Abstract Objective This study aimed to develop, validate, and compare robust machine learning (ML) models that integrate readily available clinical data for predicting prostate cancer (PCa) and clinically significant PCa (csPCa) in patients within the prostate-specific antigen (PSA) gray zone from a multicenter cohort in Saudi Arabia. Methods A retrospective multicenter study was conducted using data from 704 patients in Riyadh, Saudi Arabia. Two predictive models were developed: Model 1 for any PCa (N = 240/704) and Model 2 for csPCa (N = 154/704) patients. The input features included age, PSA density, prostate volume, and mpMRI risk. The dataset was split into training (N = 563) and testing (N = 141) sets. To ensure a robust evaluation, k-fold cross-validation (k = 5) was performed on the training set to assess model stability before the final evaluation on the independent test set. Eight ML algorithms were evaluated, with performance assessed using Accuracy, F1-score, and the Area Under the Receiver Operating Characteristic Curve (AUC) on the test set. Results For clinically relevant Model 2 (csPCa prediction), the GradientBoost classifier demonstrated superior performance, achieving an AUC of 0.88 (95% CI: 0.83–0.93) and an accuracy of 0.82. For Model 1 (any PCa), GradientBoost also performed best, with an AUC of 0.897 and an accuracy of 0.83. Analysis of importance revealed that prostate volume was the most influential predictor in both models. Explainable AI (XAI) techniques, specifically SHAP (SHapley Additive exPlanations), were incorporated to provide transparency into the model’s decision-making process. Conclusion The developed machine learning model, particularly the GradientBoost classifier, is a promising tool for risk stratification of csPCa in the PSA gray zone. This model has the potential to aid in patient selection for prostate biopsy, thereby reducing unnecessary procedures and associated morbidity in the Saudi population. Further prospective validation is required to confirm its clinical impact. Integrating this model into clinical software could offer clinicians real-time, data-driven risk assessments, thereby optimizing personalized patient care.

Background While global meta-analyses have identified broad risk factors for kidney stone recurrence, data on specific determinants of recurrent ureteral stones in the Middle Eastern region remain limited. We aimed to identify the clinical, demographic, and metabolic determinants of recurrent ureteral stones, including body mass index (BMI). Materials This retrospective cohort study was conducted at a single institution in Saudi Arabia. Clinical data from 57 patients with ureteral stones were analyzed. The variables included age, sex, BMI, stone composition, comorbidities (diabetes mellitus (DM), hypertension (HT), and gout), and back pain. Univariate (independent t-tests and chi-square tests) and multivariate logistic regression models were used to assess associations with recurrence. Recurrence was defined as two or more episodes of stone passage or intervention within 12 months. Results Recurrence occurred in 30% of the patients. On multivariate analysis, gout (odds ratio (OR): 8.6, 95% confidence interval (CI): 1.3-56.7, p = 0.026) and uric acid stones (OR: 4.9, 95% CI: 1.1-21.9, p = 0.038) were independently associated with recurrence, while back pain showed a trend toward significance (OR: 4.1, 95% CI: 0.9-18.6, p = 0.07). BMI, age, and sex were not significantly associated (p > 0.05). Conclusion Gout and uric acid stone composition were independent predictors of ureteral stone recurrence. Despite the limitations of a small sample size and short follow-up period, targeted metabolic screening and management of hyperuricemia may reduce the risk of recurrence.

Machine learning (ML) is a significant area of artificial intelligence, which can improve the accuracy of predictive or diagnostic models for differentiating between prostate biopsy outcomes. This study aims to develop a novel decision-support ML model for classifying patients with biopsy-negative (cancer-free), clinically significant, and non-clinically significant prostate cancer across two prostate-specific antigen (PSA) cut-offs ≤ 10 ng/ml and > 10 ng/ml. The data for the current study were retrieved from the records of two main hospitals in Riyadh, Saudi Arabia from July 2018 through July 2024. Six machine learning algorithms were employed, and the dataset was randomly divided into a training set and a validation set at a ratio of 8:2. The following metrics were used as performance indicators across the six algorithms: Accuracy, Precision, Recall, F1-score, and area under the curve. Recent data from the two hospitals was utilized for external validation. The metrics for Random Forest, Extra Tree, and Decision Tree algorithms showed excellent capability in classifying the outcomes of prostate biopsy for the two PSA cut-offs. However, the metrics for the PSA cut-off > 10 ng/ml are higher than those for PSA ≤ 10 ng/ml. For the three-class classification, the accuracy and area under the curve for the cut-off > 10 ng/ml were 0.96 and 0.99, respectively. While for the cut-off ≤ 10 ng/ml they were 0.92 and 0.94 for Random Forest and 0.94 and 0.95 for the Extra Tree algorithm. The metrics of non-clinically significant and biopsy-negative cases outperformed those of clinically significant cases. ML models are proving to be effective tools in differentiating between prostate biopsy outcomes, enhancing diagnostic accuracy, and potentially transforming clinical practices in prostate cancer management.

Prostate cancer (PCa) is an emerging public health concern in Saudi Arabia, with increasing incidence and significant challenges in early detection and management. This review summarizes current research on PCa in Saudi Arabia, covering its incidence, risk factors, treatment outcomes, screening practices, awareness, and recent advancements. We aim to offer a thorough understanding to healthcare professionals, policymakers, and the public. Data from observational studies, cancer registries, and clinical guidelines published between 2008 and 2024 were also reviewed. The incidence of prostate cancer is rising, with 752 new cases by 2022; however, it remains lower than that in Western countries. High metastasis rates at diagnosis (31.4%) and low screening uptake contribute to poor outcomes, with a 5-year survival rate of 49%. Treatment aligns with international standards; however, awareness and early detection lag. Enhanced screening and education are recommended to improve prognosis.

Objectives: This study aimed to predict and classify MRI PI-RADs scores using different machine learning algorithms and to detect the concordance of PI-RADs scoring with the outcome target of prostate biopsy. Methods: Machine learning (ML) algorithms were used to develop best-fitting models for the prediction and classification of MRI PI-RAD. The Random Forest and Extra Trees models achieved the best performance compared to the other methods. Results: The accuracy of both models was 91.95%. The AUC was 0.9329 for the Random Forest model and 0.9404 for the Extra Trees model. PSA level, PSA density, and diameter of the largest lesion were the most important features for the importance of outcome classification. ML prediction enhanced the PI-RAD classification, where clinically significant prostate cancer (csPCa) cases increased from 0% to 1.9% in the low-risk PI-RAD class, this showed that the model identified some previously missed cases. Conclusions: Predictive machine learning models showed an excellent ability to predict MRI Pi-RAD scores and discriminate between low- and high-risk scores. However, caution should be exercised, as a high percentage of negative biopsy cases were assigned Pi-RAD 4 and Pi-RAD 5 scores. ML integration may enhance PI-RAD’s utility by reducing unnecessary biopsies in low-risk patients (via better csPCa detection) and refining the high-risk categorization. Combining such PI-RAD scores with significant parameters, such as PSA density, lesion diameter, number of lesions, and age, in decision curve analysis and utility paradigms would assist physicians’ clinical decisions.

Background Despite Saudi Arabia's sunny climate, vitamin D deficiency is prevalent. We aimed to utilize several machine learning algorithms to predict Vitamin D deficiency among Saudi men and identify correlated features. Methods We collected data from the records of King Khalid University Hospital in Riyadh between 2019 and 2021. Variables included health conditions, race, blood pressure, BMI, blood glucose, lipid profile, and total 25-hydroxyvitamin D (25OHD) levels. Six ML algorithms (Support Vector Machine, decision tree, linear regression, gradient boosting, XGBoost, and random forest) were employed to construct models for both cutoff points of <75 nmol/L and <50 nmol/L. The dataset was randomly divided into the training set and validation set at a ratio of 8:2. The accuracy of the algorithm was tested using the ten-fold cross-validation method. Performance metrics such as accuracy, precision, recall, F1 score, and area under the precision-recall curve (PRC, AUC) were assessed and compared between the models for both categories. Results Among 1700 Saudi men, 76.1% exhibited vitamin D deficiency (<75 nmol/l), with 52.5% deficient using an alternative cutoff (<50 nmol/l). Gradient boosting algorithm exhibited superior predictive accuracy, especially at the <75 nmol/L cutoff, outperforming the discrimination power of other algorithms for both classes. BMI emerged as the strongest predictor of vitamin D deficiency, followed by age and blood sugar results. The PRC, AUC for the <50 cutoff varies between 0.59 and 0.63 for the four classifiers (SVM, Linear regression, XGBoost, and Gradient boosting), whereas it reached 0.83 for the <75 cutoff. Conclusion Vitamin D deficiency is prevalent among healthy Saudi Arabian men. ML algorithms have proven effective in identifying correlated features within this highly impacted population, enabling tailored interventions and appropriate preventive strategies to address vitamin D deficiency and insufficiency. This model's high accuracy can help identify individuals at risk without the need for costly and time-consuming blood tests.

The integration of artificial intelligence (AI) into healthcare has sparked significant debate regarding its potential to outperform human physicians in the diagnosis and treatment of complex medical cases. While physicians rely on years of education, clinical experience, and intuition, AI platforms leverage vast datasets, machine learning algorithms, and computational power to analyze patterns and predict outcomes. This manuscript explores real-world scenarios in which AI and physicians have been pitted against each other or worked collaboratively, examining whether AI truly holds an advantage in managing complicated cases. By analyzing the strengths and limitations of both approaches, we aimed to provide insights into how AI can complement, rather than replace, physician expertise in modern medicine. This complementary relationship becomes particularly significant when considering the inherent complexity of medical practice, in which human expertise and technological capabilities must work together to address multifaceted clinical challenges. This study investigates the specifics of how AI can augment physicians’ capabilities in handling complicated medical cases, setting the stage for detailed exploration.

Artificial intelligence (AI) has evolved rapidly in the last century. Once a futuristic concept with negative connotations, AI has now begun to permeate various fields, reaching academic and scientific writing. In scientific writing, AI applications promise to significantly improve writing accuracy, provide quality control, and thereby enhance manuscript evaluation, among other possible contributions. It is generally agreed that AI and machine learning tools may become writing assistants if involved in writing tasks. Keywords: Artificial Intelligence, Scientific Writing

Introduction: Cancer education and informing people about cancer treatment and its sequel and their fertility can significantly lessen their health risk. Objective: The aim of the current study was to assess medical students’ knowledge, attitudes, and understanding toward fertility preservation (FP) for cancer patients. Methods: This cross-sectional study was conducted among medical students at two universities in Riyadh. A questionnaire was developed based on different surveys and was adapted to our culture. It was composed of two parts: sociodemographic data and questions assessing students’ knowledge and attitudes regarding FP. The second section discussed factors that could influence the utilization of FP services. It was composed of 5 questions, 4-point Likert scale (greatly, usually, rarely, never) scored from 1 for never to 4 for greatly. Results: Students, particularly females, were more knowledgeable about different FP methods, such as Gonadotrophin releasing hormones, sperm cryopreservation, and oocyte cryopreservation. They stated that cost, lack of information, and access to FP services are the most common factors hindering the utilization of services. They expressed a good attitude toward FP; however, nearly half of them mentioned that cancer treatment should be started first before FP. Conclusion: This study demonstrated the respectable awareness and attitude of FP among Saudi medical students. However, some gaps are present, indicating the need to improve education about FP in the medical curriculum.

Introduction A quasi-experimental study was conducted to assess students' attitudes toward the flipped practical classroom and evaluate its effectiveness in teaching practical anatomy. Methods Two survey questionnaires were developed: the first assessed students' attitudes toward flipped practical classrooms, while the second focused on the obstacles and difficulties students might encounter in this learning environment. Results We found that students rated flipped learning significantly higher compared to other teaching methods, particularly in terms of the quality of learning materials, enhancement of learning skills, engagement and understanding of anatomy topics, and problem-solving abilities. The highest mean examination grades were observed for the pretest flipped modality, followed by the pretest small group discussion (mean scores: 82.72 vs. 54.46, F = 43.2, P = 0.004). Conclusions Students hold positive attitudes toward flipped classrooms and small group discussions compared to traditional classes.

Artificial intelligence (AI) is developing rapidly. Integrating AI into healthcare practices in the Arab world will transform diagnosis, prediction, and disease management. Today, countries such as Saudi Arabia and the United Arab Emirates (UAE) are at the forefront of AI adoption in healthcare, supported by strategic frameworks such as Saudi Arabia's Vision 2030 and the UAE National Artificial Intelligence Strategy 2031. However, adopting AI in daily healthcare practice on a large scale faces many obstacles that need to be overcome. Keywords: Artificial intelligence, AI, healthcare practice, diagnosis, prediction, and disease management, Arab world.

OBJECTIVES:The aims of the study were to construct a new prognostic prediction model for detecting prostate cancer (PCa) patients using machine-learning (ML) techniques and to compare those models across systematic and target biopsy detection techniques. METHODS:The records of the two main hospitals in Riyadh, Saudi Arabia, were analyzed for data on diagnosed PCa from 2019 to 2023. Four ML algorithms were utilized for the prediction and classification of PCa. RESULTS:A total of 528 patients with prostate-specific antigen (PSA) greater than 3.5 ng/mL who had undergone transrectal ultrasound-guided prostate biopsy were evaluated. The total number of confirmed PCa cases was 234. Age, prostate volume, PSA, body mass index (BMI), multiparametric magnetic resonance imaging (mpMRI) score, number of regions of interest detected in MRI, and the diameter of the largest size lesion were significantly associated with PCa. Random Forest (RF) and XGBoost (XGB) (ML algorithms) accurately predicted PCa. Yet, their performance for classification and prediction of PCa was higher and more accurate for cases detected by targeted and combined biopsy (systematic and targeted together) compared to systematic biopsy alone. F1, the area under the curve (AUC), and the accuracy of XGB and RF models for targeted biopsy and combined biopsy ranged from 0.94 to 0.97 compared to the AUC of systematic biopsy for RF and XGB algorithms, respectively. CONCLUSIONS:The RF model generated and presented an excellent prediction capability for the risk of PCa detected by targeted and combined biopsy compared to systematic biopsy alone. ML models can prevent missed PCa diagnoses by serving as a screening tool.

BACKGROUND:Neuroanatomy is essential to clinical neurosciences and is one of the most difficult components of the anatomy curriculum. Flipped classrooms are one of the pedagogical approaches that have been found to enhance students' abilities and encourage in-depth learning. The current study aims to assess the attitudes and effects of flipped classrooms on neuroanatomy teaching among medical students compared to traditional classrooms. METHODS:A quasi-experimental study was carried out during the period January through June 2023. The effectiveness of teaching neuroanatomy in flipped classrooms versus traditional classrooms was assessed using formative assessment and a pre-designed structured questionnaire. The questionnaire was composed of four sections assessing different domains on a Likert scale ranging from 1 (strongly disagree) to 5 (strongly agree). RESULTS:The total sample reached 214 students. Most students' attitude statements covering skills, knowledge and learning process, and length of time were significantly in favor of flipped teaching at the expense of traditional teaching. Then mean examination grades were significantly higher for pre-test flipped and post-test flipped in comparison to pre-test and post-test traditional examination. CONCLUSIONS:Although the flipped classroom is an effective method of learning neuroanatomy as compared to traditional classes, it faces some challenges in its implementation. Such challenges need awareness and solutions from educational institutions.

The metal ion-based nanocomposite photocatalysts were accepted to exhibit a wide range of photocatalytic and biological applications. In this paper, we synthesize bare Fe2O3, 1 wt% metal (Ag, Co, and Cu) doped Fe2O3 nanoparticles (NPs) using a simple hydrothermal process and wet impregnation method. The as-prepared nanomaterials crystalline structure, shape, optical characteristics, and elemental composition were determined by using X-ray powder diffraction (XRD), X-ray photoelectron spectroscopy (XPS), Scanning electron microscope (SEM), Energy-dispersive X-ray (EDS) and Transmission electron microscopy (TEM) techniques. Furthermore, the synthesized nanocomposites were utilized as a photosensitizer for the degradation of reactive red (RR120) and orange II (O-II) dyes under sunlight irradiation. The synthesized 1 wt% Ag–Fe2O3 (AgF) NPs samples exhibit a more exceptional catalytic performance of RR120 and O-II dyes (98.32%) within 120 min than the existing Fe2O3, 1 wt% Co–Fe2O3, and Cu–Fe2O3 NPs. The effect of parameters such as exciton formation under solar irradiation, charge recombination rate, and surface charge availability. The metal oxide-doped nanocomposite economic relevance is revealed by their long-term durability and recyclability in photodegradation reactions. The photocatalytic investigations show that the active species O2∙−, HO∙ and h+ play an important role in the dye degradation process. This research might pave the opportunity for the sustainable development of greater photocatalysts for photodegradation and a wide range of environmental applications.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by social, stereotypical, and repetitive behaviors. Neural dysregulation was proposed as an etiological factor in ASD. The sodium leakage channel (NCA), regulated by NLF-1 (NCA localization factor-1), has a major role in maintaining the physiological excitatory function of neurons. We aimed to examine the level of NLF-1 in ASD children and correlate it with the severity of the disease. We examined the plasma levels of NLF-1 in 80 ASD and neurotypical children using ELISA. The diagnosis and severity of ASD were based on the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition (DSM-IV), Childhood Autism Rating Score, Social Responsiveness Scale, and Short Sensory Profile. Then, we compared the levels of NLF-1 with the severity of the disease and behavioral and sensory symptoms. Our results showed a significant decrease in the plasma levels of NLF-1 in ASD children compared to neurotypical children (p < 0.001). Additionally, NLF-1 was significantly correlated with the severity of the behavioral symptoms of ASD (p < 0.05). The low levels of NLF-1 in ASD children potentially affect the severity of their behavioral symptoms by reducing neuron excitability through NCA. These novel findings open a new venue for pharmacological and possible genetic research involving NCA in ASD children.

Background: Prostate cancer screening with prostate-specific antigen (PSA) can result in unnecessary biopsies and overdiagnosis. Alternately, PSA density (PSAD) calculation may help support biopsy decisions; however, evidence of its usefulness is not concrete. Objective: To evaluate the predictive value of PSAD for clinically significant prostate cancer detection by systematic and MRI-targeted biopsies. Methods: This prospective study was conducted at two tertiary hospitals in Riyadh, Saudi Arabia, between December 2018 and November 2021. Patients suspected of prostate cancer were subjected to multi-parametric MRI, and for those with positive findings, systematic and targeted biopsies were performed. Clinically non-significant and significant prostate cancer cases were classified based on histopathology-defined ISUP grade or Gleason score. The PSAD was measured using the prostate volume determined by the MRI and categorized into ≤0.15, 0.16–0.20, and >0.20 ng/ml2 subgroups. Results: Systematic and targeted biopsies were carried out for 284 patients. The discriminant ability of PSAD is higher in MRI-targeted biopsy compared with systematic biopsy (AUC: 0.77 vs. 0.73). The highest sensitivity (97%) and specificity (87%) were detected at 0.07 ng/ml2 in targeted biopsy. More than half of the clinically significant cases were detected in the >0.2 ng/ml2 PSAD category (systematic: 52.4%; targeted: 51.1%). The CHAID methodology found that the probability of having clinically significant cancer (CSC) in patients with PSAD >0.15 ng/ml2 was more than threefold than that in patients with PSAD ≤0.15 ng/ml2 (64% vs. 20.2%). When considered by age, in PSAD ≤0.15 ng/ml2 subgroup, the percentage of CSC detection rate increased from 20.2% to 24.6% in patients aged ≥60 years. Conclusion: PSAD has good discriminant power for predicting clinically significant prostate cancer. A cutoff of 0.07 ng/ml2 should be adopted, but should be interpreted with caution and by considering other parameters such as age.

This research was performed to evaluate physico-chemical properties of farmland soil nearby the magnesite mine site. Unexpectedly, few physico-chemical properties were crossing the acceptable limits. Particularly, the quantities of Cd (112.34 ± 3.25), Pb (386.42 ± 11.71), Zn (854.28 ± 3.53), and Mn (2538 ± 41.11) were crossing the permissible limits. Among 11 bacterial cultures isolated from the metal contaminated soil, 2 isolates names as SS1 and SS3 showed significant multi-metal tolerance up to the concentration of 750 mg L-1. Furthermore, these strains also showed considerable metal mobilization as well as absorption ability on metal contaminated soil under in-vitro conditions. In a short duration of treatment, these isolates effectively mobilize and absorb the metals from the polluted soil. The results obtained from the greenhouse investigation with Vigna mungo revealed that the among various treatment (T1 to T5) groups, the T3 (V. mungo + SS1+SS3) showed remarkable phytoremediation potential (Pb: 50.88, Mn: 152, Cd: 14.54, and Zn: 67.99 mg kg-1) on metal contaminated soil. Furthermore, these isolates influence the growth as well as biomass of V. mungo under greenhouse conditions on metal contaminated soil. These findings suggest that combining multi-metal tolerant bacterial isolates can improve the phytoextraction efficiency of V. mungo on metal-contaminated soil.

MnO2 nanoparticles have a wide range of applications, including catalytic abilities due to their oxygen reduction potential. Industrial processes and the burning of organic materials released PAHs into the biosphere which have adverse effects on living organisms when continually exposed. In this study, MnO2 nanoparticles were synthesized chemically using sodium thiosulphate as reducing agent. MnO2 nanoparticles were characterized using UV-visible adsorption spectroscopy and Fourier Transform Infrared Spectroscopy (FTIR). A X-Ray Diffraction Spectrophotometer (XRD), a Scanning Electron Microscopy - Energy Dispersive X-Ray Analyzer (SEM-EDAX), and Dynamic Light Scattering (DLS) were used to identify the crystalline nature and particle size of the fabricated MnO2 nanoparticles. Batch adsorption studies were conducted to identify the optimal conditions for better benzene and pyrene adsorption from aqueous solution using MnO2 nanoparticles. They are also effective in degrading benzene and pyrene by batch adsorption as determined by their adsorption isotherms and kinetics.

Abstract Background Current practice of offering fertility preservation counseling and treatment has become one of the focal points in patient care throughout cancer treatment. The turning point was the approval of the Council of Senior Religious Scholars four years ago to freeze tissues from the ovarian membrane, the entire ovary, and the eggs for later use in reproduction to preserve the offspring. Thus, we aimed to assess any development in oncologists' knowledge, attitude, and referral practices toward fertility preservation (FP) in Saudi Arabia. Results Most oncologists showed superior knowledge and positive attitudes toward FP; however, their referral practices could be better. Most were familiar with FP options. The most significant factors influencing the oncologist-patient FP discussion were the number of existing children (96.6%), marital status, cost, and type of cancer (76.7%, 65.7%, and 58.9 respectively). Conclusions There is a significant improvement in the knowledge and attitude of oncologists toward FP. However, patients' counseling and referral to fertility services still need to be improved. There is a shortfall in the clinical practice guidelines for FP in cancer patients in Saudi Arabia. The implementation of clinical practice guidelines would enhance FP. However, patients' counseling and referral to fertility services still need to be improved.