Search Results (20)

Background: Rehabilitation depends on using instructional materials, which many patients find difficult to understand; thus, their adherence to the safety and care may be affected. Text simplification systems used, in general, do not usually focus on procedure-oriented guidance or the degree of personalization required in rehabilitation settings. Methods: We present PatientEase, a domain-aware retrieval-augmented generation framework that changes rehabilitation instructions to simple words without changing the clinical meaning. PatientEase incorporates two complementary retrievers that is a corpus retriever that is tuned for rehabilitation and a user-aligned retriever that is conditioned on patient profiles, together with a role-structured, multi-agent rewriting pipeline; outputs can be further refined by using reinforcement learning from human feedback with a composite reward for readability, factuality, and clinician-preferred structure. Results: The latter was quite comprehensively compared in four benchmark tests against baselines, wherein SARI, FKGL, BERTScore, and MedEntail indices are employed, as well as clinician-patient assessments. PatientEase achieves 52.7 SARI and 92.1% factual entailment, and receives the highest fluency and simplicity ratings; ablations also underline each module’s role. Conclusions: PatientEase paves the road for safer, patient-centered communication in rehabilitation and lays the groundwork for trustworthy clinical dialogue systems. Full article

The development of new technologies, improved by advances in artificial intelligence, has enabled the creation of a new generation of applications in different scenarios. In medical systems, adopting AI-driven solutions has brought new possibilities, but their effective impacts still need further investigation. In this context, a chatbot prototype trained with large language models (LLMs) was developed using data from the Santa Catarina Telemedicine and Telehealth System (STT) Dermatology module. The system adapts Llama 3 8B via supervised Fine-tuning with QLoRA on a proprietary, domain-specific dataset (33 input-output pairs). Although it achieved 100% Fluency and 89.74% Coherence, Factual Correctness remained low (43.59%), highlighting the limitations of training LLMs on small datasets. In addition to G-Eval metrics, we conducted expert human validation, encompassing both quantitative and qualitative aspects. This low factual score indicates that a retrieval-augmented generation (RAG) mechanism is essential for robust information retrieval, which we outline as a primary direction for future work. This approach enabled a more in-depth analysis of a real-world telemedicine environment, highlighting both the practical challenges and the benefits of implementing LLMs in complex systems, such as those used in telemedicine. Full article

The exponential growth of scientific literature demands scalable methods to evaluate large-language-model outputs beyond surface-level fluency. We present a two-phase framework that separates generation from evaluation: a retrieval-augmented generation system first produces candidate abstracts, which are then embedded into semantic co-occurrence graphs and assessed using seven robustness metrics from complex network theory. Two experiments were conducted. The first varied model, embedding and prompt configurations, achieved results showing clear differences in performance; the best family combined gemma-2b-it, a prompt inspired by chain-of-Thought reasoning, and all-mpnet-base-v2, achieving the highest graph-based robustness. The second experiment refined the temperature setting for this family, identifying $\tau =0.2$ as optimal, which stabilized results (sd $=0.12$) and improved robustness relative to retrieval baselines ($\Delta E_G=+0.08$, $\Delta \rho =+0.55$). While human evaluation was limited to a small set of abstracts, the results revealed a partial convergence between graph-based robustness and expert judgments of coherence and importance. Our approach contrasts with methods like GraphRAG and establishes a reproducible, model-agnostic pathway for the scalable quality control of LLM-generated scientific content. Full article

History tools facilitate iterative analysis data by allowing users to view, retrieve, and revisit visualization states. However, traditional history tools are constrained by screen space limitations, which restrict the user’s ability to fully understand historical states and make it challenging to provide an intuitive preview of these states. Most immersive history tools, in contrast, operate independently of screen space and fail to consider their integration. This paper proposes HybridFilm, an innovative mixed-reality history tool that seamlessly integrates screen space and immersive reality. First, it expands the user’s understanding of historical states through a multi-source spatial fusion approach. Second, it proposes a “focus + context”-based multi-source spatial historical data visualization and interaction scheme. Furthermore, we assessed the usability and utility of HybridFilm through experimental evaluation. In comparison to traditional history tools, HybridFilm offers a more intuitive and immersive experience while maintaining a comparable level of interaction comfort and fluency. Full article

Synthetic medical text generation has emerged as a solution to data scarcity and privacy constraints in clinical NLP. This review systematically evaluates the use of Large Language Models (LLMs) for structured medical text generation, examining techniques such as retrieval-augmented generation (RAG), structured fine-tuning, and domain-specific adaptation. Four search queries were applied following the PRISMA methodology to identify and extract data from 153 studies. Key benchmarking metrics, such as performance measures, and qualitative insights, including methodological trends and challenges, were documented. The results show that while LLM-generated text improves fluency, hallucinations and factual inconsistencies persist. Structured consultation models, such as SOAP and Calgary–Cambridge, enhance coherence but do not fully prevent errors. Hybrid techniques that combine retrieval-based grounding with domain-specific fine-tuning improve factual accuracy and task performance. Conventional evaluation metrics (e.g., ROUGE, BLEU) are insufficient for medical validation, highlighting the need for domain-specific benchmarks. Privacy-preserving strategies, including differential privacy and PHI de-identification, support regulatory compliance but may reduce linguistic quality. These findings are relevant for clinical NLP applications, such as AI-powered scribe systems, where structured synthetic datasets can improve transcription accuracy and documentation reliability. The conclusions highlight the need for balanced approaches that integrate medical structure, factual control, and privacy to enhance the usability of synthetic medical text. Full article

Background: Primary progressive aphasia (PPA) is a neurodegenerative disorder that worsens over time without appropriate treatment. Although referral to a speech and language pathologist is essential for diagnosing language deficits and developing effective treatment plans, there is no scientific consensus regarding the most effective treatment. Thus, our study aims to assess the efficacy and safety of various therapeutic interventions for PPA. Methods: Google Scholar, PubMed, Web of Science, and the Cochrane Library databases were systematically searched to identify articles assessing different therapeutic interventions for PPA. To ensure comprehensive coverage, the search strategy employed specific medical subject headings. The primary outcome measure was language gain; the secondary outcome assessed overall therapeutic effects. Data on study characteristics, patient demographics, PPA subtypes, therapeutic modalities, and treatment patterns were collected. Results: Fifty-seven studies with 655 patients were included. For naming and word finding, errorless learning therapy, lexical retrieval cascade (LRC), semantic feature training, smartphone-based cognitive therapy, picture-naming therapy, and repetitive transcranial magnetic stimulation (rTMS) maintained effects for up to six months. Repetitive rTMS, video-implemented script training for aphasia (VISTA), and structured oral reading therapy improved speech fluency. Sole transcranial treatments enhanced auditory verbal comprehension, whereas transcranial direct current stimulation (tDCS) combined with language or cognitive therapy improved repetition abilities. Phonological and orthographic treatments improved reading accuracy across PPA subtypes. tDCS combined with speech therapy enhanced mini-mental state examination (MMSE) scores and cognitive function. Several therapies, including smartphone-based cognitive therapy and VISTA therapy, demonstrated sustained language improvements over six months. Conclusions: Various therapeutic interventions offer potential benefits for individuals with PPA. However, due to the heterogeneity in study designs, administration methods, small sample sizes, and lack of standardized measurement methods, drawing a firm conclusion is difficult. Further studies are warranted to establish evidence-based treatment protocols. Full article

Empathetic and coherent responses are critical in automated chatbot-facilitated psychotherapy. This study addresses the challenge of enhancing the emotional and contextual understanding of large language models (LLMs) in psychiatric applications. We introduce Emotion-Aware Embedding Fusion, a novel framework integrating hierarchical fusion and attention mechanisms to prioritize semantic and emotional features in therapy transcripts. Our approach combines multiple emotion lexicons, including NRC Emotion Lexicon, VADER, WordNet, and SentiWordNet, with state-of-the-art LLMs such as Flan-T5, Llama 2, DeepSeek-R1, and ChatGPT 4. Therapy session transcripts, comprising over 2000 samples, are segmented into hierarchical levels (word, sentence, and session) using neural networks, while hierarchical fusion combines these features with pooling techniques to refine emotional representations. Attention mechanisms, including multi-head self-attention and cross-attention, further prioritize emotional and contextual features, enabling the temporal modeling of emotional shifts across sessions. The processed embeddings, computed using BERT, GPT-3, and RoBERTa, are stored in the Facebook AI similarity search vector database, which enables efficient similarity search and clustering across dense vector spaces. Upon user queries, relevant segments are retrieved and provided as context to LLMs, enhancing their ability to generate empathetic and contextually relevant responses. The proposed framework is evaluated across multiple practical use cases to demonstrate real-world applicability, including AI-driven therapy chatbots. The system can be integrated into existing mental health platforms to generate personalized responses based on retrieved therapy session data. The experimental results show that our framework enhances empathy, coherence, informativeness, and fluency, surpassing baseline models while improving LLMs’ emotional intelligence and contextual adaptability for psychotherapy. Full article

Metacognition is vital for creativity; however, the specific contributions of its components (i.e., metacognition knowledge, metacognition experience, and metacognition monitoring and control) have received varying levels of attention, particularly due to the limited research on metacognitive experience. Additionally, the interactions among these components in influencing creative cognition remain unclear. We conducted two experiments to explore the influence of metacognitive experience on divergent thinking (e.g., alternative uses tasks, AUT) and the moderating role of creative mindsets—a core element of metacognitive knowledge—in this process. In Experiment 1, retrieval fluency, measured by the quantity of the ideas generated, was used to activate varying levels of metacognitive experience (fluency vs. disfluency) during the AUT. The findings showed that the originality of ideas generated under the disfluency condition was significantly higher than under the fluency condition, suggesting a positive effect of metacognitive disfluency experience on AUT. In Experiment 2, a multiple-choice task was used to prime individuals’ creative mindsets (entity vs. incremental). The results indicated that individuals with a creative growth mindset exhibited greater cognitive persistence under the disfluency condition, subsequently enhancing the originality of their ideas, indicating that creative mindsets moderate the effect of metacognitive disfluency experience on AUT performance via cognitive persistence. We integrated previous findings to describe the interactive impacts of creative mindsets, metacognitive experience, and metacognitive monitoring and control on divergent and convergent creative thinking processes within a metacognitive framework, providing a model to reveal the dynamic interplay of metacognitive processes in creative cognition. Practically, fostering individuals’ growth-oriented creative mindsets may represent a promising avenue for creativity development. Full article

A conversational system is an artificial intelligence application designed to interact with users in natural language, providing accurate and contextually relevant responses. Building such systems for low-resource languages like Swahili presents significant challenges due to the limited availability of large-scale training datasets. This paper proposes a Retrieval-Augmented Generation-based system to address these challenges and improve the quality of Swahili conversational AI. The system leverages fine-tuning, where models are trained on available Swahili data, combined with external knowledge retrieval to enhance response accuracy and fluency. Four models—mT5, GPT-2, mBART, and GPT-Neo—were evaluated using metrics such as BLEU, METEOR, Query Performance, and inference time. Results show that Retrieval-Augmented Generation consistently outperforms fine-tuning alone, particularly in generating detailed and contextually appropriate responses. Among the tested models, mT5 with Retrieval-Augmented Generation demonstrated the best performance, achieving a BLEU score of 56.88%, a METEOR score of 72.72%, and a Query Performance score of 84.34%, while maintaining relevance and fluency. Although Retrieval-Augmented Generation introduces slightly longer response times, its ability to significantly improve response quality makes it an effective approach for Swahili conversational systems. This study highlights the potential of Retrieval-Augmented Generation to advance conversational AI for Swahili and other low-resource languages, with future work focusing on optimizing efficiency and exploring multilingual applications. Full article

This narrative review delves into the area of endogenous hormones and their impact on cognitive function, with a focus on women transitioning through perimenopause. While artificial intelligence technologies have revolutionized cognitive research, the inclusion of hormonal biomarkers remains sparse. The review synthesizes findings from diverse studies exploring the relationships between estrogen, progesterone, testosterone, other sex hormones, and cognitive performance. The research question explores the potential for monitoring endogenous hormonal levels during perimenopause to predict cognitive decline and inform preventive strategies. An analysis of relevant studies reveals a complex relationship, with varying impacts on cognitive domains. Thus, high E2 levels correlate positively with verbal memory and retrieval efficiency, contrasting with lower levels associated with enhanced visual memory, and testosterone shows positive links to verbal fluency. The limitations of existing research, including heterogeneous methodologies and a dearth of premenopausal representation, emphasize the necessity for future studies. To achieve this objective, it is important to leverage data from studies implementing standardized methodologies for tracking endogenous hormonal levels while accounting for cycle phases and menopausal transition stages. Additionally, employing standardized assessments for cognitive decline and analyzing extensive datasets derived from real-world sources, such as hospital or outpatient clinic chains, and digital apps, is crucial. Full article

This study aims to identify and analyze relevant characteristics associated with creative thinking, particularly in arts and design education. A systematic literature review was conducted following the PRISMA protocol, utilizing the Scopus database, where 292 studies were retrieved through search strings. From these, 187 studies were selected for the final analysis. The results highlight an emphasis on experiential learning, STEAM (Science, Technology, Engineering, Arts, and Mathematics), and interdisciplinary approaches as prevalent educational methodologies for fostering creative thinking. The identified techniques include interdisciplinary projects, artistic practices, nature-based activities, and the use of digital tools. The core skills identified include originality, fluency, flexibility, and elaboration. Furthermore, it was observed that most of the studies were conducted in higher education institutions. The study underscores the urgency of promoting research in specific regions, such as Latin America, to contribute to advancing and enriching the educational landscape in these areas. Additionally, it emphasizes the importance of fostering creativity from an early age. The significance of this study lies in its contribution to more effective pedagogical practices for the development of creative thinking that positively impacts education and prepares individuals for the challenges of the 21st century. Full article

The purpose of this study was to investigate attrition effects in a group of L1-Greek–L2-English speakers and to explore their views on attrition and their feelings about their own use of both languages. The first part (n = 32) was a psycholinguistic study measuring semantic and formal verbal fluency which was part of a broader project. The second part (n = 14) was a sociolinguistic study of semi-structured interviews aiming to gain insights into participants’ lived experiences of attrition. In verbal fluency, monolinguals outperformed bilinguals in the number of correct responses in both semantic and formal fluency. The analysis of the interview transcripts suggested that attriters experience attrition negatively, as a loss of a competence they once had, with two types of negative experiences emerging more prominently: (a) the realisation that they have difficulties with lexical retrieval and (b) stigmatising and judgemental comments by (non)-attriters. Combining quantitative and qualitative methods, this study on attriters can give us unique insights into their lived experience of attrition. Full article

Math fluency is the ability to solve arithmetic facts quickly and accurately (i.e., addition and subtraction problems up to 20, and multiplication and division problems from the multiplication table). Curricula in primary school devote a significant period of time for learning and retrieval of arithmetic facts. Recently, a new computerized tool to assess math fluency—the BGU-MF (Ben-Gurion University Math Fluency) test—was developed and found to be a reliable and valid tool for adults. In the current study, we examine the performance of first to sixth-grade children in math fluency using the BGU-MF. The results present the performance of MF during childhood and emphasize that it continues to develop during primary school. Importantly, proficiency of MF differed by operations, and the automaticity of math facts was acquired in different grades. Moreover, we found that the BGU-MF is a reliable and valid tool not only for adults but also for children during primary school. Our study has educational implications for the teaching, practice, and retrieval of arithmetic facts. Full article

Metabolic syndrome (MetS) or otherwise insulin resistance (IR) is described as a cluster of several commonly occurring disorders, including abdominal obesity; lipids disorders, such as hypertriglyceridemia; and low levels of high-density-lipoprotein cholesterol (HDL-C), hypertension (≥130/85 mmHg), and carbohydrates disorders, such as impaired fasting glucose or diabetes mellitus type 2. Type 2 diabetes (T2DM) constitutes insulin resistance, which is a strong risk factor for strokes. Patients with MetS are often prone to cognitive decline. Metabolic risk factors, hypertension, and diabetes, amongst them, have been hypothesized to play a great role in the pathogenesis of Alzheimer’s disease (AD) and the development of vascular dementia. For neuropsychological diagnostic and theoretical purposes verbal fluency is defined as a cognitive function that facilitates information retrieval from memory. It engages executive control and other cognitive processes, such as selective attention, selective inhibition, mental set shifting, internal response generation, and self-monitoring, as well as imagination and psychomotor skills. A total of 90 subjects, divided into 2 groups, patients with MetS (45) and healthy controls (45), were assessed. A significant difference in performance was found between the patients and controls, both in the phonetic (p < 0.01) and semantic fluency trials (p < 0.001). The MetS patients produced less words in the letter K and animal categories. The analysis of descriptive statistics shows that the group of patients with metabolic syndrome generated fewer words in both the phonetic and semantic categories. Our study shows that there is an association between metabolic factors and the verbal fluency performance of MetS patients. This is true, especially for phonetic verbal fluency, which is traditionally connected with the frontal cortex. Lower switching signifies possible executive dysfunctions amongst people with MetS. Subjects with this condition generated more diverse words and created less standard associations. This further implies the existence of dysexecutive syndrome and the need for diagnosing patients in this direction and involving this group of people in therapy. The proper correction of MetS components may improve cognitive function. Full article

Research in bilingual healthy controls (BHC) has illustrated that detailed characterization of verbal fluency along with separate measures of executive control stand to inform our understanding of the lexical and cognitive underpinnings of the task. Such data are currently lacking in bilinguals with aphasia (BWA). We aimed to compare the characteristics of verbal fluency performance (semantic, letter) in Bengali–English BWA and BHC, in terms of cross-linguistic differences, variation on the parameters of bilingualism, and cognitive underpinnings. BWA showed significant differences on verbal fluency variables where executive control demands were higher (fluency difference score, number of switches, between-cluster pauses); whilst performed similarly on variables where executive control demands were lower (cluster size, within-cluster pauses). Despite clear cross-linguistic advantage in Bengali for BHC, no cross-linguistic differences were noted in BWA. BWA who were most affected in the independent executive control measures also showed greater impairment in letter fluency condition. Correlation analyses revealed a significant relationship for BWA between inhibitory control and number of correct responses, initial retrieval time, and number of switches. This research contributes to the debate of underlying mechanisms of word retrieval deficits in aphasia, and adds to the nascent literature of BWA in South Asian languages. Full article