Search Results (27)

This study explores the application of artificial intelligence (AI) in higher education to enable the early identification of at-risk students using only engagement data from learning management systems (LMS). Unlike many existing early-warning models that are limited to single disciplines or rely on sensitive demographic and prior academic records, the proposed approach offers a privacy-conscious and highly generalizable predictive framework suitable for diverse higher education contexts. The dataset includes over 1.7 million LMS interaction records from 236 undergraduate subjects spanning four academic divisions. These subjects encompass a wide variety of instructional designs and assessment structures. To address cross-subject heterogeneity, this study employs rank-based engagement features that represent students’ relative behavioral patterns within each course, facilitating meaningful comparison across disciplines without reliance on absolute activity levels. Using standard machine learning classifiers, the model achieves over 90% prediction accuracy for final subject performance by Week 3 of the semester, demonstrating that reliable early detection of at-risk students is feasible at an early stage of teaching and learning. Rather than claiming intervention effectiveness, the study positions AI-enabled early prediction as a scalable foundation for proactive student support and enhanced teaching responsiveness, with the potential to inform timely pedagogical actions such as targeted outreach and academic advising. By emphasizing generalizability, ethical data use, and privacy protection in AI-enabled learning analytics, this research contributes practical insights into how predictive AI can responsibly support teaching and learning in higher education. Full article

Background/Objectives: Depression is a mood disorder characterized by persistent sadness and loss of interest. Pharmacy students exhibit a relatively high prevalence of depressive symptoms, which may negatively impact quality of life, academic performance, and, in severe cases, lead to suicidal ideation. Given the increasing trend of medication use among young adults, we hypothesized that this behavior may be associated with depressive symptoms, potentially reflecting attempts to manage concurrent physical symptoms or reduced psychological well-being. Therefore, the objective of this study was to assess the association between depressive symptoms and medication use among pharmacy students. Methods: A cross-sectional study was conducted among students enrolled in pharmacy-related programs from University Center for Exact Sciences and Engineering (CUCEI), University of Guadalajara. Participants completed a personalized questionnaire assessing sociodemographic variables, medication use, comorbid conditions, and depressive symptoms using the Patient Health Questionnaire-9. Descriptive statistics were used to summarize participant characteristics. Categorical variables were reported as frequencies and percentages and compared using the chi-square test. Continuous variables were summarized as means and standard deviations and compared using Student t-test. To evaluate factors associated with moderate-to-severe depressive symptoms, logistic regression and multivariable linear regression analyses were performed. Results: A total of 365 students completed our personalized questionnaire; nearly half of the sample (47.3%) presented moderate-to-severe depressive symptoms. Multivariable analyses showed that insufficient sleep, academic stress, psychological support, and the number of medications used simultaneously were significantly associated with depressive symptoms. Logistic regression identified being in a relationship and receiving psychological support for at least one year as protective factors, while employment, insufficient sleep, academic stress, and a greater number of concomitant medications were associated with increased odds of moderate-to-severe depressive symptoms. Conclusions: A modest association was observed between self-reported medication use and moderate-to-severe depressive symptoms among pharmacy students. These findings suggest that medication use patterns may warrant further investigation as a potential marker of depressive symptoms in pharmacy students. Future longitudinal studies are needed to clarify the nature and direction of this association and to determine whether medication use could contribute to the identification of students at increased risk of depression. Full article

Early identification of behavioral risk patterns in large student populations remains a challenge in higher education, particularly when support systems depend on voluntary help-seeking. This study presents YuumCare, a structured and scalable framework that operationalizes population-level digital screening through a reproducible data pipeline for early detection and decision support. The framework was implemented during the first weeks of the academic term in a public higher education institution in Latin America, where 466 first-year students (38.9% coverage) completed a structured questionnaire capturing indicators of emotional well-being, academic pressure, and help-seeking attitudes. Responses were processed through a structured data pipeline comprising data ingestion, preparation, feature construction, and rule-based classification, transforming distributed self-reported data into standardized features and interpretable institutional signals for consistent analysis at scale. Results show that emotional strain, evaluation-related anxiety, and adaptation difficulties emerge early and frequently co-occur, while most students report low willingness to seek professional support. The classification process indicates that approximately one third of the cohort presents moderate to critical levels of need, providing a structured representation of vulnerability. The proposed approach connects digital screening with institutional decision-making through an interpretable and operational workflow that does not rely on complex infrastructure. Beyond descriptive findings, the study contributes a lightweight and reproducible data framework that supports scalable monitoring and coordinated response under real-world constraints, demonstrating the feasibility of transforming self-reported behavioral data into actionable decision-support signals for population-level monitoring in higher education. Full article

Traditional talent identification systems often rely on static assessments and overlook the dynamic nature of long-term development. To address this limitation, this study proposes a biomimetic predictive framework inspired by crayfish behavioral ecology. The Crayfish Optimization Algorithm (COA), derived from adaptive foraging and competition mechanisms observed in crayfish, is enhanced through a Thinking Innovation Strategy (TIS) to form TISCOA for hyperparameter optimization of a Gradient Boosting Decision Tree model. Using a five-year longitudinal dataset of 160 elite mathematical students, the framework models Professional Achievement in Mathematics (PAM) from multidimensional baseline indicators. Comparative experiments with multiple metaheuristic optimizers show that the proposed approach achieves stable generalization performance within the examined cohort. Feature attribution analysis indicates that non-cognitive factors, particularly Emotion Regulation, contribute substantially to long-term outcomes, while temporal variables such as the Latency Period further shape developmental trajectories. Residual analysis highlights heterogeneous patterns that may reflect unobserved contextual influences. Overall, the study demonstrates how a biologically inspired optimization mechanism can support interpretable and stability-oriented longitudinal prediction in small-sample educational settings. Full article

Sustainable and equitable STEM education requires assessment mechanisms that support timely instructional decisions while remaining feasible in resource-constrained classroom environments. Traditional assessments typically report only class-level statistics, limiting teachers’ ability to diagnose individual learning difficulties. This study proposes a classroom-oriented AI-assisted diagnostic framework that integrates generative adversarial networks (GANs) and convolutional neural networks (CNNs) to support learning pattern identification under conditions of severe data scarcity. Student response-behavior data collected through an online testing platform were used to categorize learners into predefined learning behavior types. The GAN was employed to generate locally perturbed samples for stability-oriented data expansion at multiple scales, while the CNN served as a pattern consistency learner operating on the expanded dataset. Rather than aiming for population-level generalization, the framework examines the stability and consistency of learning behavior classification within a single classroom context. Classification results across different expansion scales showed stable performance, with CNN accuracies exceeding 72%. Based on diagnostic outputs, teachers implemented targeted remedial instruction. Case study results show that four out of five remedial interventions exhibited observable improvement. These findings indicate that the proposed framework functions as a proof-of-concept decision-support tool for formative diagnosis and targeted instruction, supporting more equitable learning opportunities, improving instructional efficiency, and contributing to sustainable STEM education aligned with SDG 4. Full article

Background: Teamwork promotes the quality and safety of care. The TeamSTEPPS^® program enhances communication and teamwork among healthcare professionals and students, as well as the associated benefits. Currently, there are no studies that comprehensively explore the benefits achieved through the implementation of TeamSTEPPS^® across different contexts (educational and clinical practice). Objective: This scoping review aimed to map the existing evidence on the benefits of implementing TeamSTEPPS^® in educational and professional settings, emphasizing its contribution to sustainable teamwork, patient safety, and organizational learning. Methods: A scoping review was conducted following the Joanna Briggs Institute methodology and reported according to the PRISMA-ScR guidelines. Searches were performed in CINAHL Ultimate, Medline Ultimate, Scopus, the Portuguese Open Access Scientific Repository, Web of Science and Psychology and Behavioral Sciences Collection, with no time restrictions. Studies were selected based on the PCC framework, focusing on healthcare students and professionals (Population), TeamSTEPPS^® implementation (Concept), and academic or clinical settings (Context). A descriptive and thematic analysis was used, enabling the identification of emerging categories and recurring patterns among the included studies. Results: Twenty-eight articles published between 2009 and 2025, predominantly from the United States of America and conducted in hospital settings, were found. The included studies comprised quantitative (n = 11), qualitative (n = 4) and quasi-experimental study (n = 13) designs. From the analysis, four thematic categories emerged: academic education, interprofessional education and simulation; professional transition and professional development; clinical implementation of the TeamSTEPPS^® program in real-world settings; and patient safety culture as a central focus. Conclusions: The available evidence suggests that the TeamSTEPPS^® program may strengthen teamwork and promote safe and high-quality care in both educational and clinical settings. While short-term training leads to immediate improvements in team dynamics, continuous training demonstrates greater long-term effectiveness. The consolidation of the TeamSTEPPS^® methodology relies on organizational commitment, leadership engagement, and the integration of interprofessional training from the academic level onward. Full article

Sustainability has become a central pillar of public policy and higher education, with university students playing a key role both as recipients of knowledge and as agents of change toward more responsible practices. Existing literature shows that students’ attitudes, beliefs, and behaviors related to sustainability are shaped by multiple explanatory factors; however, prior research has often addressed these factors in isolation, resulting in a fragmented understanding of how sustainability is constructed within the university context. Students’ engagement with sustainability emerges from the interaction of several interconnected dimensions, including conceptual clarity, everyday lifestyle practices, academic experiences, institutional environments, and sustainability-related training. This study provides a descriptive and exploratory empirical overview of the dimensions that shape university students’ understanding of sustainability, enabling the identification of patterns, trends, and key influences on attitudes, intentions, and sustainable behaviors. Data were collected from a sample of university students in Spain using a structured questionnaire designed to capture perceptions, behaviors, and experiences related to sustainability. The data were analyzed using quantitative descriptive techniques. The findings reveal distinct sustainability dimensions and highlight the interplay between conceptual understanding, educational experiences, institutional initiatives, and lifestyle practices in shaping students’ engagement with sustainability. By offering a comprehensive, non-manipulative empirical perspective, the study lays the groundwork for the development of more effective educational and university management strategies aimed at strengthening student commitment to the Sustainable Development Goals. Beyond its descriptive contribution, the study proposes an integrated conceptual model of sustainable education that brings together conceptual, attitudinal, educational, and institutional dimensions from the students’ perspective. This holistic framework provides actionable guidance for universities seeking to adapt curricula, pedagogical approaches, and institutional initiatives to foster more coherent, inclusive, and effective sustainability education. Full article

Student dropout prediction remains critical in higher education, where timely identification enables effective interventions. Learning Management Systems (LMSs) capture rich temporal data reflecting student behavioral evolution, yet existing approaches underutilize this sequential information. Traditional machine learning methods aggregate behavioral data into static features, discarding dynamic patterns that distinguish successful from at-risk students. While Long Short-Term Memory (LSTM) networks model sequences, they assume discrete time steps and struggle with irregular LMS observation intervals. To address these limitations, we introduce Completion-aware Risk Neural Ordinary Differential Equations (CR-NODE), integrating continuous-time dynamics with completion-focused features for early dropout prediction. CR-NODE employs Neural ODEs to model student behavioral evolution through continuous differential equations, naturally accommodating irregular observation patterns. Additionally, we engineer three completion-focused features: completion rate, early warning score, and engagement variability, derived from root cause analysis. Evaluated on Canvas LMS data from 100,878 enrollments across 89,734 temporal sequences, CR-NODE achieves Macro F1 of 0.8747, significantly outperforming LSTM (0.8123), Extreme Gradient Boosting (XGBoost) (0.8300), and basic Neural ODE (0.8682). McNemar’s test confirms statistical significance ($p<0.0001$). Cross-dataset validation on the Open University Learning Analytics Dataset (OULAD) demonstrates generalizability, achieving 84.44% accuracy versus state-of-the-art LSTM (83.41%). To support transparent decision-making, SHapley Additive exPlanations (SHAP) analysis reveals completion patterns as the primary prediction drivers. Full article

Background/Objectives: Leadership in physical education plays a critical role in the holistic development of students, influencing variables such as satisfaction, group cohesion, and performance. Despite the abundance of cross-sectional studies, there is a paucity of longitudinal evidence exploring the temporal stability of these perceptions in adolescent populations, which limits the current understanding of leadership development in educational settings. This longitudinal study investigates how secondary and high school students perceive and prefer different leadership styles in PE and how these relate to gender, academic level, and sport participation, grounded in the multidimensional leadership model. The analysis is further contextualized by recent research emphasizing adaptive, evidence-based pedagogical approaches in physical education, the influence of competitive environments on leadership expectations, and the role of emotional support in training contexts. Methods: Using validated questionnaires (LSS-1 and LSS-2), five dimensions were assessed: Training and Instruction, democratic behavior, autocratic behavior, Social Support, and positive feedback, considering variables such as gender, academic level, and extracurricular sport participation. Data were collected at two time points over a 12-month interval, enabling the identification of temporal patterns in students’ perceptions and preferences. Sampling procedures were clearly defined to enhance transparency and potential replicability, and the choice of a convenience sample from two private schools was justified by accessibility and continuity in longitudinal tracking. Although no a priori power analysis was conducted, the sample size (n = 370) was deemed adequate for the non-parametric analyses employed, with an estimated statistical power ≥ 0.80 for medium effect sizes (Cohen’s d = 0.3–0.5). Results: The results revealed a marked preference for leadership styles emphasizing social support and positive feedback, particularly among students engaged in sports. Statistically significant differences (p < 0.05) were identified based on gender and academic maturity, with female students favoring democratic behavior and students in the fourth year of compulsory secondary education showing a stronger inclination toward styles prioritizing emotional support. Trends toward statistical significance (p < 0.10) were also reported, following precedents in the sport psychology and sport sciences literature, as they provide potentially relevant indications for future research directions. The congruence between perceived and preferred leadership emerged as a key factor in student satisfaction, confirming that adaptive leadership enhances students’ learning experiences and overall well-being. However, this satisfaction was inferred from congruence measures, rather than directly assessed, representing a key methodological limitation. Conclusions: This study underscores the importance of physical education teachers tailoring their leadership styles to the individual and group characteristics of their students. The findings align with methodological approaches used in preference hierarchy analyses in sport contexts and support calls for individualized pedagogical strategies observed in sports medicine and training research. By providing longitudinal evidence on leadership perception stability and integrating recent cross-disciplinary findings, the study makes an original contribution to bridging the gap between educational theory and practice. The results address a gap in the literature concerning the temporal stability of leadership perceptions among adolescents, offering a theoretically grounded basis for future research and the design of pedagogical innovations in PE. Full article

Student behavior analysis plays a critical role in enhancing educational quality and enabling personalized learning. While previous studies have utilized machine learning models to analyze campus card consumption data, few have integrated multi-source behavioral data with large language models (LLMs) to provide deeper insights. This study proposes an intelligent educational system that examines the relationship between student consumption behavior and academic performance. The system is built upon a dataset collected from students of three majors at Xinjiang Normal University, containing exam scores and campus card transaction records. We designed an artificial intelligence (AI) agent that incorporates LLMs, SageGNN-based graph embeddings, and time-series regularity analysis to generate individualized behavior reports. Experimental evaluations demonstrate that the system effectively captures both temporal consumption patterns and academic fluctuations, offering interpretable and accurate outputs. Compared to baseline LLMs, our model achieves lower perplexity while maintaining high report consistency. The system supports early identification of potential learning risks and enables data-driven decision-making for educational interventions. Furthermore, the constructed multi-source dataset serves as a valuable resource for advancing research in educational data mining, behavioral analytics, and intelligent tutoring systems. Full article

Society’s adaptation to shared mobility services is a growing topic that requires detailed understanding of the local circumstances of potential and current users. This paper focuses on analyzing barriers to the adoption of urban bike-sharing systems in post-industrial cities, using a case study of the Silesian agglomeration in Poland. Methodologically, the article integrates quantitative survey methods with multivariate statistical analysis to analyze the demographic, socioeconomic, and motivational factors that underline the adoption of shared micromobility. The study highlights a detailed segmentation of users by income, age, professional status, and gender, as well as the observation of profound disparities in access and perceived usefulness. Of note is the study’s identification of a highly concentrated segment of young, low-income users (mostly students), which largely accounts for the general perception of economic and infrastructural barriers. These include the use of factor analysis and regression to plot the interaction patterns between individual user characteristics and certain system-level constraints, such as cost, infrastructure coverage, weather, and health. The study’s findings prioritize problem-specific interventions in urban mobility planning: bridging equity gaps between user groups. This research contributes to the current literature by providing detailed insights into the heterogeneity of user mobility behavior, offering evidence-based recommendations for inclusive and adaptive options for shared transportation infrastructure in a changing urban context. Full article

The COVID-19 pandemic, which posed a global threat, led many countries, including Turkey, to implement changes in their educational practices. In response to the “stay at home” directive aimed at preventing the spread of the virus, face-to-face education was suspended, and online education was adopted. As a result, children were unable to attend school for nearly two years. This sudden shift posed significant challenges for children, who were in the process of socialization and learning, as adapting to this new educational norm was not in alignment with their natural developmental needs. This study examines how staying at home affected the behaviors of children who were supposed to attend school, interact with their teachers and peers, socialize, and engage in learning. The research follows a qualitative phenomenological design, with the study group selected through criterion sampling. The collected data were analyzed using content analysis, leading to the identification of themes, categories, and codes. Particular attention was paid to participant and data saturation during the analysis process. The findings indicate that noticeable behavioral patterns were categorized under discipline, cognitive skills, social skills, motor skills, emotional skills, digital addiction, and personality traits across different educational levels. It is suggested that the type and frequency of these prominent behaviors observed in students may be associated with the shift to online education following the suspension of face-to-face learning due to COVID-19. Factors such as reduced peer interaction, diminished social engagement, and a lack of communication and interaction are considered to have played a role in these behavioral changes. Full article

Background: Eating behavior is influenced by intrinsic and extrinsic factors from early infancy, shaping an individual’s relationship with food. Tools such as the Children’s Eating Behaviour Questionnaire (CEBQ) were designed to evaluate these patterns in children and facilitate the early identification of potential issues. Objective: The objective of this study is to validate the CEBQ for use in Brazilian children and adolescents. Methods: Parents/caregivers of students from public and private schools in southern Brazil completed the CEBQ. Anthropometric measurements of students’ weight and height were also taken. Psychometric properties were assessed by internal consistency (Cronbach’s alpha), construct validity (exploratory factor analysis), and criterion validity (correlation between CEBQ scores and participants’ body mass index-for-age categories). Results: A total of 205 participants aged 3 to 13 and their caregivers participated in this study. Exploratory factor analysis resulted in a five-factor questionnaire and a reduction of four items. All remaining items had a factor loading > 0.3. Cronbach’s alpha values were satisfactory, with values ≥ 0.7 in all factors, supporting the instrument’s internal consistency. The findings also showed significant associations between CEBQ scales and participants’ BMI for age. Conclusions: The findings of this study provide evidence that the CEBQ is a valid tool for assessing eating behavior in Brazilian children and adolescents. Full article

Suicidal ideation is a process that is intertwined with suicidal behavior. It begins with the formation of an idea about whether it is worth continuing to live, an idea that can evolve and trigger a series of actions ranging from planning to the execution of the suicidal act. This is a descriptive observational study based on numerical measurements with its respective statistical analysis that established the behavioral patterns of the phenomenon studied. The research proposal was approved by the research committee of the Faculty of Medicine and Surgery, URSE; data collection was performed through the instruments: Beck Suicidal Ideation Scale, Beck Depression Inventory, Abbreviated Scale of School Bullying Questionnaire, Drug Dependence Identification Questionnaire, and Family Apgar. The prevalence of suicidal ideation was 5.4%; 19.7% of the medical students have been victims of bullying in any form; 22.2% reported regular use of alcohol, tobacco, drugs, and other addictive substances; in addition, 17.7% had mild family dysfunction, moderate in 9.9% and severe with 15.3%; depression was recorded to a mild degree with 6.4%, followed by moderate in 1.5% of cases. Suicidal ideation among medical students is of concern; these problems must be addressed comprehensively, promoting a supportive environment that promotes the mental health and well-being of medical students. Full article

This study aimed to evaluate the awareness, comprehension, and practices concerning forensic odontology among dental students and faculty at a Dental School in Cyprus. An online, cross-sectional, descriptive survey, employing an adapted, self-administered questionnaire, was disseminated to all dental students and faculty at the School of Dentistry, European University Cyprus, in November 2022. The survey assessed participants’ demographic information and explored their awareness with questions alluding to knowledge, attitudes and practices in forensic dentistry. Of those surveyed, 47 faculty members and 304 students responded, yielding response rates of 66.2% and 80%, respectively. Statistical analysis, including Kendall’s tau test and χ² test were employed to examine correlations and associations, with Cramer’s V used to measure the strength of significant associations. The predetermined significance level was α = 0.05. Awareness levels were assessed through participants’ responses to specific questions in the survey. It was revealed that 87% of faculty and 65% of students were familiar with forensic odontology. A noteworthy 94% of faculty and 85% of students recognized teeth as DNA repositories. A high percentage, 98% of faculty and 89% of students, acknowledged the role of forensic odontology in the identification of criminals and deceased individuals. Awareness of age estimation through dental eruption patterns was evident in 85% of faculty and 81.6% of students. A substantial proportion (80% of faculty) maintained dental records, while 78% of students recognized the importance of dental record-keeping in ensuring quality care. Interestingly, 57% of students and 64% of faculty were aware of the possibility of dentists testifying as expert witnesses. The majority, 95.7% of faculty and 85% of students, concurred that physical harm, scars, and behavioral alterations predominantly indicate child abuse. The findings, revealing robust awareness among respondents, underscore the importance of enhancing faculty engagement in relevant seminars to further strengthen their knowledge. Additionally, emphasizing improved record-keeping practices for potential forensic applications emerges as a crucial aspect. These insights have implications for refining dental education in Cyprus and enhancing forensic practices by promoting ongoing professional development and emphasizing meticulous record-keeping within the dental community. Full article