19/43 (IQR: 16-22). Family history (65.5%, n = 445) and increasing age (56.7%, n = 385) were the most recognized risk factors, while early puberty (16.2%, n = 110) and nulliparity (23.6%, n = 160) were the least. While 90.9% (n = 617) identified a breast mass as a sign, only 5.9% (n = 40) correctly recognized that a painful mass is not a typical early presentation. Breast self-examination and clinical breast examination uptake were low at 40.4% (n = 274) and 23.4% (n = 159), respectively. However, these screening practice findings should be interpreted considering the young age distribution of participants, with many being below the recommended age for routine mammography screening. AlMaarefa University affiliation was the strongest predictor of knowledge (OR = 2.718; 95% CI: 1.398-5.282; p = 0.003) and screening practice (OR = 5.488; 95% CI: 2.863-10.519; p < 0.001), with family history also predicting sufficient screening practice (OR = 2.384; 95% CI: 1.488-3.819; p < 0.001). Conclusion A striking knowledge-attitude-practice gap exists in this population. Universities are underutilized platforms for breast cancer health education, and structured, culturally sensitive interventions are urgently needed to convert attitudinal willingness into consistent screening practice.
breast cancer screeningknowledge-practice gapfemale university studentsbreast cancer risk factors
Sultan Qaboos University medical journal · مجلد 26 (1) · 455-465
Objectives: Breast cancer (BC) is the most common malignancy among women worldwide and represents a significant burden for Yemeni women. Early detection through breast self-examination (BSE) and knowledge of risk factors and symptoms are crucial. This study aimed to assess awareness, knowledge and practice regarding BC risk factors, symptoms and BSE among female healthcare workers (HCWs) in Al-Mukalla, Yemen. Methods: This cross-sectional study was conducted from September to October 2022 at three public hospitals in Al-Mukalla, Yemen. A census sampling approach was used to recruit HCWs. Data were collected using a validated self-administered questionnaire covering breast awareness practices, risk factor awareness, symptom recognition and BSE frequency. Descriptive statistics and logistic regression were used to identify BSE predictors. Results: A total of 151 HCWs were included in this study (response rate = 83.0%). The mean participant age was 30.4 ± 6.1 years; 49.7% were aged 20–29 years. Most participants were unmarried (66.2%), university-educated (57.0%) and doctors (47.0%). Knowledge of hallmark symptoms such as breast masses (90.0%) was high; however, 51.0% misidentified the specific laterality (right upper outer quadrant) of the most common cancer site, rather than the quadrant itself. Regular (monthly) BSE was reported by 71.5% of participants. Multivariable analysis showed that nurses were less likely than doctors to perform BSE (adjusted odds ratio [aOR] = 0.32, 95% confidence interval [CI]: 0.14–0.73; P = 0.007). Diploma holders practised BSE less than university graduates (aOR = 0.38, 95% CI: 0.19–0.78; P = 0.008), while higher BC knowledge independently predicted greater BSE practice (aOR = 2.15, 95% CI: 1.10–4.20; P = 0.025). Conclusion: Despite good symptom awareness, significant knowledge gaps remain regarding risk factors and breast anatomy among female HCWs in Al-Mukalla, Yemen. BSE practice is still suboptimal, influenced by professional role, education level and BC knowledge. Targeted interventions focusing on breast awareness and structured education are urgently required.
breast cancerbreast self-examinationbreast cancer screeningbreast cancer knowledge
Temporal Lobe Epilepsy (TLE), a very common type of focal epilepsy, requires early and precise identification to enable prompt treatment and enhance patient outcomes. Traditional methods of detection, most notably manual MRI interpretation, tend to be time-consuming, subjective, and dependent on expert specialists, hindering their scalability and reliability. Due to the limitations of conventional and current automated systems—e.g., poor feature extraction, poor segmentation, and low accuracy in classification—this work presents NeuroTLEDNet, a new end-to-end artificial intelligence model for early TLE detection from medical images. The new methodology integrates multiple series of innovations across every processing phase. In preprocessing, skull stripping, Gaussian blurring, and color normalization are used to improve image uniformity and suppress irrelevant structures. In segmentation, the improved TLE-SegNet + is suggested—based on Mask R-CNN and supplemented with DarkNet-53, DenseNet, HetConv layers, and Attention Feature Pyramid Networks (FPN)—to facilitate highly accurate delineation of epileptogenic areas. For further describing the segmented areas, a rich feature space encompassing color histograms, Local Binary Patterns (LBP), and geometric features (eccentricity, area, perimeter) is developed. To resolve inefficiencies in feature selection, this paper presents the Squirrel Reptilian Optimization (SRO) algorithm, a new hybrid metaheuristic that incorporates both the Squirrel Search Algorithm (SSA) and the Reptile Search Algorithm (RSA). The hybrid enhances discriminative feature selection by handling exploration and exploitation dynamics better compared to individual methods. For categorization, NeuroTLEDNet utilizes an in-depth hybrid ensemble of 3D Convolutional Neural Networks (3D-CNN), Recurrent Neural Networks (RNN), Radial Basis Function Networks (RBFN), and SqueezeNet, facilitating powerful modeling of spatial-temporal relationships in brain MRI scans. Tested on an 80/30 split MRI dataset, the designed model attains a remarkable accuracy of 98.6%, outperforming current methods like CNN-LSTM (94.2%), Mask R-CNN (92.7%), and ResNet-based architectures (93.1%). Indeed, NeuroTLEDNet provides an end-to-end solution for the shortcomings of existing TLE detection methods by utilizing advanced preprocessing, segmentation, feature optimization, and hybrid classification, with state-of-the-art performance in terms of both accuracy and explainability. The suggested model is a promising candidate for clinical application, and it has the potential to assist neurologists in faster and more accurate TLE diagnosis.
Journal of the Egyptian Ophthalmological Society · مجلد 119 (2) · 165-170
Background Diabetic retinopathy (DR) is a leading cause of visual impairment and blindness worldwide. It develops as a complication of diabetes mellitus and often progresses without noticeable symptoms until vision is severely compromised. Early detection through regular screening is crucial to prevent vision loss, as timely intervention can slow disease progression. Enhancing public awareness about DR and the importance of routine ophthalmic examinations is essential for reducing its impact. Objective This study aimed to assess the level of awareness of DR among the Saudi population. Patients and methods A cross-sectional study was conducted using an online questionnaire distributed across various regions of Saudi Arabia after obtaining Institutional Review Board (IRB) approval. A total of 1000 Saudi participants aged 18 years and above were recruited using a snowball sampling method. Results Among the participants, 65.6% were females, with the largest age group between 18 and 29 years (55.5%). The central region provided the highest response rate (25%). The study revealed a high level of awareness, with 91.6% recognizing that diabetes affects the eyes and 83.5% acknowledging the need for regular screening even without symptoms. Additionally, 93.2% understood that good glycemic control can prevent DR, while 81.6% knew that DR is treatable. Furthermore, 85% were aware that the duration of diabetes influences DR development, and 83% recognized hypertension as a contributing factor. Conclusion The Saudi population demonstrates commendable awareness of DR. Continuous public health initiatives and educational campaigns are necessary to sustain and further enhance awareness, encouraging preventive practices and early detection.
Frontiers in Microbiology · مجلد 16 · 1549044-1549044
Antimicrobial resistance (AMR) is recognized as one of the foremost global health challenges, complicating the treatment of infectious diseases and contributing to increased morbidity and mortality rates. Traditionally, microbiological culture and susceptibility testing methods, such as disk diffusion and minimum inhibitory concentration (MIC) assays, have been employed to identify AMR bacteria. However, these conventional techniques are often labor intensive and time consuming and lack the requisite sensitivity for the early detection of resistance. Recent advancements in molecular and genomic technologies-such as next-generation sequencing (NGS), matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS), lateral flow immunoassays (LFIAs), PCR-based diagnostic methods, and CRISPR-based diagnostics-have revolutionized the diagnosis of AMR. These innovative approaches provide increased sensitivity, reduced turnaround times, and the ability to identify genetic resistance mechanisms. This review seeks to examine the advantages and disadvantages of both emerging technologies and traditional methods for detecting AMR, emphasizing the potential benefits and limitations inherent to each. By understanding the strengths and limitations of these technologies, stakeholders, including researchers, healthcare professionals, regulatory agencies, health authorities, financial managers, and patients, can make informed decisions aimed at preventing the emergence and dissemination of antibiotic-resistant strains, thereby ultimately increasing patient safety.
antimicrobial resistanceantibiotic resistance detectionnext-generation sequencingMALDI-TOF mass spectrometry
People of all demographics are impacted by mental illness, which has become a widespread and international health problem. Effective treatment and support for mental illnesses depend on early discovery and precise diagnosis. Notably, delayed diagnosis may lead to suicidal thoughts, destructive behaviour, and death. Manual diagnosis is time-consuming and laborious. With the advent of AI, this research aims to develop a novel mental health disorder detection network with the objective of maximum accuracy and early discovery. For this reason, this study presents a novel framework for the early detection of mental illness disorders using a multi-modal approach combining speech and behavioral data. This framework preprocesses and analyzes two distinct datasets to handle missing values, normalize data, and eliminate outliers. The proposed NeuroVibeNet combines Improved Random Forest (IRF) and Light Gradient-Boosting Machine (LightGBM) for behavioral data and Hybrid Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) for voice data. Finally, a weighted voting mechanism is applied to consolidate predictions. The proposed model achieves robust performance and a competitive accuracy of 99.06% in distinguishing normal and pathological conditions. This framework validates the feasibility of multi-modal data integration for reliable and early mental illness detection.
mental disorder detectionearly diagnosisspeech analysisbehavioral data
Congenital heart disease (CHD), impacting around 1 % of infants worldwide, constitutes a significant healthcare challenge. Early detection is crucial, however constrained by the intricacies of conventional diagnostic techniques such as auscultation and echocardiography. This research presents a tailored one-dimensional convolutional neural network (1D-CNN) for the classification of phonocardiogram (PCG) signals into normal or abnormal categories, providing an automated and efficient solution for congenital heart disease (CHD) diagnosis. The model was trained on a composite dataset consisting of local pediatric PCG signals and publicly accessible dataset. Preprocessing methods, such as low- and high-pass filtering (60-650 Hz), resampling, and noise reduction, were utilized to enhance signal quality. Data augmentation techniques, including chunking, padding, and pitch-shifting, were employed to rectify dataset imbalances and improve model efficacy. Experimental results indicate substantial enhancements, attaining an accuracy of 98.56 %, precision of 98.56 %, F1 score of 98.55 %, sensitivity of 0.98, and specificity of 0.99. The comparative analysis demonstrates the proposed approach's superiority over current methods regarding accuracy and reliability. The research highlights the promise of combining modern signal processing with deep learning for efficient CHD screening. The suggested model exhibits outstanding performance yet, issues like dataset variability and noise persist. Future endeavors involve extending to multiclass categorization and assessing performance across a wider range of medical problems. This study represents a significant advancement in accessible, automated CHD diagnoses, enhancing clinical competence to elevate pediatric treatment.
Frontiers in Pharmacology · مجلد 16 · 1525529-1525529
Introduction: Gentamicin (GM) is a frequently used aminoglycoside for managing serious illnesses; nonetheless, renal complications limit its use. Bee venom (BV) is a biological toxin that exhibits anti-inflammatory and antioxidant activities. This study was designed to explore the mitigating effect of BV remediation on GM induced renal injury. Methods: Twenty male rats were divided into four groups (five rats each), namely, control (saline subcutaneously); BV group (1 mg/kg S/C twice weekly for 1 month); GM group (100 mg/kg i. p. for 1 week); and GM-BV group (the same aforementioned dosages of GM and BV, with GM administered in the last week for 4 weeks). Results and discussion: BV mitigated the GM-inflicted kidney damage, as evidenced by a substantial improvement in the renal function and oxidative state. In addition, a downregulation in the expression of inflammatory biomarkers (Casp-1, IL-6, TNF-α, and NF-κB/P65/P50) and an upregulation of oxidative stress marker expression (NRF2) were noticed. BV upregulated the expression of aquaporins (AQPs) and renal water channel proteins (AQP1 and AQP2), which are useful for the early detection of renal injury. Additionally, BV exposure exerted a mitigating effect on the apoptotic cascade, as evidenced by the downregulation of cleaved Caspase-3 (Casp-3) and cytochrome c (Cyto c). BV administration also led to an improvement in RBC, WBC, and platelet counts, along with enhanced Hb levels. Interestingly, BV could protect against GM triggered nephrotoxicity.
Diabetes mellitus (DM) is a growing public health concern globally, particularly in Saudi Arabia, where increasing prevalence is associated with significant morbidity. This study aimed to assess the prevalence of diabetes-related complications among patients in Riyadh and examine the impact of sociodemographic factors, comorbidities, and lifestyle habits on these complications. A cross-sectional study was conducted with 980 diabetic patients attending health centers in Riyadh from March to April 2023. Data were collected via a validated bilingual questionnaire that captured sociodemographic information, diabetes-related variables, comorbid conditions, lifestyle habits, and complications. Statistical analyses, including descriptive statistics, chi-square tests, and binary regression, were performed via SPSS to identify significant associations. A p-value less than 0.05 was considered significant for all comparisons. Among the participants (980), 38% (378) reported diabetes-related complications, primarily neuropathy (30%), retinopathy (25%), and cardiovascular diseases (20%). Complications were significantly associated with older age (p < 0.001) and longer diabetes duration (more than 5 years; p < 0.001). Individuals with hypertension, hyperlipidemia, heart disease, kidney disease, and obesity had significantly higher complication rates than those without these conditions (p < 0.05). The most pronounced association was observed in participants with heart disease (85% vs. 15%; RR = 1.506), highlighting the need for better management of these comorbidities. Consuming fruits and vegetables, milk, and regular exercise were inversely associated with the risk of complications (p < 0.05). Conversely, sugary drinks, white bread, sheesha/vaping, and inadequate sleep were linked to increased risk (p < 0.05), highlighting the protective role of healthy dietary and lifestyle habits. This study highlights the impact of sociodemographic factors and lifestyle choices-such as age, education, family history, comorbidities, and poor diet-on diabetes complications. While early detection and lifestyle interventions are vital, a cautious approach is needed when applying these findings to other regions, given differences in socioeconomic circumstances.
type 2 diabetesdiabetes complicationsdiabetic neuropathydiabetic retinopathy
Journal of Family and Community Medicine · مجلد 32 (1) · 1-15
Prostate cancer (PCa) is a significant health issue characterized by the uncontrolled growth of cells in the prostate gland primarily affecting men 50 years old or older. The aim of this research was to assess the level of knowledge and attitudes of men in the Middle East towards PCa. A comprehensive search strategy in major databases from the date of first publication on this topic to April 2024 was conducted of cross-sectional studies assessing the knowledge and attitudes of adult men in the Middle East toward PCa. Data on the study's methodology, participant characteristics, and outcomes related to the knowledge of PCa and attitudes towards PCa were extracted and analyzed using the comprehensive meta-analysis software. The Newcastle-Ottawa Scale was used for quality assessment. The meta-analysis of 26 studies revealed significant heterogeneity among studies, with an overall rate of previous education on PCa at 76.3% (95% confidence interval [CI]: 61.2%- 86.8%), but a much lower rate of education on PCa screening at 20.5% (95% CI: 7.2%-46.2%). Knowledge of PCa, its screening tools, symptoms, risk factors, and treatments, as well as attitudes towards PCa screening, varied widely, with knowledge rates of 50.5% for PCa, 32.3% for screening tools, 45.5% for symptoms, 49.4% for risk factors, and 58.4% for treatments. The rate of favorable attitude towards PCa screening was reported at 50.0% (95% CI: 36.7%-63.3%). The Middle East has some understanding of PCa but there is little knowledge of screening techniques, symptoms, risk factors, and treatments. To improve early detection and patient outcomes, comprehensive education and culturally sensitive communication strategies are necessary.
prostate cancerprostate cancer screeninghealth knowledgeattitudes toward screening
Down syndrome (DS) is one of the prevalent chromosomal disorders, representing distinctive craniofacial features and a range of developmental and medical challenges. Due to the lack of clinical expertise and high infrastructure costs, access to genetic testing is restricted to resource-constrained clinical settings. There is a demand for developing a non-invasive and equitable DS screening tool, facilitating DS diagnosis for a wide range of populations. In this study, we develop and validate a robust, interpretable deep learning model for the early detection of DS using facial images of infants. A hybrid feature extraction architecture combining RegNet X-MobileNet V3 and vision transformer (ViT)-Linformer is developed for effective feature representation. We use an adaptive attention-based feature fusion to enhance the proposed model's focus on diagnostically relevant facial regions. Bayesian optimization with hyperband (BOHB) fine-tuned extremely randomized trees (ExtraTrees) is employed to classify the features. To ensure the model's generalizability, stratified five-fold cross-validation is performed. Compared to the recent DS classification approaches, the proposed model demonstrates outstanding performance, achieving an accuracy of 99.10%, precision of 98.80%, recall of 98.87%, F1-score of 98.83%, and specificity of 98.81%, on the unseen data. The findings underscore the strengths of the proposed model as a reliable screening tool to identify DS in the early stages using the facial images. This study paves the foundation to build equitable, scalable, and trustworthy digital solution for effective pediatric care across the globe.
face imagesinfantsnon-invasive screeninghybrid feature extraction
BACKGROUND: Neonatal sepsis, a leading cause of newborn mortality, arises from systemic infections due to an immature immune system. Its subtle early symptoms complicate timely diagnosis. Hematological parameters act as an indicator for early detection, crucial for prompt treatment, improving prognosis, and are not a challenging or cumbersome process. AIM: The primary objective was to evaluate the significance of hematological parameters including red blood cell (RBC), WBC, and platelet counts in the context of neonatal sepsis. METHODS: This hospital-based cohort study examined 73 neonates admitted to the neonatal intensive care unit (NICU) of Saveetha Medical College and Hospital, Chennai, India during the period of January 2023 to March 2024. All the new born patients were presented with blood culture-confirmed septicemia. RESULTS: The investigation identified Klebsiella pneumoniae as the most prevalent etiological agent (26.02%), followed by Coagulase-Negative Staphylococci (CONS) and Acinetobacter baumannii (both 8.2%). Alterations in total leukocyte count and hematocrit were observed in 57% and 68.1% of cases, respectively, providing a prompt indication of infection status. Subsequent analyses revealed prominent leukocytosis, hematocrit irregularities, and thrombocytopenia, frequently manifesting in septic cases and demonstrating potential as early markers for neonatal sepsis. CONCLUSION: The study highlights the diagnostic value of hematological alterations, such as leukocytosis and hematocrit distortion, in the prompt identification of septicemia among neonates. Based on the findings, it is recommended that routine hematological screening to be integrated as a standard component of neonatal sepsis diagnosis for rapid investigation of neonatal sepsis.
Sepsis is a life-threatening condition, and early recognition in the emergency department (ED) is crucial for reducing mortality. However, traditional ED sepsis screening tools (e.g., Systemic Inflammatory Response Syndrome (SIRS) and quick Sequential Organ Failure Assessment (qSOFA)) often lack sensitivity for early detection. Machine learning (ML)-based early warning systems have been proposed to address this gap by analyzing complex clinical data in real time. To address this, we systematically reviewed studies (2015-2025) assessing ML-based sepsis warning systems in adult EDs. Databases searched included PubMed, Embase, Scopus, and Web of Science. Included studies reported diagnostic performance and/or clinical outcomes. Overall, a total of 11 studies (primarily retrospective, with a few prospective) were included. ML models using vital signs, laboratory results, and electronic health record (EHR) data demonstrated high discrimination for sepsis, with area under the receiver operating characteristic curve (AUROC) values often exceeding 0.80, and outperformed traditional scoring tools. Many provided earlier warnings, often two to four hours before sepsis was clinically recognized. Implementation studies showed that ML-based alerts expedited treatment; one multi-center system reduced time to antibiotics by ~1.8 hours when alerts were promptly addressed. Some reports noted reduced organ failure and mortality. However, evidence of improved patient outcomes remains inconsistent, likely due to study heterogeneity and limited prospective validation. ML-based early warning systems show strong potential for improving sepsis recognition and treatment in EDs. Further multi-center trials are needed to confirm their impact on outcomes and guide safe implementation.
sepsisearly warning systemsmachine learningemergency department