IntroductionAdaptive assessment has emerged as a promising approach for addressing learner heterogeneity in digital and online education, yet many existing systems rely on predefined psychometric assumptions that inadequately capture the complex, non-linear relationships among learner characteristics, engagement patterns, and academic performance. This study reports an exploratory feasibility study of a data-driven framework for personalised adaptive question recommendation, designed to estimate anticipated item difficulty using a multivariate set of learner indicators comprising prior academic achievement, engagement levels, study behaviours, and prior course experience. Because the anticipated-difficulty label is derived from four of these same learner indicators, the framework is best understood as a proof-of-concept for recovering a theoretically motivated scoring rule rather than as an independently validated measure of difficulty.MethodsTo explore this proof-of-concept, an exploratory research design was adopted using an authentic dataset of 71 undergraduate students enrolled across two courses at a higher education institution in Saudi Arabia. A multilayer perceptron (MLP) model was employed to capture non-linear interactions among learner variables, with preprocessing safeguards including ordinal-preserving feature encoding, LOWESS-based outlier suppression, and stratification-controlled oversampling applied exclusively to the training partition. Model performance was evaluated using Repeated Stratified K-Fold cross-validation across nine classifiers, with holdout test evaluation and post hoc feature influence analysis conducted to support pedagogical interpretability.ResultsThe proposed MLP (RMSprop) achieved 93.33% test accuracy (Wilson 95% CI: 70.2%–98.8%, n = 15), demonstrating stable predictive performance and generalisation beyond training data despite sample size constraints. However, the small holdout sample, and the single observation underlying the Hard-class result in particular, mean these figures should be read as indicative rather than precise. Feature analysis indicated that learner engagement and prior academic performance were the most influential contributors to anticipated difficulty estimation, while misclassification patterns were primarily confined to adjacent difficulty levels, reflecting the inherent continuity of learner challenge.DiscussionThe findings suggest that data-driven adaptive mechanisms can complement traditional assessment approaches by providing context-sensitive, learner-relative difficulty estimation aligned with formative assessment principles. Fairness was not empirically evaluated in this study and is identified as a direction for future work rather than a current contribution. While exploratory in nature, this work contributes to bridging the gap between machine learning–based modelling and principled educational assessment design, offering a foundation for future large-scale and multi-context investigations.

The rapid integration of artificial intelligence (AI) into higher education is reshaping teaching, learning, and assessment, particularly in programming education. While AI coding assistants can enhance feedback, scaffolding, and student engagement, their educational value depends on pedagogical alignment, institutional readiness, and faculty practice, not merely technical capability. Existing adoption frameworks, however, inadequately address these pedagogical and institutional dimensions in domain-specific contexts. This study proposes the AI Coding Assistant Adoption Framework (AICAAF), a theoretically grounded model integrating the Technology Acceptance Model (TAM), the Unified Theory of Acceptance and Use of Technology (UTAUT), and Self-Determination Theory (SDT). The framework was developed iteratively from prior literature and refined through faculty perspectives. It conceptualises adoption across four interrelated dimensions: usability, pedagogical adequacy, institutional readiness, and faculty engagement. Using PyChatAI as an instrumental case study, this qualitative research draws on semi-structured interviews with 15 faculty members teaching programming courses at Jouf University, a public institution in Saudi Arabia operating in a low- to mid-resource context. Data were analysed using reflexive thematic analysis. Findings indicate that PyChatAI is intuitive and beneficial for novice learners, particularly through instant feedback and automated error correction. However, its pedagogical value is limited in advanced and industry-aligned contexts. Institutional barriers, such as inadequate infrastructure, limited technical support, and the absence of policy frameworks, significantly constrain effective integration. Despite this, faculty expressed strong commitment to adopting AI tools, proposing strategies including curriculum redesign, professional development, and gamified instruction. The study reconceptualises AI adoption as a pedagogical and institutional transformation rather than a purely technological shift. The AICAAF provides a robust foundation to guide curriculum design, teaching practice, and policy development for responsible AI integration in programming education.

IntroductionOnline assessments often fail to differentiate student performance because scores compress near the maximum, a ceiling effect that can make a genuine engagement-performance relationship statistically invisible, whether or not one exists. This study demonstrates that risk.MethodsAmong undergraduate female computer science students at King Khalid University (KKU), Saudi Arabia (N = 242), just over half achieved perfect assessment scores, and no significant relationship between behavioural engagement and performance emerged across correlation, regression, or classification analysis.ResultsCluster analysis, which does not depend on score variance in the same way, tells a different story: it reveals four distinct engagement-performance profiles, including a high-effort, low-performance group invisible to the correlational approach. A descriptive faculty survey (N = 20) points to a plausible cause: most assessments are custom-designed rather than drawn from difficulty-calibrated item banks and motivates a preliminary Adaptive Online Assessment Design Framework (AOADF) for future testing.DiscussionThe central contribution is not a claim about whether engagement predicts performance, but a demonstration that null results in ceiling-affected assessment data reflect an instrument limitation rather than an absent relationship, with direct implications for how learning-analytics findings should be interpreted across online assessment research.

This study investigates the adoption of PyChatAI, a bilingual AI-powered chatbot for Python programming education, among female computer science students at Jouf University. Guided by the Technology Acceptance Model 3 (TAM3), it examines the determinants of user acceptance and usage behaviour. A Solomon Four-Group experimental design (N = 300) was used to control pre-test effects and isolate the impact of the intervention. PyChatAI provides interactive problem-solving, code explanations, and topic-based tutorials in English and Arabic. Measurement and structural models were validated via Confirmatory Factor Analysis (CFA) and Structural Equation Modelling (SEM), achieving excellent fit (CFI = 0.980, RMSEA = 0.039). Results show that perceived usefulness (β = 0.446, p < 0.001) and perceived ease of use (β = 0.243, p = 0.005) significantly influence intention to use, which in turn predicts actual usage (β = 0.406, p < 0.001). Trust, facilitating conditions, and hedonic motivation emerged as strong antecedents of ease of use, while social influence and cognitive factors had limited impact. These findings demonstrate that AI-driven bilingual tools can effectively enhance programming engagement in gender-specific, culturally sensitive contexts, offering practical guidance for integrating intelligent tutoring systems into computer science curricula.

Health information systems are vital for healthcare modernization; however, their implementation across Saudi Arabia remains inconsistent due to technical, organizational, and governance challenges. Current evaluation methods lack lifecycle coverage and fail to align with international standards. This study proposes a lifecycle-based evaluation framework tailored to the Saudi context, integrating findable, accessible, interoperable, reusable principles along with Health Level Seven (HL7)/Fast Healthcare Interoperability Resources (FHIR) standards and the CApable Reuse of EHR Data (CARED) architecture across three phases: pre-implementation, implementation, and post-deployment. Developed using a design science research methodology, the framework addresses key gaps in planning, interoperability, usability, and the use of secondary data. A multi-phase evaluation strategy comprising Delphi consensus, literature benchmarking, scenario-based simulations, and pilot trials is recommended. The framework incorporates measurable indicators and scalable tools to support Saudi Vision 2030, enhance the effectiveness of the health information system, and guide policymakers and informatics leaders in developing sustainable, standards-aligned digital health infrastructure.

The increasing use of the Internet, along with the widespread access to social media, video games, and various online platforms, presents significant safety challenges, particularly for young people and teenagers. To address these concerns, this study develops and validates the Internet Security Awareness (ISAS) e-safety framework, designed to promote safe Internet usage among youth in Saudi Arabia. The framework was constructed based on a survey of 92 IT professionals and experts, ensuring its relevance and reliability. Data analysis was conducted using IBM SPSS for exploratory factor analysis (EFA) and IBM AMOS for confirmatory factor analysis (CFA). Of the 33 initial survey items, the study identified 5 items related to privacy, 4 items concerning security, 5 items addressing threats, and 3 items focusing on communication. The findings confirm that these four factors—privacy, security, threats, and communication—are strongly interrelated, demonstrating high validity and reliability. These factors were further examined to assess young people's behavioral intentions to adopt the ISAS e-safety framework in their online activities. This study offers valuable insights for IT professionals and educators while providing practical recommendations for managers aiming to enhance Internet safety awareness among young users.

This paper presents strategies for effectively integrating AI tools into programming education and provides recommendations for enhancing student learning outcomes through intelligent educational systems. Learning computer programming is a cognitively demanding task that requires dedication, logical reasoning, and persistence. Many beginners struggle with debugging and often lack effective problem-solving strategies. To address these issues, this study investigates PyChatAI—a bilingual, AI-powered chatbot designed to support novice Python programmers by providing real-time feedback, answering coding-related questions, and fostering independent problem-solving skills. PyChatAI offers continuous, personalised assistance and is particularly beneficial for students who prefer remote or low-pressure learning environments. An empirical evaluation employing a Solomon Four-Group design revealed significant improvements across all programming skill areas, with especially strong gains in theoretical understanding, code writing, and debugging proficiency.

The aim of this paper is to propose solutions to challenges faced by database systems for clinical research purposes. Current clinical databases are primarily based on data acquisition for healthcare intentions. However, these healthcare databases lack the data analysis capability for clinical researchers. In order for clinical researchers to use the healthcare databases in an effective manner, such as in their clinical trial studies, challenges of data integration, data storage, and data retrieval in the current healthcare database settings need to be overcome. Our proposed solutions include using: 1) NoSQL to efficiently integrate clinical databases with legacy healthcare databases, (2) entity attribute value model for data retrieval, and (3) warehouse for big data storage.

In general, databases provide a single comprehensive view suitable for analysis and relevant information for a variety of organizational purposes. The intent of this paper is to review the contemporary database design in terms of data modelling, process modelling, relational databases, and data storage. The review indicates the contemporary relational database architecture provides numerous advantages such as high consistency and availability. However, it is not suitable for big data because its performance decreases as the data grows and faces scalability constraints as it is impossible to scale horizontally, and its vertical growth is limited. An implication here is that big data requires more than a relational database and the traditional SQL.

There are few sources from which to obtain clinical and genetic data for use in research in Saudi Arabia. Numerous obstacles led to the difficulty of integrating these data from silos and scattered sources to provide standardized access to large data sets for patients with common health conditions. To this end, we sought to contribute to this area and offer a practical and easy-to-implement solution. In this paper, we aim to design and implement a "not only SQL" (NoSQL) based integration framework to generate an Integrated Data Repository of Genetic Disorders Data (GENE2D) to integrate data from various genetic clinics and research centers in Saudi Arabia and provide an easy-to-use query interface for researchers to conduct their studies on large datasets. The major components involved in the GENE2D architecture consists of the data sources, the integrated data repository (IDR) as a central database, and the application interface. The IDR uses a NoSQL document store via MongoDB (an open source document-oriented database program) as a backend database. The application interface called Query Builder provides multiple services for data retrieval from the database using a custom query to answer simple or complex research questions. The GENE2D system demonstrates its potential to help grow and develop a national genetic disorders database in Saudi Arabia.

Background: Although in recent times the Saudi government has paid much attention to the adaptation of hospital information systems (HIS) and electronic medical records (EMR), the importance of utilising HIS to enhance medical research has been neglected. Objective: We aimed to (i) investigate the current state of medical research in Saudi Arabia, (ii) identify possible issues that hinder improvement of medical research and (iii) identify possible solutions to enhance the role of HIS in medical research in Saudi Arabia. Method: We used a questionnaire and structured interview approach. Questionnaires were distributed to Saudi healthcare professionals. One hundred responses to our questionnaire were captured by the online Google Form designed specifically for our survey. Structured interviews with two IT professionals were conducted regarding technical aspects of their hospital data management systems. Results: Six themes contributing to the inefficacy of HIS in medical research in Saudi Arabia emerged from the data: incorrect datasets, difficult data collection and storage, poor data analytics, a lack of system interoperability across different HIS for universal access and negative perception of the usefulness of HIS for medical research. Conclusion and implications: Our findings suggest (i) cloud-based HIS would support efficient, reliable and integrated data collection and storage across all hospitals in Saudi Arabia; (ii) EMR data sources should be seamlessly linked to avoid incomplete, fragmented or erroneous EMR in Saudi Arabia; and (iii) collaboration between all hospitals in Saudi Arabia to adopt a uniform standard to support interoperability and improve data exchange and integration is necessary.

Current health information systems used in genetic research centers and clinics in the Kingdom of Saudi Arabia have failed to enable researchers and health care physicians to utilize genetic and clinical data in their research. In this paper, we aim to design and implement a Genetic Disorders Diagnosis Data Management System (G3DMS) to support clinicians in the process of diagnosing genetic diseases and conducting genetic studies. A case study was undertaken to analyze a health information system in Saudi to understand its design problems via a brainstorming method. We then used the Barker’s system design method and a prototype to validate our proposed system via usability testing. This research has resulted in the development of the G3DMS that comprises: electronic data-capture forms for data entry; a customized query builder to display and modify patient data as well as form research queries; a module that allows historical data to be uploaded in the form of bulk data using a template; export data options to Excel and JavaScript Object Notation (JSON) format; and authorization access for healthcare researchers and clinicians. The G3DMS was implemented in the Princess Al-Jawhara Center of Excellence in Research of Hereditary Disorders, Jeddah, KSA.

Cloud-based technologies play a significant role in the technology-enhanced learning domain. The adoption of cloud technologies in the educational environment has a positive impact on the learning process by offering new tools and services to improve and support the learning life cycle, including interactivity. In specific fields, such as clinical skills training, that involve computer-intensive training scenarios, there is an increased demand to deliver training services to a larger number of learners, therefore the need for cloud services. However, to date there has been a lack of a formalized framework relating to the use of cloud computing for on-demand interactive e-training resources. This paper is to formalize a theoretical framework for an interactive e-training system particularly for clinical skills training, taking into consideration e-training system requirements and with a focus on applying cloud technologies to ensure the dynamic scalability of services and computing power while maintaining QoS and security

Clinical skills education is an essential component of the teaching plan in medical science courses, such as nursing education. Simulation-based learning is an effective teaching method in any practical or vocational-based training. The development of simulation-based teaching has been impacted by the integration of emerging technologies, such as Intelligent Tutoring Systems (ITSs), which results in a more interactive and adaptive environment. Recently, educational data mining (EDM) has played an important role in the development of ITSs by providing different methods and techniques to predict a student's performance. Research carried out to deliver intelligent simulation-based systems for clinical skills teaching has applied several artificial intelligence techniques, however there is a lack of research that describes the use of the powerful methods and techniques available in EDM. This paper investigates and traces the technological developments of the most effective methods employed to promote learning in clinical skills education, particularly in nursing education, where skills acquisition is imperative for the provision of high quality care. To this end, we propose a conceptual model for an intelligent simulation-based learning system using a data mining agent in clinical skills education.