Clinical application of large language models in sleep medicine

The integration of large language models (LLMs) into healthcare has heralded a new era of digital transformation, particularly given the diverse and rapidly evolving landscape of both proprietary and open-source LLM architectures. Since the emergence of ChatGPT and its contemporaries, there has been an exponential growth in LLM adoption across key sectors, with healthcare at the forefront of this revolution. LLMs are streamlining clinical documentation, enhancing decision support, enabling research synthesis, and supporting education, fundamentally reshaping workflows and the delivery of care. Recent studies have demonstrated their ability to convert unstructured clinical data into structured, actionable insights and to assist in evidence-based treatment planning. However, the application of these technologies to specialized fields, such as sleep medicine, remains at an early but promising stage.In sleep medicine, LLMs are emerging as partners in diagnostic evaluation, patient education, and the interpretation of complex sleep study data. Preliminary research indicates that their diagnostic capacities are beginning to approach those of experienced clinicians, opening avenues for broader patient engagement and workflow standardization. Despite these advancements, significant questions remain regarding the robustness of model validation, the nuances of clinical integration, generalizability across varied populations, longitudinal patient management, and the establishment of robust ethical frameworks. Ongoing debates also highlight the necessity of transparent benchmarking, continuous monitoring, and responsible deployment of these technologies in real-world settings.This Research Topic aims to unify leading academic researchers, clinicians, industry innovators, and stakeholders to address existing knowledge gaps and chart a thoughtful path forward for LLM adoption within sleep medicine. The objective is to generate and disseminate rigorous, methodologically sound research on the application, outcomes, and ethical dimensions of LLM use in this specialty — with emphasis on fostering a dialogue that will deepen understanding, encourage safe innovation, and shape the future of digital health in sleep medicine.This Research Topic in sleep medicine will consider studies centered on methodological, clinical, and applied research within defined boundaries. We are particularly interested in contributions that address cross-disciplinary applications while maintaining a focus on real-world clinical and research practice. To gather further insights in these domains, we welcome articles detailing, but not limited to, the following themes:o Diagnostic and therapeutic performance of LLMs in sleep medicineo Integration of LLMs into clinical workflows (including EHR compatibility and efficiency gains)o LLMs in clinical decision support, patient education, and research applicationso Automated generation of clinical documentation and sleep study reportso Agentic LLMs, multi-agent cooperation, and task delegation in sleep careo Ethical, regulatory, and implementation considerations for LLM deployment in sleep medicineo Generalizability, validation, and longitudinal patient characterization using LLMsTopic Editor Dr. Ambrose Chiang received financial support from Belun Technology Company Limited and NightWare. The other Topic Editors declare no competing interests with regard to the Research Topic subject. Topic editors: Ambrose A Chiang, Haoqi Sun, Joseph Cheung, Steven Holfinger Source: https://www.frontiersin.org/research-topics/79562/clinical-application-of-large-language-models-in-sleep-medicine