Search Results (342)

Empathetic dialogue systems built upon large language models overwhelmingly adopt a monolithic inference paradigm that processes emotion perception, causal reasoning, memory retrieval, and response planning within a single forward pass without architecturally enforced intermediate representations, forfeiting intermediate-state transparency and long-horizon personalization. Drawing on neuroscientific and cognitive–psychological evidence that human empathy is functionally dissociable, we present MOSAIC (Multi-agent Orchestration with Structured Affective memory for Interpretable empathiC dialogue), a training-free framework that operationalizes empathetic dialogue as a four-stage cognitive pipeline: affective perception, causal appraisal, episodic memory retrieval, and response synthesis. Three innovations distinguish MOSAIC from prior work: (1) a cognitively motivated modular architecture whose functionally dissociable stages enable post hoc failure attribution through logged intermediate states; (2) a hierarchical three-tier emotional memory—perceptual, semantic, and episodic—coupled with adaptive three-dimensional retrieval over emotion, situation, and coping-strategy cues; and (3) a heterogeneous model orchestration strategy coordinating open-source and API-accessible models through role-specific chain-of-thought prompts, requiring no task-specific fine-tuning. We note that the EmpatheticDialogues evaluation pre-populates the memory store with 200 training-split episodes prior to test-set interaction, a data-access asymmetry relative to single-model baselines that must be borne in mind when interpreting comparative results. Experiments on EmpatheticDialogues and ESConv show that MOSAIC achieves a 76.4% weighted F1 and an empathy score of 3.87 (on a 1–5 Likert scale) and that it improves over single-model, training-free baselines on aggregate empathy and—most prominently—on human-rated personalization (3.67 vs. 3.24 against Claude-3.5 five-shot, $d=0.48$). We caution that the comparison against training-free baselines is not data access-controlled (see the cold-start discussion in Methods); the personalization advantage, supported by the ablation without the Event Agent, is the result we treat as the primary practical contribution of this work. Full article

Background/Objectives: Posterior cortical atrophy, also referred to as Benson’s syndrome, is a presentation of Alzheimer’s disease that occurs in 5–15% of Alzheimer’s patients. Visual processing is the predominantly affected modality in posterior cortical atrophy, and symptoms such as prosopagnosia, simultanagnosia, alexia, optic ataxia, and visual hallucinations may occur, as well as blurred vision and visual distortions. Posterior cortical atrophy is considered to be a disease without a known cause or effective treatment. Methods: Here, we report a patient with posterior cortical atrophy who responded to a personalized, precision medicine protocol. Results: The patient had improved MRI volumetrics, symptoms, and cognitive testing. She regained the ability to read, use a computer, and undertake computer-based brain training, among other cognitive improvements. She has now sustained this improvement for over one year and continues to regain her independence and confidence. Conclusions: These results argue for additional laboratory testing in the evaluation of patients with posterior cortical atrophy, and they support the possibility of utilizing a similar approach in a proof-of-concept trial. Full article

Background/Objectives: The use of personal smartphones by healthcare professionals in clinical settings has become a growing area of concern as practice may not consistently align with policy guidance. This study enhances our understanding of how and why medical residents are using smartphones to communicate patient healthcare information with other physicians in daily practice and provides insights into the role that institutional governance, policies, and structures play in the use of smartphones. Methods: This study used qualitative techniques to examine medical residents’ use of smartphones to communicate healthcare-related information with colleagues. Additionally, a neo-institutional theory lens was applied to assess the role that regulative (guidelines/policies), normative (what peers/staff are doing), and cultural-cognitive (beliefs/perceptions) factors play in smartphone use by medical residents. Results: The results suggest that behaviour related to smartphone use is based primarily on normative and cultural-cognitive factors rather than regulative factors. Regulative elements around smartphone use play a smaller role in shaping behaviour, particularly when they: (1) lack clarity; (2) are not seen as credible/legitimate; or (3) are viewed as cumbersome and do not align with workflow needs. Conclusions: The implementation of future guidelines/policies should consider the use of mentorships throughout postgraduate medical training whereby staff physicians educate, model, and promote behaviour in accordance with the associated policies/guidelines. Full article

Complex psychosis (CP) remains one of the most challenging conditions in mental health, characterized by persistent symptoms, cognitive impairment, functional disability, and reduced autonomy. Traditional rehabilitation approaches, although essential, are often insufficient to address the multidimensional needs of these individuals. Over the past decade, rapid advances in digital health have opened new opportunities to enhance psychosocial rehabilitation, improve engagement, and personalize treatment pathways. This narrative review synthesizes current evidence on the use of digital and immersive technologies in the rehabilitation of people with CP, including virtual reality (VR), augmented reality (AR), telerehabilitation platforms, mobile health (m-Health) applications, digital phenotyping, and AI-assisted cognitive remediation. We examine clinical trials, feasibility studies, and real-world implementations published between 2015 and 2025, highlighting the efficacy of VR-based social cognition training, remote cognitive remediation, ecological momentary interventions, and hybrid digital–in-person rehabilitation models. Mechanisms of action, transfer to real-world functioning, and predictors of engagement are described. Barriers such as digital literacy, access disparities, privacy concerns, and clinical integration are critically discussed. We also outline future directions, including adaptive algorithms, biosensor integration, and the development of multimodal digital ecosystems tailored to individual recovery trajectories. By integrating technological innovation with recovery-oriented care, digital rehabilitation tools have the potential to transform the treatment landscape for people with CP. This review offers a roadmap for clinicians, researchers, and policymakers seeking to incorporate evidence-based digital solutions into modern psychiatric rehabilitation. Full article

Background: Hospital-acquired infections (HAIs) pose significant safety risks, making nursing students’ behavioural intention during clinical rotations vital for prevention. Objective: To analyze the influence of Perceived Behavioural Control (PBC) and knowledge on students’ intention to maintain a safe clinical environment. Methods: A cross-sectional design was conducted with 242 nursing students at a Type A referral hospital in Pekanbaru, Indonesia. Participants were selected via simple random sampling. Data were collected using validated questionnaires measuring PBC (six indicators), knowledge (three subscales), and behavioural intention. Statistical analysis involved Chi-square tests for unadjusted Odds Ratios (OR) and binary logistic regression to calculate adjusted Odds Ratios (AOR) by entering all variables into the model simultaneously. Results: The majority of participants demonstrated high intention (66.5%) and high PBC (83.9%). In the univariate analysis, all six PBC indicators and general nosocomial knowledge were significantly associated with high intention (p < 0.05), with staff direction (OR = 5.96) and specific training (OR = 4.94) showing the strongest independent effects. However, when all environmental and cognitive variables were entered into the regression model simultaneously, only knowledge of personal protective equipment (PPE) use remained a significant independent factor (AOR = 2.66; 95% CI: 1.40–5.06, p = 0.003). The unadjusted OR emphasized the isolated influence of each factor, whereas the adjusted OR showed that technical knowledge was the only variable to retain significance after controlling for other factors. Conclusions: Technical knowledge regarding PPE use is the primary independent driver of nursing students’ intention to maintain a safe clinical environment. While environmental support and general knowledge are important foundational elements, clinical education should prioritize practical, technical training in protective measures to translate knowledge into behavioural intention effectively. Full article

Neurological injuries and disorders affecting hand motor control can severely impair the ability to perform activities of daily living and substantially reduce quality of life. Technologies such as virtual reality (VR) are increasingly used to address fundamental challenges in therapy, including motivation and engagement; further, programmable features of digital interfaces offer additional opportunities to personalize and optimize motor training. In this proof-of-concept study, we developed and evaluated a novel VR-based training framework to support improved dexterity and hand function using physiological (sensory-driven) and cognitive (memory) cues designed to promote greater task-relevant neural engagement. The proposed approach leverages the integration of augmented sensory feedback (ASF) with memory-anchored cues for motor learning of target hand gestures. Using a within-subjects design, thirteen neurotypical adults completed four training conditions: (1) control (baseline gesture-matching in VR), (2) visual ASF (enhanced visualization and feedback of gesture accuracy), (3) memory-anchored cues (associating gestures with semantically meaningful entities, loosely analogous to American Sign Language), and (4) hybrid multimodal (visual ASF + memory-anchored cues). Training with the hybrid condition produced the fastest skill acquisition (9.3 trials to reach an 80% accuracy threshold) and the steepest initial learning slope (1.86 ± 0.12%/trial), with all conditions differing significantly in initial slope (all p < 0.002). Post-training assessment showed that the hybrid condition achieved the highest gesture accuracy (95.2%), greatest normalized post-training accuracy gain (14.3% above baseline), fastest execution time to target gesture (1.14 s), and lowest variability in gestural kinematics (SD = 3.9%). Both ASF and memory-anchored cue conditions each also independently outperformed the control condition on gesture accuracy (both p ≤ 0.002), with omnibus ANOVAs indicating significant condition effects across metrics. Together, these findings suggest that pairing ASF cues with memory-based cognitive scaffolding can yield additive benefits for motor skill acquisition and stability. Pending validation in clinical populations, such approaches may inform the design of VR-based motor training frameworks for rehabilitation. Full article

Traditional cognitive diagnosis models typically rely on expert-annotated Q-matrices to define the relationship between exercises and knowledge concepts. This process is not only highly subjective and costly, but also prone to introducing noise and bias, which directly affects diagnostic accuracy. Meanwhile, most existing deep learning-based methods overlook the rich semantic information contained in concept descriptions, making it difficult to deeply model the intrinsic relationships among knowledge points, resulting in limited interpretability of the models. To address these issues, this paper proposes a cognitive diagnosis model that incorporates key textual information from concept descriptions to refine the Q-matrix (KECQCD). The core innovation of the model lies in leveraging the pre-trained language model RoBERTa to encode concept texts, fusing semantic features with identifier embeddings through a gating mechanism to construct semantically-enhanced concept representations. It designs a concept-exercise heterogeneous information network and employs a graph attention mechanism to adaptively aggregate node features, explicitly modeling high-order knowledge dependencies. Furthermore, a multi-task joint learning framework is established to predict student performance while dynamically correcting association errors in the initial Q-matrix. Experimental results on the public Junyi dataset show that the KECQCD model significantly outperforms mainstream baseline models across multiple metrics, including accuracy (ACC), area under the curve (AUC), and root mean square error (RMSE). Ablation studies confirm the effectiveness of each core module, and diagnostic consistency (DOA) evaluation further demonstrates the enhanced interpretability of the model’s outcomes. This research offers a new solution for building accurate, reliable, and interpretable cognitive diagnosis systems, contributing positively to the advancement of personalized intelligent education. Full article

In recent years, there has been increasing interest in personalizing cognitive training to enhance the likelihood of positive training effects at the individual level. Machine learning methods have proven suitable for this purpose due to their ability to generate predictions at the individual level. The aim of the study was to develop supervised machine learning models to predict near and far transfer of three cognitive training interventions (memory training, reasoning training and speed-of-processing training) based on baseline characteristics of elderly individuals including sociodemographic data, measures of cognitive and everyday functioning and depressive symptoms. In addition, near-transfer models were further utilized to predict individual responsiveness to all three types of cognitive training. Publicly available data from the ACTIVE study were used, which examined the effects of memory training, reasoning training and speed-of-processing training in healthy adults. Multiple supervised machine learning classification algorithms were applied to establish optimal predictive models for each type of cognitive training and transfer measure. Selected models for predicting near transfer were then used to estimate individual responsiveness to all three interventions. The results show selected models for all three types of cognitive training and both near- and far-transfer outcomes demonstrated better discriminative ability than chance based on all included features (AUC range 0.56–0.74), although models predicting far transfer demonstrated limited performance. Predicted responsiveness to cognitive training varied according to participant characteristics. Differences between model-predicted responders indicate that initially advantaged participants would have greater likelihood of benefiting from a broader range of interventions compared to initially disadvantaged ones, which would support magnification effects. The developed models need external validation, but have practical potential for selecting effective interventions tailored to individual characteristics, which could improve the future implementation of cognitive training programs. Full article

Background: Home-based digital healthcare interventions are increasingly used to support people living with dementia (PLWD) and their family caregivers. However, evidence regarding their effectiveness across patient and caregiver outcomes remains heterogeneous. Methods: This systematic review followed PRISMA 2020 guidelines and was prospectively registered in PROSPERO (CRD420261302166). Six databases (PubMed, Embase, CINAHL, PsycINFO, Web of Science, and Scopus) were searched from January 2000 to October 2025. Randomized and quasi-experimental quantitative studies evaluating home-based or remotely delivered digital interventions for PLWD and/or informal caregivers were included. Risk of bias was assessed using RoB 2 and ROBINS-I. Due to heterogeneity, findings were synthesized narratively. Results: Fourteen studies met the inclusion criteria. Interventions included web-based psychoeducation, telecoaching, digital cognitive training, assistive technologies, and multicomponent programs. Caregiver outcomes demonstrated the most consistent benefits, including reduced burden and stress, improved self-efficacy, and improved sleep efficiency in technology-supported trials. For PLWD, small-to-moderate improvements were observed in global cognition and selected neuropsychiatric symptoms, particularly in interactive and personalized programs. Multicomponent interventions combining caregiver education with patient activation and professional feedback showed more durable effects. Conclusions: Home-based digital interventions appear feasible and beneficial, particularly for caregiver outcomes. Future large-scale trials with longer follow-up and standardized outcome measures are needed to confirm durability, equity, and cost-effectiveness. Full article

Digital technologies are widely recognized for their potential to support active learning and foster higher-order cognitive skills, including critical thinking. However, limited research has examined the extent to which students are directly involved in selecting digital tools that shape their learning. This study investigates teachers’ ability to engage students in the selection and pedagogical use of digital technologies, with attention to practices supporting active, personalized learning and critical thinking. Data were collected from 156 educators across diverse disciplines in five teacher-training colleges in Israel using an online questionnaire assessing levels of digital tool use, from non-use to active student involvement. Item Response Theory (IRT) was applied to model teachers’ proficiency and examine differences across tools and background characteristics. Results indicate substantial variability in teachers’ ability to involve students, with particularly low involvement in tools related to problem-solving, differentiation, and personalized learning. Gender and institutional role were significant predictors, with female educators and those holding additional roles demonstrating higher proficiency. These findings highlight the importance of teachers’ techno-pedagogical competence in enabling student participation in digital decision-making and suggest that involving students in tool selection can support the development of critical thinking and learner agency in digitally mediated learning environments. Full article

The rapid development of artificial intelligence (AI) has intensified debates regarding its impact on the labor market, specifically concerning the potential for replacement versus the augmentation of human labor. While the existing literature highlights both the opportunities and risks associated with AI, research conducted by faculty in academic settings focuses predominantly on academic integrity, paying limited attention to AI readiness and/or anxiety related to labor market entry. This study aims to compare the perceptions of students and faculty in Romania regarding the impact of AI on employment, exploring the role of personal and organizational readiness in shaping these attitudes. The research is based on an empirical approach utilizing a questionnaire applied to a sample of 271 respondents, consisting of 197 students and 74 faculty members. Data analysis included descriptive and inferential methods, such as Chi-square tests and binary logistic regression, and was theoretically grounded in the Unified Theory of Acceptance and Use of Technology (UTAUT) and Social Cognitive Theory (SCT). The results indicate significant differences between students and faculty regarding general attitudes toward AI, with students manifesting higher levels of concern regarding job replacement. However, both groups converge in their functional definition of AI as a major factor in labor transformation, suggesting an evaluative rather than a cognitive difference. Multivariate analyses show that personal readiness and the perception of organizational readiness are the primary predictors of a positive attitude toward AI, while demographic variables lose statistical significance when these dimensions are controlled. This study contributes to the literature by highlighting that AI-related anxiety is not inherently determined by demographic characteristics but represents a malleable state shaped by individual competencies and institutional conditions. The findings underscore the strategic role of universities in reducing perceptions of replacement and facilitating the transition to an AI-augmented labor market through training policies, adequate infrastructure, and transparent institutional communication. Full article

Food waste management represents an important economic and environmental challenge for the hospitality sector on a global level, and especially for markets that are still developing, such as Serbia. This exploratory qualitative pilot study supported by descriptive statistics based on expert interviews investigates management perceptions of food waste in Belgrade’s hotels, analyzing the gap between sustainability food waste awareness and operational implementation within a transitional economy. An exploratory pilot study was conducted using a purposive sample of nine general managers from upscale hotels. Interviews with general managers were conducted in person and data was collected via a structured questionnaire based on a five-point Likert scale. The results suggest that general managers perceive food waste reduction primarily as a cost-saving measure rather than a strategic driver of profitability. Using Upper Echelons Theory (UET), this research provides insights into how management-level cognition shapes sustainability routines. The findings offer a preliminary framework for integrating basic training modules and transparent cost-tracking systems to transition from passive to proactive sustainable operations in the Serbian hospitality sector. This exploratory pilot study advances hospitality sustainability research by offering preliminary insights into managerial cognition concerning food waste within a transitional tourism economy. Full article

Automated video-based detection of cognitive disorders can enable a scalable non-invasive health monitoring. However, existing methods focus on a single disease and provide limited interpretability, whereas real-world videos often contain co-occurring conditions. We propose a novel unified multi-task method to detect depression and Parkinson’s disease (PD) from in-the-wild video data called DEPART (DEpression and PArkinson’s Recognition Technique). It performs body region extraction, Contrastive Language-Image Pre-training (CLIP)-based visual encoding, Transformer-based temporal modeling, and prototype-aware classification with a gated fusion technique. Gradient-based attention maps are used to visualize task-specific regions that drive predictions. Experiments on the In-the-Wild Speech Medical (WSM) corpus demonstrate competitive performance: the multi-task model achieves Recall of 82.39% for depression and 78.20% for PD, compared with 87.76% and 78.20%, for the best single-task models. The multi-task learning initially increases false positives for healthy persons in the PD subset, mainly due to annotation–modality mismatches, static visual content misinterpreted as motor impairments, and occasional body detection failures. After cleaning the test data, Recall for healthy individuals becomes comparable across models; the multi-task model improves Recall for both depression (from 82.39% to 87.50%) and PD (from 78.20% to 86.14%), suggesting better robustness for real-life clinical applications. Full article

Background/Objectives: Dental anxiety and uncooperative behavior present significant challenges in pediatric dentistry and may adversely affect treatment outcomes and oral health. The main goal of this study was to evaluate the predictive performance of machine learning models in classifying dental anxiety measured using the Abeer Children Dental Anxiety Scale (ACDAS), predicting uncooperative behavior, estimating continuous dental anxiety scores, and identifying key predictors among children aged 6–11 years attending pediatric dental clinics in Jeddah, Saudi Arabia. Methods: This is an analytical cross-sectional study conducted among 952 children to evaluate whether machine learning models could predict dental anxiety and cooperative behavior based on demographic, clinical, and behavioral variables. Twenty variables captured demographic, medical, and dental history, BMI, and anxiety/behavioral measures. Data preprocessing included removing sparse variables, imputing missing values, and encoding categorical and ordinal variables appropriately. Logistic Regression models were trained to classify dental anxiety and cooperative behavior. A Random Forest Regressor was used to predict continuous anxiety scores, and a Random Forest Classifier was used for feature importance analysis. Principal Component Analysis (PCA) and K-Means clustering were applied to explore behavioral subgroups. Results: This dataset shows the Logistic Regression model with 0.92 accuracy (ROC AUC 0.98) for predicting dental anxiety and 0.91 accuracy (ROC AUC 0.95) for cooperative behavior. The Random Forest Regressor predicted anxiety scores with R² = 0.97. Feature importance revealed that sensory and cognitive responses were key predictors of anxiety and cooperation. Unsupervised clustering identified two behavioral profiles: one with lower and another with higher anxiety and cooperation. Conclusions: ML models demonstrated strong prediction of dental anxiety and cooperation in this pediatric sample. While promising for early detection and personalized management of anxious or uncooperative children, further validation is essential before clinical use. Full article

Burnout among long-term care workers is a public health concern, yet mixed-methods evidence from China is scarce. To examine multilevel correlates of burnout, a convergent mixed-methods study using a Social–Ecological Framework was conducted. In the quantitative strand, 494 workers were surveyed using two-stage cluster sampling, and probability-weighted multivariable linear regression examined factors associated with emotional exhaustion, depersonalization, and reduced personal accomplishment. In the qualitative strand, 15 participants completed semi-structured interviews; transcripts were managed in MAXQDA 2025 and analyzed thematically. Burnout was common (30.77% mild, 33.00% moderate, 17.00% severe). Quantitative findings showed that burnout dimensions were associated with gender, age, marital status, employment arrangement, institution type, training intensity, caregiver burden, and recognition of the long-term care insurance policy (p < 0.05). Qualitative findings highlighted cognitive adaptation, emotional reciprocity with older adults, organizational training and support, and policy recognition as potential buffering resources. These findings suggest that burnout is shaped by influences across multiple levels. Coordinated efforts may help alleviate burnout by strengthening training systems, reducing caregiving burden, enhancing recognition of long-term care policies, and elevating the societal value of care work. Future research should validate these potential courses of action through longitudinal or intervention studies. Full article