With the advancement in technology, machine learning can be applied to diagnose the mass/tumor in the brain using magnetic resonance imaging (MRI). This work proposes a novel developed transfer deep-learning model for the early diagnosis of brain tumors into their subclasses, such as pituitary, meningioma, and glioma. First, various layers of isolated convolutional-neural-network (CNN) models are built from scratch to check their performances for brain MRI images. Then, the 22-layer, binary-classification (tumor or no tumor) isolated-CNN model is re-utilized to re-adjust the neurons’ weights for classifying brain MRI images into tumor subclasses using the transfer-learning concept. As a result, the developed transfer-learned model has a high accuracy of 95.75% for the MRI images of the same MRI machine. Furthermore, the developed transfer-learned model has also been tested using the brain MRI images of another machine to validate its adaptability, general capability, and reliability for real-time application in the future. The results showed that the proposed model has a high accuracy of 96.89% for an unseen brain MRI dataset. Thus, the proposed deep-learning framework can help doctors and radiologists diagnose brain tumors early.

Breast cancer is the most commonly diagnosed cancer among women in the Kingdom of Saudi Arabia and other Middle East countries. This analytical cross-sectional study assessed knowledge, attitude towards breast cancer, and barriers to mammogram screening among 414 randomly selected female healthcare workers from multiple healthcare facilities in northern Saudi Arabia. Of the studied population, 48.6% had low knowledge, and 16.1% had a low attitude towards breast cancer risk factors and symptoms. The common barriers to mammogram screening were fear to discover cancer (57.2%) and apprehension regarding radiation exposure (57%). Logistic regression analysis found that lack of awareness regarding mammogram was significantly associated with age (p = 0.030) and healthcare workers category (ref: physicians: p = 0.016). In addition, we found a significant negative correlation between knowledge and barrier scores (Spearman’s rho: −0.315, p < 0.001). It is recommended to develop target-oriented educational programs for the healthcare workers, which would empower them to educate the community regarding the risk factors and the importance of mammogram screening. Furthermore, a prospective study is warranted in other regions of the Kingdom of Saudi Arabia to understand the region-specific training needs for the healthcare workers.

Parents are an essential element of family intervention for all children, including those with autism spectrum disorders (ASDs). We can better understand and address parents’ knowledge gaps about ASD through in-depth research and inquiry into parents’ current level of understanding, attitude, and perception. We aimed to assess the knowledge, attitude, and perception of ASD and influencing factors towards ASD among a group of parents with and without a child diagnosed with ASD in Sakaka, Al-Jouf Region, Saudi Arabia. Using the cross-sectional study design, information from the parents was gathered using a pretested questionnaire that included validated scales for measuring knowledge, attitudes, and perceptions related to ASD. The required number of participants was selected using the convenience sampling method. We used Spearman’s correlation test to determine the strength and direction of correlation between each domain. As a last step, we analyzed the influencing factors using binomial logistic regression. Among the 400 participants, 41.2% had high knowledge, 69.1% had a positive attitude, and 60.3% had a high perception of ASD. We found that knowledge was significantly higher among the parents with autistic individuals in the family (p = 038). The high and positive attitude was significantly greater among females (p = 0.010) and parents with high income (p = 0.007), and the perception was significantly associated with females (p = 0.037) and highly educated participants (p = 0.046). Furthermore, we found a positive correlation between knowledge, attitude, and perception. Overall, only less than half of the participants had a high knowledge of ASD. Hence, we recommend awareness-raising programs for the parents in this region. Furthermore, a prospective study involving parents from all provinces of Saudi Arabia is recommended.

Background: Mammogram screening (MS) is the gold-standard method for early detection of breast cancer (BC), and its use has been proven to minimize BC-related deaths and reduce treatment costs. However, recent epidemiological surveys have reported that rates of mammogram uptake by the Saudi female population are low. Here, we assessed the knowledge of BC and perceived barriers to MS uptake among pre-eligible northern Saudi women. Participants and Methods: We administered a standard and validated Arabic questionnaire to 400 women aged 40– 69 years. SPSS version 21.0 (IBM Corporation, Armonk, NY, USA) was used for data analysis. We applied logistic regression analysis to find the factors associated with participants’ knowledge of BC and MS. Spearman correlation test was applied to find the correlation between knowledge and barrier scores. Results: The study participants reported that smoking habits (61.3%) and unhealthy food habits (57.8%) were the most common risk factors for BC. Of the studied participants, 56.3% had low or medium degrees of knowledge about BC risk factors and MS. The degree of knowledge was significantly associated with education level (adjusted odds ratio [aOR], 2.35; 95% confidence interval [CI]. = 1.61– 3.13; P = 0.008) and a family history of BC (aOR, 3.66; 95% CI, 1.94– 5.49; P < 0.001). Fear of a BC diagnosis (50.8%) and concerns regarding test procedures were the most common barriers to MS uptake. We also found a negative correlation between participants’ knowledge and perceived barriers to MS (rho = − 0.389, P < 0.001). Conclusion: We recommend that concerned authorities offer women multiple health education sessions covering BC risk factors and the necessity for pre-eligible women to undergo MS spaced at regular intervals at different facilities. Furthermore, a multicentric mixed-methods survey is warranted to find the qualitative aspects of barriers to MS.

Automated chest X-ray diagnosis fails most critically when models produce confident yet incorrect predictions, suppressing clinical oversight at the point of decision-making. Existing uncertainty estimation methods define epistemic uncertainty primarily as a property of model parameters, overlooking whether predictions remain consistent with clinically similar cases. We propose that the divergence between a model’s prediction and the empirical label distribution of neighbouring training cases provides a practical reliability signal—one that correlates with, and can serve as a proxy for, epistemic uncertainty, while acknowledging that it may also reflect additional sources of discrepancy including label noise, representation error, and local population variability. To operationalize this perspective, we introduce a retrieval-based framework that constructs a fixed embedding-space memory of training cases and estimates a non-parametric label distribution over nearest neighbours. This enables direct comparison between model predictions and local case-level structure without introducing additional trainable parameters or modifying the diagnostic backbone. Experiments on ChestX-ray14 demonstrate improved detection of misclassified predictions relative to deep ensembles, with approximately 2.9 percentage-point gains in uncertainty-based error identification and an approximately 23% reduction in calibration error. Under zero-shot transfer to PadChest and CheXpert, the proposed approach exhibits smaller degradation in uncertainty estimation quality, with larger improvements observed for rare pathological conditions. These findings suggest that case-level consistency provides a meaningful practical signal for reliability estimation in medical imaging, whose relationship to the classical epistemic–aleatoric decomposition warrants further theoretical investigation across broader clinical settings.