Search Results (342)

Metabolic dysfunction-associated steatotic liver disease (MASLD) represents the hepatic manifestation of systemic metabolic dysfunction and has emerged as one of the leading causes of chronic liver disease worldwide. Its pathogenesis is complex and multifactorial, involving insulin resistance, altered lipid metabolism, mitochondrial dysfunction, oxidative stress, and chronic low-grade inflammation. Beyond these classical mechanisms, growing evidence highlights the central role of modifiable lifestyle-related factors, including chronic positive energy balance, high intake of fructose and saturated fats, ultra-processed foods, physical inactivity, sleep disruption, and environmental exposures such as endocrine-disrupting chemicals and air pollution, which have been associated with the activation of lipogenic and proinflammatory pathways in preclinical and observational studies. Conversely, protective dietary patterns, particularly the Mediterranean diet, together with regular physical activity, exert hepatoprotective metabolic and anti-inflammatory effects. An extensive literature search was conducted across the PubMed, Scopus, Cochrane Library, and Embase databases, covering publications through June 2026. The review was conducted following the SANRA recommendations for narrative reviews. The inclusion criteria encompassed clinical trials, systematic reviews, meta-analyses, and international clinical practice guidelines. This review provides an integrated framework by linking in a single interpretative model the classical pathogenic pathways with emerging dietary, behavioral, and environmental determinants and with systemic interorgan communication networks involving hepatokines, adipokines, and myokines. Understanding MASLD as a multisystemic metabolic disease driven by multiple determinants has critical implications for the development of targeted preventive and therapeutic strategies aimed at reducing its global burden and prevalence. Full article

Objectives: To identify factors influencing influenza vaccination willingness and uptake among adults aged ≥60 years in Henan Province and to evaluate the effect of a brief educational intervention on vaccination willingness and behavior. Methods: In September 2024, a cross-sectional survey based on the Behavioral and Social Drivers (BeSD) framework was conducted among adults aged ≥60 years across five counties in Henan. For participants without baseline willingness, a 3 min one-on-one educational intervention was delivered. In May 2025, following the end of the 2024–2025 influenza vaccination season (which runs from 1 October to 31 March in Henan Province), we retrieved vaccination records for all participants from the Henan Provincial Immunization Information System. This system captures all influenza vaccinations administered at designated vaccination clinics across the province. To ensure completeness for doses administered outside the provincial system (e.g., in other provinces or at private healthcare facilities), we conducted telephone follow-up interviews with all participants whose baseline vaccination intention was inconsistent with their actual vaccination behavior (i.e., willing but unvaccinated or unwilling but vaccinated). During these interviews, for those who reported receiving the vaccine outside Henan Province or at private facilities, we inquired about the specific date and location of vaccination to supplement the registry data. We also explored the reasons behind the intention–behavior discrepancy. For these participants, we requested vaccination certificates or other supporting documentation to confirm their vaccination status. Results: Baseline vaccination willingness was 68.20% (1630/2390), whereas the actual vaccination rate was only 6.95% (166/2390), yielding a willingness-to-behavior conversion rate of 9.51% (155/1630) among those with baseline willingness. Of the 760 participants without baseline willingness, 543 (71.45%) completed the 3 min one-on-one instant educational intervention and the follow-up assessment; the remaining 217 were excluded due to refusal or loss to follow-up. Among these 543 completers, 46 (8.47%) became willing to vaccinate, and eight (1.47%) were subsequently vaccinated. Multivariate analysis identified the social processes dimension as the strongest correlate of both willingness (OR = 1.38 per 1-point increase, 95% CI: 1.33–1.44) and uptake (OR = 1.12, 95% CI: 1.03–1.22). Urban residence was associated with higher willingness (OR = 1.41, 95% CI: 1.12–1.78) and higher uptake (OR = 1.64, 95% CI: 1.11–2.42). Current smokers had a significantly lower uptake than never smokers (OR = 0.43, 95% CI: 0.22–0.85). Among the 11 participants without baseline willingness who were eventually vaccinated (eight from the intervention group and three from the non-intervention group), family/friend influence (63.64%, 7/11) and physician recommendation (36.36%, 4/11) were the primary drivers. For those with willingness but no action (n = 1475), the main barriers were perceived good health (33.29%), high vaccine cost (27.12%), and lack of time (26.31%). Conclusions: Influenza vaccination among older adults in Henan exhibits a “high willingness, low conversion” pattern, with social processes as the strongest driver bridging the intention–behavior gap. A brief educational intervention improved willingness but failed to translate into meaningful uptake, underscoring that knowledge transfer alone is insufficient. We recommend a multi-component strategy that (1) mobilizes family members and community doctors as trusted vaccine advocates; (2) leverages family and village doctor networks to reduce urban–rural disparities; (3) counters the “perceived good health” barrier with age-specific risk communication; and (4) integrates vaccine recommendations into routine care for high-risk groups, particularly frequent outpatient attendees and smokers. Full article

To address the major safety hazard that heat released from mining polyurethane (PU) reinforcement materials may induce spontaneous combustion of residual coal in goaf, this study selected No. 3 coal from Wangzhuang Coal Mine, Shanxi Lu’an, as the research object. A self-developed large-capacity, large-scale experimental system was used to conduct programmed heating experiments on 2.0 kg multi-particle-size coal-PU mixed samples. The effects of PU content on characteristic gas release, crossing point temperature (CPT), residue morphology, and TGA-DSC characteristic temperatures were systematically investigated, and the reaction-kinetic evolution was further analyzed using the distributed activation energy model (DAEM). The results show that coal and PU exhibit a significant synergistic enhancement effect during co-heating. As the PU content increased, the release concentrations of CO, C₂H₄, and C₂H₆ increased markedly, and their initial release temperatures decreased, whereas CH₄ generation was inhibited by hydrogen-radical competition; no C₂H₂ was produced below 400 °C. The CPT decreased linearly with an increasing PU content, with an average decrease of approximately 8.5 °C for every 10% increase in PU content. Residue morphology showed clear critical features: glassy agglomerates appeared when the PU content exceeded 16.67%, and dense bulk coking occurred when the PU/coal mass ratio was greater than 1:10. TGA-DSC analysis showed that when the PU/coal ratio was lower than 1:10, the ignition temperature of the mixed sample was higher than that of pure coal, indicating an inhibitory synergistic effect. When the ratio exceeded 1:10, the ignition temperature decreased significantly, and the synergy shifted to promotion; increasing the heating rate shifted the characteristic temperatures to higher values and increased the reaction intensity. DAEM analysis further confirmed that when the PU ratio exceeded 1:10, the apparent activation energy of the mixed samples was lower than that of pure coal. Coal powder also acted as a physical skeleton that effectively dispersed molten PU, eliminated the activation-energy peaks of pure PU in the conversion ranges of 30–50% and 70–90%, and substantially improved combustion stability. Mechanistically, low-temperature PU melting and coating optimized heat and mass transfer, medium-temperature pyrolysis released active radicals and combustible gases that altered coal pyrolysis pathways and the radical reaction environment, and high-temperature hydrogen-radical competition reshaped the gas-product distribution. Together, these processes form a complete chain of synergistic spontaneous combustion. This study identifies key safety threshold parameters for PU reinforcement materials, recommends a PU content of ≤9.10%, and identifies CO and C₂H₄ as priority early-warning gases, providing direct experimental evidence for characteristic-gas-based early warning and mine fire prevention. Full article

Robo-advisors have expanded access to automated investment services, but many platforms continue to rely on relatively static onboarding procedures and limited forms of user interaction. This study examines how participants with investment experience respond to two next-generation robo-advisory design features: financial digital twins, understood as dynamic investor profiles that integrate goals, risk tolerance, cash-flow patterns, and anticipated life events, and conversational artificial intelligence (AI), understood as an interactive interface for explaining recommendations. Using a scenario-based randomized 2 × 2 online experiment, 336 adult respondents with self-reported investment experience, recruited through professional and academic networks, were assigned to one of four robo-advisor scenarios that varied the personalization architecture, standard profile versus digital twin, and the interface style, plain dashboard versus conversational AI, while holding the portfolio recommendation constant. The results show that digital-twin personalization increases perceived personalization and privacy concern, indicating that more adaptive advisory architectures may be viewed as both more relevant and more data-intensive. Conversational AI increases the perceived interactive quality of the advisory experience, while selected willingness-related patterns, especially in the combined digital-twin and conversational-AI condition, are treated as exploratory because several secondary composites displayed limited internal consistency. The strongest confirmatory emphasis is therefore placed on perceived personalization and privacy concern, and the remaining findings are best interpreted as scenario-based investor responses rather than evidence of actual adoption behavior or confirmed psychological mechanisms. The study contributes to behavioral FinTech research by clarifying the personalization–privacy tension in AI-enabled robo-advisory services and by offering design implications for more transparent, interactive, and responsibly personalized digital wealth-management systems. Full article

Background: Herpes zoster (HZ), commonly known as shingles, and post-herpetic neuralgia (PHN) represent growing public health concerns, particularly among older adults. Despite the established efficacy of the herpes zoster vaccine (HZV), global uptake remains suboptimal. Objectives: This scoping review maps evidence from Saudi Arabia evaluating the baseline knowledge, awareness, attitudes, acceptance, hesitancy, and clinical uptake of the HZV among general adults, high-risk populations, and healthcare workers (HCWs). Methods: The JBI and PRISMA-ScR methodological frameworks were strictly adhered to during mapping. Eligible sources included peer-reviewed, observational cross-sectional studies conducted in Saudi Arabia and published in English between 2022 and 2026. The search was conducted across PubMed, Scopus, Web of Science, and Google Scholar. Data were systematically extracted and charted using a standardized digital piloting framework to capture study characteristics (author, year, and region), sample sizes, target populations, knowledge percentages, actual vaccine uptake rates, and self-reported barriers. Results: Out of 25 retrieved records, 19 unique primary studies were mapped. Public knowledge of HZ complications and vaccine eligibility criteria was consistently low to moderate, falling below 50% across most cohorts. Conversely, while verbal willingness to receive the vaccine was highly favorable (ranging from 60% to 75%), a profound “intention–behavior gap” was observed, with actual clinical uptake being below 10%. Key barriers included a lack of public health campaigns, safety concerns regarding reactogenicity, online misinformation, and a lack of proactive provider communication. For HCWs, barriers included unclear local guidelines and a lack of workplace mandates. Ultimately, a proactive physician recommendation was identified as the single most powerful clinical facilitator, increasing vaccine acceptance by over 80% across all cohorts. Conclusions: While the shingles vaccine is now distributed completely free across Saudi Arabia, high public willingness has not translated into actual vaccination rates (10%) due to low public awareness of disease severity. Free vaccine availability alone is insufficient; primary care systems must shift from a passive delivery model to an active, provider-driven framework to successfully close this gap Full article

This study investigates the linguistic mechanisms of politeness and conversational implicature in digital classroom interactions at “1 Decembrie 1918” University of Alba Iulia (UAB), Romania. Rather the research adopts a corpus-based approach to analyze five authentic communicative situations extracted from institutional digital platforms (Moodle (version 4.3.2; R Core Team, 2023), Microsoft Teams, and institutional email exchanges) between academic staff and students during 2022–2024. The corpus comprises 247 naturally occurring discourse units. Through qualitative and quantitative analysis, the study identifies recurrent patterns of face-threatening acts (FTAs), mitigation strategies, and implicature generation in asynchronous and synchronous digital contexts. The findings reveal that digital mediation creates a distinctive pragmatic register in which participants use compressed politeness strategies, exploit contextual ambiguity, and rely on shared institutional knowledge to convey and decode implicature. Crucially, the study situates its results within the broader framework of the Romanian higher education system, reflecting ongoing tensions between hierarchical academic culture and digitalization imperatives introduced in the post-pandemic educational environment. Recommendations for digital communication literacy training at an institutional level are provided. Full article

Health tourism represents a dynamic sector operating at the intersection of medical services, international patient mobility, and tourism development. Despite its growing prominence, the academic literature frequently conflates health tourism with medical and wellness tourism—a conceptual ambiguity that complicates the establishment of robust, sustainable legal frameworks. Addressing this gap, the present paper conceptualizes health tourism as an overarching framework that encompasses recovery, wellness, and medical sub-sectors. Within this comprehensive paradigm, we explore the contemporary landscape of health tourism in Northern Cyprus through a stakeholder-driven qualitative lens. Utilizing a qualitative case study design, data were gathered via semi-structured interviews with 40 key respondents representing healthcare, travel, public administration, academia, and related professional domains, and subsequently subjected to thematic analysis using NVivo 15 software. The findings reveal that the sector in Northern Cyprus is heavily skewed toward medical tourism, with a concentrated focus on in vitro fertilization (IVF), cosmetic surgery, dental care, and bariatric procedures. Conversely, wellness and rehabilitation tourism remain largely untapped strategic niches. The analysis further indicates that sectoral growth is constrained by structural bottlenecks, including fragmented governance, limited international recognition, transport and accessibility barriers, inadequate accreditation systems, lack of stakeholder synergy, and ethical concerns regarding advertising and patient safety. Moving beyond standard environmental sustainability, this research underscores that long-term destination resilience requires ethical governance, clinical quality controls, patient-rights advocacy, transparent legal frameworks, and community-level economic integration. Ultimately, this study proposes an integrated, stakeholder-centric paradigm tailored to the unique socio-political and structural realities of Northern Cyprus, offering actionable policy recommendations that enrich the discourse on sustainable medical tourism from a small-island perspective. Full article

In the context of the influx of about 1 million displaced Rohingya people from Myanmar into the Cox’s Bazar District of Bangladesh in 2017, it is critical to examine their impacts on the sustainability of the social–ecological system in host Bangladesh. The specific objectives of the study are to assess the nature of intergroup conflicts between the resettled and host communities, the emerging threats posed by resettlement to social–ecological sustainability, and the adaptation and resilience of both communities. A Case Study approach was adopted in the Rohingya resettlement area of Ukhia Upazila of Cox’s Bazar District, Bangladesh. Primary data were collected through Key Informant Interviews, Focus Group Discussions, and oral history conversations. The findings reveal that the average population density in the Rohingya refugee camps is 20 m² per person, whereas the international guideline for refugee camp population density is 30–45 m²/person. The sudden Rohingya population influx has resulted in considerable land cover change, livelihood competition, and deteriorated security conditions. Between 2015 and 2023, a rapid decline in the extent of dense forest was observed—from 93 sq km to 63 sq km. The sense of land loss among the host community created a resentment towards the resettled Rohingyas that turned into social conflicts and unrest. Despite these damages, socioeconomic evolution, the implementation of adaptive measures, and successful restoration programs by the relevant institutions have revealed some degree of community resilience. An inclusive development planning strategy is recommended to sustain livelihood opportunities for both communities and local social–ecological systems. Full article

Pathology is foundational to biomarker-driven and translational oncology research, yet systemic barriers limit full pathology engagement in Canadian cancer clinical trials, compromising the tissue-based questions such trials are designed to answer. This commentary and white paper synthesizes the perspectives of a national pathology working group convened at the 2025 Canadian Cancer Trials Group (CCTG) Annual General Meeting with a descriptive internal audit of the CCTG Tumour Tissue Data Repository (TTDR), in which biospecimen attrition was tabulated at the patient level by disease site; no inferential testing was performed. The TTDR data revealed substantial attrition across disease sites, with no tissue submitted for 32–44% of patients and slides submitted in place of formalin-fixed paraffin-embedded blocks for up to 51% of cases, reflecting persistent misalignment between protocol expectations and laboratory capacity. From these observations, five interrelated gaps were identified—in trial design, funding and resourcing, digital pathology infrastructure, academic recognition, and knowledge translation around consent and ethics governance. Five corresponding strategies are proposed to align research demands with pathology capacity, reduce attrition, and strengthen biomarker-driven trials. As a consensus- and experience-driven analysis rather than a systematic review, these recommendations are intended to frame a national conversation and a starting point for prospective evaluation. Full article

Methamphetamine presents a significant scientific and legal challenge for sentencing because, although it is a Class A drug in England and Wales, it is not assigned explicit indicative quantity thresholds within the principal Sentencing Council guideline. This review provides a comparative expert synthesis of methamphetamine in relation to amphetamine, cocaine and heroin, with particular emphasis on pharmacodynamics, pharmacokinetics, route-specific harms, fatal toxicity indicators and broader patterns of individual-harm profiles. The analysis draws on human laboratory studies, neuroimaging, pharmacokinetic investigations, toxicological literature, drug-related mortality data and policy sources to assess where methamphetamine most appropriately sits within a harm-based sentencing framework. The evidence indicates that methamphetamine is pharmacologically closest to amphetamine, sharing core monoaminergic mechanisms of transporter-mediated neurotransmitter release and vesicular disruption, but differing across several pharmacokinetic and toxicity-related parameters. Compared with amphetamine, methamphetamine shows greater lipid solubility, more efficient central nervous system penetration, longer persistence, and exposure that may, under common high-intensity routes of use, be associated with higher risk of neuropsychiatric, cardiovascular and cerebrovascular harms. Smoked methamphetamine in particular achieves high systemic bioavailability and rapid onset, creating a pattern of exposure more severe than conventional amphetamine preparations and, in some practical respects, closer to high-intensity stimulant models such as crack cocaine. Contemporary evidence further indicates that methamphetamine is associated with higher fatal toxicity than amphetamine, although the magnitude of difference varies by endpoint and no single universal gram-for-gram conversion is supported or recommended. Overall, the literature does not justify treating methamphetamine as simply equivalent to amphetamine, nor does it support conflating it fully with heroin or crack cocaine. The most defensible interpretation is that amphetamine should remain the primary scientific comparator, but with upward adjustment to reflect methamphetamine’s greater persistence and toxicity-related burden, while cocaine may serve as a secondary comparator for proportionality within the Class A sentencing framework. Taken together, the evidence supports consideration of an upward-adjusted amphetamine-based interpretation rather than an unadjusted amphetamine analogue. Full article

This paper examines the trustworthiness of generative AI as a tourism recommender system by analyzing how ChatGPT5.2 responds to an open-ended, zero-shot prompt: “Recommend me a list of 10 German Christmas Markets.” Using German Christmas markets as a case study, outputs, texts in reasoning panels, and cited sources of fifteen replicates (carried out over five consecutive days) were systematically documented and analyzed. The results show a consistent and patterned selection which is dominated by a small canon of markets (Nürnberg, Dresden, Köln, München, and Stuttgart). The generative AI model does not neutrally sample from the entire pool of approximately 2000 German markets but instead reproduces a narrow canon of “iconic” destinations. Analysis of reasoning traces and follow-up conversations demonstrates that ChatGPT5.2 applies hidden selection criteria, including canonical status, landmark setting, branding strength, and perceived trip-planning usefulness, while also introducing undisclosed filters such as geographic spread across Germany and stylistic diversity. Although the model claims to use source triangulation and quality checks, the evidence shows substantial reliance on tourism marketing pages, travel media, blogs, and social media, especially for descriptive commentary. The study concludes that generative AI tourism recommendations are useful but non-neutral and should be interpreted as “curated,” bias-bearing constructs rather than transparent information retrieval. The implications of this on tourism management and the marketing of Christmas markets are discussed. Full article

Background: Artificial Intelligence (AI) and Machine Learning (ML) technologies, such as conversational agents, are becoming increasingly essential tools across multiple industries, particularly in healthcare. This paper presents a scoping review (PRISMA-ScR) of conversational agents (CAs) in mobile health coaching systems (MHCS). It examines existing applications of MHCS, focusing on development strategies, usage contexts, impacts on users, benefits, and research gaps, emphasizing the ability of explainable artificial intelligence (XAI) in making health guidance and decision-support recommendations transparent, trustworthy, and interpretable, if properly integrated. This scoping review identifies opportunities to maximize the use of conversational agents, explainable AI, and mobile technologies to make mobile health coaching systems more accessible and trustworthy, as well as further research gaps worth exploring. Objective: This scoping review maps the evidence on CAs and XAI-enabled technologies in MHCS, identifies trust-related design criteria, categorizes reported outcomes, and highlights opportunities for explainable conversational agents (XCA) in a mobile health context, especially in tackling general medical conditions pertinent in underserved settings. Eligibility criteria: Reported eligible resources evaluated, designed, or conceptually analyzed existing CAs, XAI techniques, and MHCS, AI-supported medical dialogue systems, e-coaching systems, and mobile health applications. We considered sources only relevant to healthcare, health coaching, trust, explainability, or patient engagement that were published between 2006 and 2025. Sources of Evidence: Searches were conducted in IEEE Xplore, Google Scholar, Springer, ScienceDirect/Elsevier, ProQuest, and ACM Digital Library, supplemented by targeted web searches and backward citation checks. Charting methods: Data were charted by system type, communication mode, health context, operational mode, technology used, XAI/trust features, degree of automation, study designs and outcome classification. We applied a revised outcome classification: generated desired outcome (GDO) and partially generated desired outcome (P-GDO), and did not generate desired outcome (DN-GDO). Results: A total of 201 resources were collected. Charted studies clustered around CAs in health, MHCS for chronic diseases and stress management, XAI methods such as LIME, SHAP, Prospector, and counterfactual explanations, and trust-related elements such as voice quality, communication style, appearance, social intelligence, privacy, and performance quality. Most health CAs and MHCS addressed chronic diseases, mental health, or behavior change; fewer addressed general medical diagnosis or autonomous mobile-based primary care support. Conclusions: Existing evidence suggests that CAs and MHCSs can support engagement, coaching, education, and selected decision-support tasks, but evidence for safe, autonomous, explainable general practice functionality remains limited. Future work should prioritize clinically supervised XCA designs, core safety assessment, interfaces with transparent explanation, data protection, culturally and linguistically responsive implementation, and future-oriented review in underserved mobile health settings. Full article

Real-time visual recognition systems integrated with culturally adaptive reasoning are urgently demanded in globalized culinary scenarios. An agent-oriented framework, Agent-based Gastronomy Recommender Enhanced Engine with YOLO (AGREE-YOLO), is proposed in this study, which integrates an optimized lightweight YOLOv13 detector and vision language model (VLM)-driven agents for cross-cultural seafood recipe recommendation. The improved YOLOv13 is equipped with group shuffle convolution (GSConv) modules and Wise-IoU (WIoU) loss, which is validated on a refined underwater seafood dataset targeting sea cucumbers, sea urchins and scallops. It achieves 91.2% precision and 87.3% recall, with 3.9% and 4.2% increments over the baseline model, and maintains 2.0 ms inference speed. Detection outputs are structured and stored in a MySQL database, and a novel ChatFlow pipeline is constructed in the Dify platform to support natural language database querying. VLM-powered agents retrieve structured data and generate culturally tailored recipes and dish images automatically. Operational validation verifies that the end-to-end pipeline realizes seamless conversion from seafood images to personalized cross-cultural recommendations. This work provides an integrated solution for intelligent, culturally adaptive gastronomy in food informatics. Full article

Acorn flours from the six Mediterranean Quercus species (Quercus cerris, Quercus petraea, Quercus robur, Quercus ilex, Quercus pubescens, and Quercus rotundifolia) were systematically fractionated for polyphenols using ultrasonic-assisted extraction with seven solvent systems varying in polarity and composition (water at 20 and 40 min; acetone, ethanol, and methanol at 20% and/or 70% v/v). The total polyphenol content (TPC), non-tannic phenolic content (NTPC), tannin content (TC), antioxidant potential (DPPH, ABTS, and FRAP), and individual phenolic profiles through high-performance liquid chromatography (HPLC) were determined. The results showed that the botanical species primarily determined the TPC and TC, while the solvent composition significantly influenced the NTPC yield. Q. cerris yielded the highest average TPC (105.1 ± 3.8 mg GAE/g) and TC, supported by a gallotannin-dominated profile. Conversely, Q. rotundifolia exhibited the lowest values but the highest NTPC/TPC ratio (32.0%). Q. ilex featured species-exclusive ellagitannins, while Q. pubescens showed the highest specific antioxidant activity. For the targeted recovery, 20% acetone is recommended for tannins and 70% ethanol for the non-tannic fractions. These findings establish a species-resolved framework for valorizing acorn flours as functional ingredients, identifying high-tannin species requiring detannification and “sweet” varieties suitable for direct food application. Full article

Background: Effective communication with patients is vital for improving health outcomes in chronic disease management. In this study, we investigated WoundScribeAI’s Scribe AI, also known as Ambient Technology, and its patient education and engagement app, Pingoo.AI. It employed a multi-agent AI model that leveraged Large Language Models (LLMs) and NotebookLM to enhance patient communication in clinical settings. Methods: The system comprised specialized agents that transcribed healthcare provider–patient conversations through ambient dictation. This transcription generated medical notes that followed the Subjective, Objective, Assessment, and Plan (SOAP) format—a structured document used by healthcare providers to record and communicate information about patient encounters. Simultaneously, comprehensive visit summaries were also created. In the next step, these visit summaries were used to produce conversational and educational content by leveraging NotebookLM, an AI model introduced by Google that can generate podcast-style conversations from provided information. Integrating these agents allows clinicians to deliver engaging, empathetic, and actionable information to patients. Medical experts conducted a two-phase evaluation of the system’s performance based on multiple criteria, with a particular focus on diabetes education and diabetic foot care. The first phase used pre-recorded training videos, while the second phase involved simulated consultations by clinicians using the system. To validate the AI-generated educational content, we used several established frameworks in health communication that closely align with our enhancement goals. Results: The results showed that the AI model generated accurate clinical documentation and met the criteria for accurate SOAP Notes, visit summaries, and engaging educational content for patients. Given that hallucination is a significant concern related to large language models, especially in critical fields like healthcare, we meticulously analyzed the generated outputs to identify any signs of hallucinated information. Three outcomes successfully passed the validation criteria, including accuracy, completeness, comprehensiveness, absence of potential harm, and no hallucination. Additionally, the Conversational Education content was confirmed against established patient education frameworks and met criteria such as the use of metaphors, empathetic tone, and appropriate language, providing additional detail to help manage the condition. Conclusions: By providing specific instructions and prompts to NotebookLM to transform visit summaries into educational conversations, we significantly enhanced the comprehensiveness and engagement of the content for patients. In contrast to a traditional summary of the clinical visit, the podcast-style conversation enriched the content with background information, encouraging language, an empathetic tone, and helpful metaphors. Our analysis confirmed that the system did not exhibit any hallucinations, highlighting the effectiveness of our approach in mitigating this risk. These findings support the use of multi-agent AI models, combined with ambient dictation and tools like NotebookLM, to improve patient communication that surpasses traditional paper-based brochures, which are often impersonal, minimal, and do not always adhere to recommended factors for health literacy. Full article