The rapid advancement of artificial intelligence (AI) in healthcare has significantly enhanced diagnostic accuracy and clinical decision-making processes. This review examines four pivotal studies that highlight the integration of large language models (LLMs) and multimodal systems in medical diagnostics. BioBERT demonstrates the efficacy of domain-specific pretraining on biomedical texts, improving performance in tasks such as named entity recognition, relation extraction, and question answering. Med-PaLM, a large-scale language model tailored for clinical question answering, leverages instruction prompt tuning to enhance accuracy and reduce harmful outputs, validated through the MultiMedQA benchmark. DR.KNOWS integrates medical knowledge graphs with LLMs, enhancing diagnostic reasoning and interpretability by grounding model predictions in structured medical knowledge. Medical Multimodal Foundation Models (MMFMs) combine textual and imaging data to improve tasks like segmentation, lesion detection, and automated report generation. These studies demonstrate the importance of domain adaptation, structured knowledge integration, and multimodal data fusion in developing robust and interpretable AI-driven diagnostic tools.

This paper explores the advancements and applications of large‐scale models in the medical field, with a particular focus on Medical Large Models (MedLMs). These models, encompassing Large Language Models (LLMs), Vision Models, 3D Large Models, and Multimodal Models, are revolutionizing healthcare by enhancing disease prediction, diagnostic assistance, personalized treatment planning, and drug discovery. The integration of graph neural networks in medical knowledge graphs and drug discovery highlights the potential of Large Graph Models (LGMs) in understanding complex biomedical relationships. The study also emphasizes the transformative role of Vision‐Language Models (VLMs) and 3D Large Models in medical image analysis, anatomical modeling, and prosthetic design. Despite the challenges, these technologies are setting new benchmarks in medical innovation, improving diagnostic accuracy, and paving the way for personalized healthcare solutions. This paper aims to provide a comprehensive overview of the current state and future directions of large models in medicine, underscoring their significance in advancing global health.

In recent years, advancements in gene structure prediction have been significantly driven by the integration of deep learning technologies into bioinformatics. Transitioning from traditional thermodynamics and comparative genomics methods to modern deep learning-based models such as CDSBERT, DNABERT, RNA-FM, and PlantRNA-FM prediction accuracy and generalization have seen remarkable improvements. These models, leveraging genome sequence data along with secondary and tertiary structure information, have facilitated diverse applications in studying gene functions across animals, plants, and humans. They also hold substantial potential for multi-application in early disease diagnosis, personalized treatment, and genomic evolution research. This review combines traditional gene structure prediction methods with advancements in deep learning, showcasing applications in functional region annotation, protein-RNA interactions, and cross-species genome analysis. It highlights their contributions to animal, plant, and human disease research while exploring future opportunities in cancer mutation prediction, RNA vaccine design, and CRISPR gene editing optimization. The review also emphasizes future directions, such as model refinement, multimodal integration, and global collaboration. By offering a concise overview and forward-looking insights, this article aims to provide a foundational resource and practical guidance for advancing nucleic acid structure prediction research.

In recent years, immune checkpoint inhibitors (ICI) have revolutionized the treatment landscape of renal cell carcinoma (RCC), significantly enhanced patient outcomes and expanded therapeutic options beyond traditional surgical and targeted approaches. In this review, we provide a comprehensive review of the current applications of ICI in RCC therapy, elucidating their mechanisms of action, clinical efficacy across both clear cell and non-clear cell subtypes, and safety profiles. We compare the effectiveness of monotherapy versus combination therapies, demonstrating how synergistic approaches can improve efficacy and durability of responses. Furthermore, we explore the integration of multi-omics technologies, such as single-cell RNA sequencing and spatial transcriptomics, which are pivotal in predicting ICI response and addressing resistance mechanisms. Our discussion also addresses the critical challenges in RCC immunotherapy, including primary and acquired resistance, economic and ethical barriers, and the management of immune-related adverse events. By synthesizing current research and clinical findings, this review aims to provide valuable insights for optimizing RCC immunotherapy, fostering the development of more effective and individualized treatment protocols, and ultimately improving patient survival and quality of life.

Congenital split hand/split foot malformation (SHFM) is a complex congenital disorder with a highly variable clinical presentation and a poorly understood molecular basis, particularly associated with chromosome 10q24 microduplications. This review examines the genetic and molecular mechanisms underlying SHFM, with a focus on the role of microduplications in altering key genes such as FBXW4 and FGF8. It explores the integration of artificial intelligence (AI) in genomic data analysis, protein structure prediction, and protein-protein interaction modeling to enhance our understanding of the condition. Furthermore, the application of AI in optimizing smart biomaterials for personalized treatment strategies and gene editing technologies is discussed, offering novel approaches for regenerative repair. The review highlights how AI and advanced genomic tools can together provide new insights into SHFM's pathology, with potential for transformative clinical applications in diagnosis and treatment.

The rapid advancement of artificial intelligence (AI) and robotics is progressively transforming traditional medical practices. This review highlights the latest developments in the application of AI and robotics in the medical field, exploring their roles in diagnosis, treatment, surgery, nursing, and health management, while also addressing the challenges and future potential they present. By analyzing relevant research findings, this paper aims to provide healthcare professionals and researchers with a comprehensive perspective to better understand this swiftly evolving domain.

With the continuous advancement in tumor research, universal models have emerged as a vital research tool, increasingly recognized for their role in understanding tumor biology, evaluating treatment efficacy, and predicting disease prognosis. This review outlines the applications of universal models in tumor research, highlighting their significance in elucidating tumorigenesis mechanisms, drug development, personalized therapy, and clinical trials. Furthermore, it addresses the current challenges faced by universal models and explores future development directions, offering researchers new perspectives and insights.

The rapid advancement of artificial intelligence (AI) technologies, particularly the emergence of large models, has ushered in unprecedented opportunities within the medical field. The application of open-source large models enables more efficient utilization of data in medical research and clinical practice, enhancing the precision of diagnosis and treatment. This review outlines the current status of AI large models in medicine, exploring their potential in disease prediction, image analysis, and personalized treatment. Furthermore, it analyzes the challenges faced by these technologies and discusses future development directions, emphasizing the need for improved methodologies and collaborative efforts to maximize their impact on healthcare.

AlphaFold is a deep learning-based protein structure prediction tool with immense potential in biomedical research. This paper aims to explore the multifaceted applications of AlphaFold in the medical field, including its roles in protein structure prediction, elucidation of disease mechanisms, and drug discovery. By analyzing current research advancements, this review will demonstrate how AlphaFold is accelerating the drug development process and discuss its prospects in personalized and precision medicine. The integration of AlphaFold's capabilities into various aspects of medical research not only enhances our understanding of protein functions but also paves the way for innovative therapeutic strategies.