7879 research outputs found
Sort by
Artificial intelligence in hospital fall Prevention: Current Applications, Challenges, and Future Directions
Full text linkHospital falls represent a critical patient safety challenge, affecting millions of patients globally and resulting in substantial morbidity, mortality, and healthcare costs. Traditional fall prevention strategies, whilst beneficial, often lack the precision and real-time responsiveness needed for optimal patient protection. This narrative review with systematic search examines the current applications, effectiveness, and implementation challenges of artificial intelligence (AI) technologies in hospital fall prevention. A comprehensive search was conducted across PubMed, EMBASE, IEEE Xplore, and Google Scholar databases from January 2015 to October 2024. AI technologies demonstrate promise across four primary domains: machine learning predictive models achieving AUROC of 0.85–0.97 (with calibration reported variably), computer vision systems enabling real-time behavioural monitoring (94–97% detection accuracy in controlled settings), sensor-based technologies providing continuous patient surveillance (89–96% accuracy with multi-sensor fusion), and natural language processing enhancing risk factor extraction from clinical documentation (sensitivity 95% CI in selected studies). These metrics represent primarily single-site, retrospective studies with limited external validation and variable baseline fall rates. Successful implementations report fall reduction rates of 0.9–1.2 falls per 1,000 patient-days (15–40% relative reduction) across various healthcare settings, though baseline rates ranged from 2.8 to 5.1 falls per 1,000 patient-days across different care settings, and secular trends and study design heterogeneity limit causal inference. AI-driven systems offer enhanced prediction accuracy, real-time monitoring capabilities, and personalised risk assessment. However, implementation challenges include alarm fatigue (alert rates and positive predictive value rarely reported), algorithmic bias requiring ongoing fairness audits, liability concerns when AI systems fail to prevent falls, data privacy concerns, integration complexities, clinical workflow adaptation, and substantial cost barriers for smaller institutions. Future developments should prioritize explainable AI systems, multisite external validation with standardised metrics (AUROC, AUPRC, calibration), federated learning approaches, and implementation trials examining both fall rates and care process outcomes
Immunotherapy-mediated cancer reversion: Possibilities and prospects
Full text linkImmunotherapy has revolutionized cancer treatment by enabling durable tumor control through immune activation. Emerging evidence suggests that beyond cytotoxic elimination, immune responses can reprogram malignant cells toward normalized, differentiated states, a phenomenon termed immunotherapy-mediated cancer reversion. This paradigm shift positions the immune system as a restorative rather than solely destructive force. This review synthesizes contemporary evidence on immunotherapy-mediated cancer reversion, evaluating mechanistic pathways and clinical implications across diverse malignancies to establish a conceptual framework for immune-driven phenotypic normalization. A comprehensive narrative review was conducted across PubMed, Web of Science, and Scopus databases, encompassing literature from 2015 to 2025. Evidence was synthesized thematically across immune checkpoint blockade, adoptive cell therapies, cytokine modulation, and microenvironmental remodeling. Immune-mediated reversion arises through coordinated epigenetic, metabolic, and microenvironmental reprogramming. Checkpoint inhibitors restore differentiation programs via IFNγ-driven chromatin remodeling, while CAR-T and NK-cell therapies induce metabolic normalization and epithelial restoration. Cytokine signaling and macrophage reprogramming reinforce reversion by modulating angiogenesis and stromal architecture. Clinical observations across melanoma, lung cancer, breast cancer, hematologic malignancies, and hepatocellular carcinoma support this restorative immune process. Single-cell and spatial omics identify transitional states bridging malignancy and normalcy. Immunotherapy-mediated cancer reversion represents a conceptual frontier shifting oncology from eradication to restoration. Future progress requires defining biomarkers, confirming mechanistic permanence, and redesigning clinical endpoints. As integrative immuno-epigenetic frameworks mature, immune-driven reversion may evolve from biological curiosity to clinically reproducible pathway toward durable remission and functional cure
Working with Interpreters in Mental Health
No full textThis fully updated edition gives an insight into the opportunities and challenges of mental health professionals and interpreters working together in mental health.Drawing on extensive theory, research, and practice, chapters combine contributions from a range of disciplines on topics including interpreters in medical consultations; issues of language provision in health care services; the application of theoretical frameworks to the work with interpreters; and the work of interpreters in a variety of practice settings. This thoroughly revised edition also features additional chapters exploring interpreter perspectives on their work, along with new chapters on working with interpreters in forensic settings, in National Health Service talking therapies/primary care settings, in humanitarian work, in schools, and with older adults, as well as presenting an interprofessional approach to interpreter and therapist training.This book will be invaluable for practitioners of psychology, psychiatry, social work, and other health professionals. It will also be relevant to interpreters working with mental health professionals and their managers and service leads. It will be of interest to anyone involved in commissioning language support in health and social care services
Reinventing DISC personality assessment: Machine learning approaches for deeper insights and greater efficiency
Full text linkThe DISC personality framework, while widely adopted in applied settings, relies on a fixed rule-based classification method that may oversimplify individual behavioural profiles. This study explores whether machine learning can offer a more flexible, efficient, and accurate approach to DISC classification. Using a dataset of over 1,000 participants, we evaluated multiple supervised models-including Logistic Regression, XGBoost, SVM, MLP, Random Forest, and K-Nearest Neighbours-alongside unsupervised clustering techniques. Logistic Regression emerged as the top-performing model, achieving 93.53% accuracy and demonstrating superior cross-validation stability. Recursive Feature Elimination identified a reduced set of ten key questionnaire items, maintaining over 91% accuracy and enabling the development of a concise assessment tool. Such a shortened questionnaire offers substantial practical benefits for real-world applications, particularly in fast-paced organisational contexts like recruitment, leadership coaching, and team composition, where rapid yet reliable personality insights are invaluable. Clustering analysis further revealed alignment with traditional DISC categories, while uncovering potential hybrid profiles. A comparative clustering analysis between the full 40-item and reduced 10-item questionnaires confirmed that the same behavioural trait structures could be recovered using fewer items. Despite minor differences in cluster alignment, DISC trait patterns remained consistent across both models. These findings confirm that machine learning can replicate and enhance conventional DISC assessments, not only in terms of classification accuracy but also by preserving the conceptual integrity of the DISC framework. The study validates that the reduced DISC assessment captures the latent personality structure of the original model, offering a scalable and empirically grounded solution for modern psychological evaluation. The complete modelling pipeline, including feature selection and clustering insights, contributes to the growing field of data-driven psychometrics
Eco-anxiety in the times of climate crisis: a grounded theory inquiry
Full text linkA contextual perspective on mental health is critical in developing a comprehensive understanding of wellbeing in line with the precepts of Geopsychiatry. A review of the literature indicates a limited understanding of how people deal with the global climate crisis using a geo-psychiatry perspective. The experience of awakening to the climate crisis has been described using the term “eco-anxiety”. A lack of in-depth exploration of this subjective experience has meant a fragmented theory. To contribute to our understanding of eco-anxiety, the current study explores qualitative aspects of this experience, looking at the reports of eco-anxiety experienced by people who self-reported attending a group psycho-ecological intervention for facing the climate crisis.Using a constructivist grounded theory approach, critical realist ontology and moderate social constructionist epistemology, semi-structured interviews were conducted with 13 adults who self-identified as experiencing “eco-anxiety” and had attended an ecopsychology support group. Two core categories of theory emerged: “the psychosocial processes of eco-anxiety” and “the psychosocial processes of regeneratively sustained eco-anxiety”. The results are explored through figures that analogise the seasons, demonstrating the participants' reported process of psychosocial adaptation: the growth and expansion of the self in the face of eco-anxiety, reflecting the integration of experiences. This metaphor does not suggest a linear process. Participants described moving bidirectionally. Despite the challenges, group participants report that the process of awareness can lead to a more connected way of life and ultimately the development of psychosocial resilience, which is essential for navigating sustained mutual care in the face of global environmental instability
Transforming patient education on retinal detachment: A multilingual voice-enabled retrieval-augmented generation chatbot
Full text linkPurpose: To design, implement, and evaluate a multilingual, voice-enabled Retrieval-Augmented Generation (RAG) chatbot that delivers personalized, clinically grounded information and answers patient questions about retinal detachment. Design: Cross-sectional systems-evaluation study benchmarking three Large Language Models (LLMs) within an identical RAG pipeline using a fixed, clinically curated question set. Participants: No human participants. Evaluation used clinically relevant retinal-detachment questions derived from clinician-verified sources. Comparative arms were GPT-4o, Claude Opus, and Gemini 1.5 Pro. Methods: A knowledge base on retinal detachment was assembled from clinician-verified materials and annotated question-answer pairs. Semantic retrieval used MiniLM embeddings and FAISS, with optional CrossEncoder reranking. Prompts incorporated dialogue history and source citations and were applied to each LLM under matched generation settings. Real-time interaction was enabled via speech recognition and multilingual text-to-speech in a Gradio interface. Regulatory and ethical safeguards addressing privacy, transparency, and usability were incorporated. Performance was assessed on the question set. Main outcome measures: Automated text-generation metrics including BLEU, ROUGE-1, ROUGE-L, and BERTScore (F1). Results: GPT-4o outperformed Claude Opus and Gemini 1.5 Pro across all metrics (BLEU 0.56; ROUGE-L 0.72; BERTScore F1 0.86). The system generated contextually appropriate responses with inline source citations and produced multilingual audio output, supporting accessibility for users with language needs or low vision. The technical design was informed by NHS-oriented digital and ethical principles. Conclusion: A multilingual, voice-enabled RAG chatbot for ophthalmology patient education is feasible and effective in automated evaluations, with GPT-4o performing best under identical conditions. The approach shows potential to improve post-surgical understanding and communication; prospective clinical validation with patient-centered outcomes is warranted
The Perception of Pharmacology Among College Students: An East London Perspective
Full text linkPharmacology is an integrative discipline that plays an integral part in the development of new medicines with improved safety and efficacy profiles. Sustained growth of this important discipline within the UK is made possible through training of the next generation of pharmacologists. In order to ensure that interest in pharmacology continues to grow, endeavors aimed at exposing students to pharmacology from earlier stages of their educational journeys have to be put in place. To this end, the current study aimed at capturing the perception of further education students on pharmacology in the East London area. This survey-based study, which took place between 2020 and 2021, consisted of multiple choice questions. The study revealed that over 80% of the surveyed biology and chemistry students have previously heard about pharmacology. However, when assessing their basic knowledge of pharmacology, it emerged that students had a somewhat distorted perception of pharmacology, as only 9.8% of the students associated pharmacology with biology. Additionally, students confused pharmacology with pharmacy. Students also had a somewhat limited understanding of what pharmacologists do. Finally, 23.5% of the students stated that they would consider studying pharmacology at university if they received sufficient introduction, with 92.2% of the students stating that they would like to see pharmacology added to their further education curriculum. In order to ensure the growth of pharmacology in the UK and given the misconceptions that students have, as highlighted in this study, we recommend that basic pharmacology education be introduced to the further education curriculum
Ground waste glass as a supplementary cementitious material for concrete: sustainable utilization, material performance and environmental considerations
Full text linkThis review paper delves into the role, potential and peculiarities of ground waste glass as both a supplementary cementitious material (SCM) and a filler in concrete. Motivated by the increasing emphasis on sustainable construction practices, the paper explores the potential of ground waste glass in enhancing concrete performance while addressing environmental concerns associated with traditional materials. The comprehensive review encompasses the properties of ground waste glass as an SCM, its global availability, its influence on various concrete properties, compatibility with cementitious systems, optimisation techniques, challenges, and practical applications. Key considerations such as particle size distribution, replacement levels, and chemical activation in optimising recycled ground waste glass incorporation are also highlighted. This comprehensive review underscores the potential of ground waste glass as a sustainable additive in concrete, enhancing both environmental responsibility and structural performance
Enterprise Social Media and Employee Agility: The Role of Task Context and Personal Motivation
Full text linkOrganizations increasingly use social media platforms to improve internal communication, content creation, and knowledge sharing among employees. This study seeks to explore whether task characteristics (complexity and interdependence) influence the relationship between the usage of enterprise social media (ESM) and employee agility. The regulatory focus theory is used to explain the influence of employees’ promotion and prevention focus on the relationship between the usage of ESM platforms and task characteristics, as well as employee agility. All assumptions were tested using 318 cases from Chinese companies using the PROCESS Macro tool. Both task complexity and task interdependence mediate the relationship of ESM platforms and employee agility. Promotion focus moderates the relationship of ESM platforms and task characteristics and the indirect connection of ESM platforms and employee agility through task characteristics, but prevention focus weakens these relationships
