GENERATIVE ARTIFICIAL INTELLIGENCE AND LARGE LANGUAGE MODELS IN EMERGENCY MEDICINE: A NARRATIVE REVIEW

Innovative technologies

Innovative Technologies

It is concluded that while generative AI holds transformative potential to reduce clerical burden and augment clinical reasoning, its successful deployment in emergency medicine requires rigorous attention to clinical safety, health equity, workflow integration, and human‑factors considerations.

Artificial intelligence in mental health: A narrative review of applications, benefits, and ethical challenges

Artificial intelligence (AI) is transforming mental health care by enabling novel approaches to assessment, outcome prediction, and treatment. However, the rapid growth of AI tools has outpaced evidence synthesis on their realworld clinical value, implementation barriers, and ethical risks, leaving clinicians and policymakers without clear guidance for responsible integration. This narrative review aimed to examine current AI applications in mental health care, identify their clinical benefits, implementation barriers, and ethical challenges, and define conditions for responsible integration that preserve the patient-clinician relationship. A structured literature search of PubMed, PsycINFO, and Scopus was conducted for peer reviewed English language articles published between January 2019 and March 2026. Studies addressing AI applications, benefits, implementation, or ethics in mental health were included and synthesised narratively into thematic categories. The review found that AI tools—for example, selfreferral chatbots that reduced waiting times and increased treatment uptake—provide expanded 24/7 access, improved clinical efficiency, and potential for individualised personalisation. Predictive models showed promise for treatment selection and risk stratification, while natural language processing unlocked unstructured clinical data. However, concerns included patient data privacy, algorithmic bias that may worsen existing inequities, potential erosion of the therapeutic relationship, and mixed acceptance among clinicians and patients. Many AI applications remain experimental, and regulatory frameworks have not kept pace with technological developments. This review did not include formal quality appraisal or quantitative synthesis; the evidence is limited by short followup periods, high dropout in chatbot trials, and a predominance of studies from highincome countries. Future research should employ longitudinal, codesigned, mixedmethods designs and pragmatic trials that evaluate clinical outcomes alongside equity, user trust, and the preservation of empathic, humanled care—rather than relying solely on uncontrolled implementation studies. AI should be responsibly integrated to augment, not replace, the clinical workforce. Successful application requires a balance between technological advancement, patient protection, and preservation of the patient-clinician relationship.

Large language models in sports cardiology: Challenges, governance, and human-in-the-loop integration.

BACKGROUND Large language models (LLMs) are increasingly integrated into clinical artificial intelligence (AI) workflows, with emerging applications in medical documentation, information synthesis, guideline retrieval, and patient communication. Recent advances in foundation models, including multimodal systems, have further expanded these capabilities. However, current evidence derives predominantly from examination-style benchmarks, retrospective vignettes, and hospital-based populations, limiting its direct applicability to athlete-centered cardiovascular care. Sports cardiology represents a uniquely challenging environment for AI because of low disease prevalence, physiological-pathological overlap, longitudinal uncertainty, and eligibility-driven decision-making. MAIN BODY This narrative review critically examines the conceptual, technical, regulatory, and governance challenges associated with LLM deployment in sports cardiology. We argue that current evaluation paradigms inadequately capture the uncertainty-intensive nature of athlete cardiovascular assessment and propose the text-proxy paradigm, a governance-oriented framework in which LLMs operate as semantic integration layers that process clinician-verified and structured outputs generated by validated upstream systems rather than directly interpreting physiological signals. Within this architecture, LLMs may support documentation, longitudinal synthesis, guideline retrieval, contextual reasoning, and athlete communication under continuous human oversight. We further discuss uncertainty propagation across layered AI systems, workflow-oriented validation, regulatory implications, and a staged framework for responsible clinical implementation. CONCLUSION Future progress will depend less on increasingly capable models than on trustworthy clinical ecosystems that prioritize governance, calibration, transparency, auditability, and clinician oversight. Rather than serving as an early adopter of autonomous AI, sports cardiology may provide a benchmark for the responsible integration of foundation models into high-stakes clinical medicine.

Large Language Models and Medical AI Systems for Healthcare Diagnosis: A Systematic Review

Although promising, LLM-based systems are not yet reliable enough for autonomous medical diagnosis, and multiple recommendations for future research are contained to ensure a high level of safety, transparency, and clinical applicability for LLMs and other AI/ML-related technologies and devices.

Generative large language models in medicine: a scoping review of recent methodological advances

Generative large language models (LLMs) are rapidly transforming medicine, demonstrating unprecedented capability across a broad spectrum of clinical and biomedical tasks. While prior literature has extensively investigated their applications, the methodological foundation underpinning these models remains comparatively underexamined. In this review, we provide a mechanically grounded analysis of recent methodological advances shaping the development and deployment of generative LLMs in healthcare. We categorize the technical landscape into three principal pillars: pretraining, fine-tuning, and prompt engineering, and examine their key architectures, subtypes, and adaptation strategies based on literature published between 2023 and 2025. We further discuss the emerging directions, including efficient model infrastructures and LLMs-powered multi-agent systems, alongside critical challenges related to bias, generalization, and evaluation. By tracing the evolutionary trajectories of these methodologies, this scoping review provides a mechanism-centered framework to inform responsible model development and deployment in medical settings, tailored to task complexity, data characteristics, and resource constraints.