Apple Vision Pro harnesses the power of virtual reality and augmented reality to bring about revolutionary transformations and contributions in medical education, clinical diagnosis and treatment, as well as medical management. It drives the advancement and application of metaverse medicine. However, the actual implementation of Apple Vision Pro also entails tackling technical and ethical challenges, including data privacy concerns, security issues, medical liabilities, and legal considerations. This article aims to explore the application of Apple Vision Pro in the metaverse medical scenario, with the hope of promoting the adoption of Apple Vision Pro in the medical field, thereby fostering advancements in medical education, clinical practice, and medical management.

Key Words: Apple Vision Pro; virtual reality; augmented reality; healthcare

Metaverse in medicine forges a novel paradigm of digitized and intelligent healthcare services using AR/VR technology and the Internet of Medical Things (IoMT), transcending the spatial and temporal constraints of conventional medical practice and unveiling significant prospects in medical training, surgical support, and chronic disease management, among others. Concurrently, the ascent of metaverse in medicine poses challenges, including technology dependency, regulatory gaps, and a shortage of skilled professionals, particularly concerning data security and privacy protection. This article scrutinizes the regulatory demands and hurdles associated with digital medical devices, encompassing the oversight of hardware, software applications, and intelligent algorithms, and reviews regulatory strategies for digital health products in leading markets such as the FDA, MDR, and NMPA guidelines. In conclusion, the paper proffers strategic recommendations for businesses to navigate forthcoming regulatory obstacles, underscores the imperative of compliance management, and anticipates the influence of nascent technologies on the trajectory of regulatory evolution. 

Key Words: metaverse in medicine; digital intelligence medical equipment; regulatory policy; data security; personal privacy protection

Objective: Tiny metallic foreign bodies may remain in the human body after accidental ingestion, surgery, or ballistic injury, potentially causing inflammation, tissue damage, and other complications. Although X-ray and CT are widely used for detection and localization, intraoperative motion and workflow constraints may reduce localization accuracy and real-time retrieval efficiency. This study aims to develop a portable multi-frequency electromagnetic excitation circuit to assist the detection and localization of tiny metallic foreign bodies in the human body. Methods: A multi-frequency electromagnetic excitation circuit was designed for balanced-coil eddy-current sensing. The proposed transmitter combines Selective Harmonic Elimination Pulse-Width Modulation (SHE-PWM) with a full-bridge Class-D power amplifier to generate synchronous multi-frequency excitation currents at 50 kHz, 150 kHz, 350 kHz, and 850 kHz. The use of multiple excitation frequencies provides complementary depth sensitivity, in which low-frequency excitation improves penetration depth for deeply embedded targets, while high-frequency excitation enhances the response and spatial resolution of small or superficial objects. Circuit simulations and hardware measurements were conducted to evaluate the time-domain and frequency-domain characteristics of the proposed circuit. Results: Simulation and experimental results showed good agreement with theoretical predictions. The proposed circuit successfully generated synchronous multi-frequency excitation currents with controllable spectral components. The results confirmed that the combination of SHE-PWM and a full-bridge Class-D power amplifier can provide spectrally controllable and energy-efficient excitation suitable for balanced-coil eddy-current sensing. Conclusions: The proposed multi-frequency electromagnetic excitation circuit provides a feasible supplementary solution for tiny metallic foreign-body detection and localization. Its low-cost, portable, and energy-efficient characteristics make it potentially suitable for bedside and intraoperative electromagnetic assistance, especially in scenarios where conventional imaging methods are limited by workflow constraints or real-time localization requirements.

Objective  To systematically review recent advances in artificial intelligence (AI) and multimodal fusion for differentiating benign from malignant pulmonary nodules, with a focus on the theoretical basis, key technologies, clinical utility, and practical boundaries of integrated decision-making based on imaging, clinical data, and blood-based biomarkers. Methods　International guidelines for pulmonary nodule management, classic risk prediction models, recent AI-based imaging studies, multi-omics and liquid biopsy studies, and methodological consensus documents were reviewed. Evidence was synthesized from six perspectives: the significance of multimodal assessment, integration of imaging and clinical variables, synergistic value of blood biomarkers including ctDNA and circulating genetically abnormal cells (CAC), clinical potential of multimodal models, the boundary between decision support and decision replacement, and current challenges with possible solutions. Results　Current pulmonary nodule management still relies primarily on nodule size, volume, density, margin characteristics, growth dynamics, and conventional clinical risk factors such as age, smoking history, and prior malignancy, under the framework of established guidelines and prediction models. However, in subcentimeter nodules, subsolid nodules, multiple nodules, inflammation-related nodules, and intermediate-risk nodules, single-modality imaging features and conventional models remain inadequate in calibration and net clinical benefit. AI-based radiomics, deep learning, and multimodal machine learning can extract high-dimensional CT features beyond human visual recognition and improve risk stratification when combined with clinical variables. Meanwhile, liquid biopsy approaches, including cfDNA/ctDNA methylation, fragmentomics, CAC, and proteomic classifiers, provide additional molecular and cellular evidence for intermediate-risk nodules, thereby helping reduce unnecessary invasive procedures and accelerating precision diagnosis in truly high-risk cases. Nevertheless, real-world implementation remains limited by data heterogeneity, insufficient external validation, lack of assay standardization, high-dimensional low-sample-size issues, and regulatory and reimbursement barriers. Conclusion　The differential diagnosis of pulmonary nodules is evolving from single-modality imaging judgment toward multimodal integrated decision-making based on imaging, clinical data, and biomarkers. At the current stage, AI should be positioned as a decision-support tool rather than a decision-replacement tool. Future practice-changing systems will likely be prospectively validated, interpretable, auditable, guideline-concordant multimodal platforms that can be seamlessly embedded into pulmonary nodule clinics and multidisciplinary workflows.

Key Words: pulmonary nodule; artificial intelligence; multimodal fusion; radiomics; deep learning; cfDNA methylation; circulating genetically abnormal cells; proteomics; decision support

Warm Disease Studies, a core course in traditional Chinese medicine (TCM), integrates physicians' historical experience and theoretical achievements in the prevention and treatment of warm diseases, demonstrating remarkable clinical practical value. Its theoretical system has shown distinct advantages in the management of infectious diseases (e.g., acute epidemics and febrile conditions) in modern times. To meet the demand for versatile military TCM professionals and military medical support, this study addresses the current status and challenges of Warm Disease Studies teaching in military medical academies. Guided by the principle of "synergy between medicine and education, combat-oriented development", a four-dimensional integrated teaching model—encompassing theory, clinical practice, research, and extension—is proposed. This model highlights the characteristics of military medical support and achieves the organic integration of professional education and ideological education.

This paper introduces BAIMGPT 1.0, an AI-powered medical metaverse platform, to democratize early diagnosis of obstructive sleep apnea (OSA) and pulmonary nodules. By integrating virtual care, federated learning, and IoT diagnostics, the platform addresses healthcare disparities in underserved regions while mitigating algorithmic bias and privacy risks through decentralized frameworks. BAIMGPT 1.0 exemplifies a scalable model for equitable chronic disease management, prioritizing inclusivity and ethical AI-metaverse synergy to redefine global healthcare delivery.

Key Words: BAIMGPT 1.0; obstructive sleep apnea; pulmonary nodules; metaverse

As a Chinese indigenous general-purpose large language model, DeepSeek is transforming the medical field with its efficient, low-cost training and reasoning, and localization advantages. This paper explores DeepSeek’s application possibilities in medicine, covering its uses in diagnosis, treatment, data management, patient services, resource optimization, and gene - biotechnology. It also outlines four levels of DeepSeek adoption by medical institutions, addresses challenges like superficial application, user privacy risks, and model hallucinations, and suggests solutions. Looking ahead, as medical knowledge bases grow and model interpretability improves, DeepSeek is set to boost precision medicine and intelligent decision-making, becoming a key driver of medical productivity.

Key Words: DeepSeek; large language model; medicine; enterprise applications

With the rapid development of biomedical engineering technology, assisted rehabilitation exoskeleton robots have emerged as a research hotspot in the field of rehabilitation medicine. We summarize the current research status and scientific progress of assisted rehabilitation exoskeleton robots both domestically and internationally, covering aspects such as design concepts, working principles, main types, technical equipment, and clinical applications. Simultaneously, recognizing that there is still a long journey ahead before they reach maturity, and considering the evolving Internet of Things, the emergence of artificial intelligence and metaverse technology, we explore the potential for integrating these technologies with rehabilitation medicine, thereby presenting new opportunities for the advancement of assisted rehabilitation exoskeleton robots.

Key Words：assisted rehabilitation exoskeleton robot; metaverse in medicine; IOT in medicine; research status; research prospects

The advent of medical robots has transformed the landscape of surgery. Compared to traditional surgical methods, the use of surgical robots provides significant advantages in enhancing precision and reducing the workload for surgeons. However, due to resource constraints, fully automated, end-to-end surgical robots are poised to become a key trend in the development of metaverse medicine. Existing knee surgery robots predominantly operate in a semi-active mode, serving as assistants to surgeons, while a limited number of "fully automated" robots can only achieve full automation during the intraoperative phase. This paper proposes an intelligent knee replacement surgery approach based on digital twin and mixed reality technologies, adopting a model of human pre-operative rehearsal and supervision, machine planning, and robotic execution. This shifts the paradigm from "semi-active" to "semi-automated" (covering the full process), serving as a transitional step toward fully automated end-to-end surgery. By ensuring safety and gaining acceptance from both medical professionals and patients, this approach enables high-quality surgical outcomes. It aligns better with current technological foundations and practical requirements while also offering potential for advancements in quantitative surgical assessment within the realm of metaverse medicine.

Key Words: knee arthroplasty; digital twin; metaverse medicine; surgical robot