Search

Large language models (LLMs) are rapidly advancing medical artificial intelligence, offering revolutionary changes in health care. These models excel in natural language processing (NLP), enhancing clinical support, diagnosis, treatment, and medical research. Breakthroughs, like GPT-4 and BERT (Bidirectional Encoder Representations from Transformer), demonstrate LLMs’ evolution through improved computing power and data. However, their high hardware requirements are being addressed through technological advancements. LLMs are unique in processing multimodal data, thereby improving emergency, elder care, and digital medical procedures. Challenges include ensuring their empirical reliability, addressing ethical and societal implications, especially data privacy, and mitigating biases while maintaining privacy and accountability. The paper emphasizes the need for human-centric, bias-free LLMs for personalized medicine and advocates for equitable development and access. LLMs hold promise for transformative impacts in health care.

Summary: This study systematically reviewed the application of large language models (LLMs) in medicine, analyzing 550 selected studies from a vast literature search. LLMs like ChatGPT transformed healthcare by enhancing diagnostics, medical writing, education, and project management. They assisted in drafting medical documents, creating training simulations, and streamlining research processes. Despite their growing utility in assisted diagnosis and improving doctor-patient communication, challenges persisted, including limitations in contextual understanding and the risk of over-reliance. The surge in LLM-related research indicated a focus on medical writing, diagnostics, and patient communication, but highlighted the need for careful integration, considering validation, ethical concerns, and the balance with traditional medical practice. Future research directions suggested a focus on multimodal LLMs, deeper algorithmic understanding, and ensuring responsible, effective use in healthcare.

Abstract Objective This study aimed to investigate the relationship between the TyG (Triglyceride-glucose index) and the prognosis of patients with HOCM (hypertrophic obstructive cardiomyopathy) without diabetes. Research design and methods A total of 713 eligible patients with HOCM were enrolled in this study and divided into two groups based on treatment: an invasive treatment group (n = 461) and a non-invasive treatment group (n = 252). The patients in both two groups were then divided into three groups based on their TyG index levels. The primary endpoints of this study were Cardiogenic death during long-term follow-up. Kaplan–Meier analysis was used to study the cumulative survival of different groups. Restricted cubic spline was used to model nonlinear relationships between the TyG index and primary endpoints. Myocardial perfusion imaging/Myocardial metabolic imaging examinations were performed to assess glucose metabolism in the ventricular septum of the HOCM patients. Results The follow-up time of this study was 41.47 ± 17.63 months. The results showed that patients with higher TyG index levels had better clinical outcomes (HR, 0.215; 95% CI 0.051,0.902; P = 0.036, invasive treatment group; HR, 0.179; 95% CI 0.063,0.508; P = 0.001, non-invasive treatment group). Further analysis showed that glucose metabolism in the ventricular septum was enhanced in HOCM patients. Conclusions The findings of this study suggest that the TyG index may serve as a potential protective factor for patients with HOCM without diabetes. The enhanced glucose metabolism in the ventricular septum of HOCM patients may provide a potential explanation for the relationship between the TyG index and HOCM prognosis.