Perioperative pain management remains challenging, as inadequate analgesia may delay recovery and increase opioid exposure. Multidisciplinary pain management (MPM) emphasizes multimodal and collaborative strategies, creating opportunities for integrating non-pharmacological interventions. Acupuncture anesthesia (AA), derived from traditional Chinese medicine, has re-emerged as a potential adjunct in perioperative care through modulation of nociceptive transmission, stress responses, and opioid requirements. This review summarizes the historical development, proposed neuroimmune mechanisms, and current clinical applications of AA in modern perioperative settings. Evidence from randomized controlled trials and meta-analyses suggests that AA may reduce postoperative pain scores, opioid consumption, and postoperative nausea and vomiting, and facilitate recovery in selected procedures. Moderate-level evidence supports its adjunctive role in gastrointestinal, orthopedic, and gynecological surgeries, whereas evidence in thoracic, cardiac, and highly invasive procedures remains limited and inconsistent. Critically, current evidence is constrained by small sample sizes, heterogeneous acupuncture protocols, inadequate blinding, regional concentration of studies, and insufficient long-term outcome reporting. These limitations reduce external validity and hinder guideline-level recommendations. Overall, AA shows promise as part of MPM pathways, particularly in enhanced recovery protocols, but standardized intervention protocols and large multicenter high-quality trials are needed before broader implementation in perioperative anesthesia practice.

Cycloastragenol, a key bioactive compound extracted from Astragalus membranaceus, has attracted increasing attention for its therapeutic potential in anti-aging, cancer treatment, and fibrosis prevention. This review summarizes the pharmacological activities of Cycloastragenol at molecular, cellular, and systemic levels, and discusses its efficacy across various disease models and potential perioperative applications. Current evidence demonstrates that Cycloastragenol exerts dose-dependent therapeutic efficacy through specific molecular targets. However, its clinical translation remains limited, particularly in surgical recovery contexts, underscoring the need for further validation through well-designed clinical trials focused on perioperative outcomes.

Sepsis is typically initiated by bacterial infection and the associated immune dysregulation displays a complex, dynamic biphasic immune response characterized by hyperinflammation followed by immunosuppression. In the initial period, pathogens activate the innate immune system through receptors such as Toll-like receptors (TLRs) and NOD-like receptors (NLRs), resulting in the massive release of cytokines, including IL-1β, IL-6, and IFN-γ, thereby initiating a "cytokine storm" that leads to vascular endothelial damage, complement activation, and the induction of abnormal cellular aggregation. Sustained activation of inflammatory signals initiates inflammasome-mediated cell death, including pyroptosis-apoptosis-necroptosis (PANoptosis), leading to systemic inflammation and organ dysfunction. Later, the host develops an immunosuppressive phase characterized by increased anti-inflammatory mediators (e.g., IL-10 and TGF-β), exhaustion of B, T, and NK cells, and immune checkpoint-mediated immune paralysis. The stepwise progression of these two stages suggests that sepsis is not simply a consequence of uncontrolled inflammation but rather reflects immune system reprogramming. A better understanding of the molecular basis of inflammation and immunosuppression, particularly the crosstalk among cell death pathways, metabolic reprogramming, and immune regulation, may facilitate timely precision interventions and the restoration of host immune homeostasis in sepsis.

The challenge facing medical research is not only information overload but also the disconnects among evidence, questions, research, implementation, and replication. Research agents can call external tools, integrate multi-source information, and perform multistep tasks, but they may likewise amplify fabricated citations, confirmation bias, version drift, and unauthorized actions into systemic research errors. Existing evaluations of medical artificial intelligence have mostly focused on simulated tasks, and rigorously defined agents remain understudied; there is also a lack of unified definitions, comparable endpoints, and prospective validation pathways for treating research agents as complex research interventions. Accordingly, this article proposes a falsifiable proposition: research agents should be evaluated under prespecified research quality standards by whether they increase reproducible net research benefit without increasing the risk of serious research errors. TRACE-Med organizes the workflow into five stages—Track (evidence tracing), Refine (question refinement), Architect (research architecting), Coordinate (coordinated implementation), and Evaluate (validation and replication)—and uses evidence provenance, prespecification, separation of privileges, and independent reruns as putative mechanisms of action. Clinical implications: This article positions the minimum implementable research unit, Valid and Reproducible Research Gain (VRRG), and Agent-Induced Research Error Rate (AIRER) as candidate components for future evaluation of the implementation effects of research agents, rather than as validated scales or efficacy endpoints. Current evidence supports controlled augmentation, not unsupervised replacement; next steps should employ blinded outcome adjudication, randomized or crossover task designs, multicenter implementation studies, and independent replication to test whether the framework produces net benefit.

Key Words: research agents; clinical research; reproducibility; artificial intelligence governance; open science; TRACE-Med

The key issue in using generative artificial intelligence in medical education (AI-on) is not whether models can complete tasks, but whether learners can retain and transfer clinical competence after AI is withdrawn (AI-off), while recognizing and controlling AI-induced unsafe reasoning. However, existing studies have focused mainly on AI-enabled immediate knowledge, skills, and satisfaction, whereas reports on AI-off transfer ability and changes in patient-related outcomes remain scarce. Therefore, based on narrative evidence syntheses published before July 2026, this article proposes the dual-competency agentic medical education (DC-AME) framework. The framework consists of two complementary competencies: AI-off independent clinical competence and AI-on safe human–AI collaboration competence, organized into a closed loop comprising learner diagnosis, contextual simulation, scaffolding fading, and transfer validation. Built on shared cases, competency objectives, and an evidence base, intelligent tutors, virtual patients, and clinical reasoning agents jointly support a minimal training unit of “AI-off independent answering—AI-on assisted reflection—AI-off transfer to unseen cases.” Nevertheless, DC-AME remains a design proposition awaiting validation. Future studies may designate delayed transfer after AI-off and the recognition and control of AI-induced unsafe reasoning as co-primary outcomes, and list AI reliance, transfer gap, and performance after scaffold withdrawal as exploratory indicators; ultimately, the value of DC-AME should be evaluated in practice.

Medical artificial intelligence is evolving from single-task prediction models and generative assistants into agents capable of perceiving the environment, decomposing goals, invoking tools, coordinating resources, and tracking outcomes. However, a leap in capability does not equate to a leap in clinical authorization. Existing evidence comes mainly from retrospective data and simulated cases, while real-world, multicenter studies with patient outcomes as endpoints remain scarce. If autonomy is pursued without boundaries, accountability, and operational monitoring, agents may amplify a single model error into continuous harm across processes and institutions. This paper proposes the agentic health system (AHS) framework: under the premises of a clearly defined intended use, action authority, accountable entities, and failure fallback, agents execute a “perceive–prioritize–coordinate–act–learn” loop around patient goals, connecting the three domains of hospital, home, and public health, and shifting healthcare from fragmented services to continuous coordination. This paper further proposes four levels of action authority, a minimum implementation unit, a four-stage translation pathway, two anchor endpoints—system safety and system benefit—and the SCORE evaluation framework. The maturity criterion for AHS is not the number of automated tasks, but whether appropriate care can be delivered at the appropriate time, in the appropriate place, and under appropriate supervision, while improving safety, continuity, operational value, resilience, and equity. The endpoint of hospital agents should not be the “unmanned hospital,” but rather a supervised autonomous healthcare system that is professional-led, patient-engaged, machine-auditable, and accountability-traceable.

Medical artificial intelligence (AI) is evolving from algorithms that perform isolated predictive tasks into medical agents capable of continuously perceiving clinical context, decomposing goals, invoking tools, coordinating communication, and tracking outcomes. This transition shifts the central clinical question from whether AI can replace physicians to how patients, physicians, agents, and healthcare institutions can jointly form judgments, authorise actions, and assume responsibility for their consequences. Existing evidence indicates that large language models (LLMs) can perform strongly in medical question answering, differential diagnosis, and management reasoning. Yet “a model outperforms a human” does not mean that “a human–AI team outperforms a human alone”: randomised trials and imaging studies have exposed systemic risks arising from interaction design, automation bias, error amplification, diffusion of responsibility, and erosion of professional competence. We propose the Symbiotic Clinical Compact (SCC), comprising four interrelated commitments—shared intelligence, bounded action, patient co-governance, and traceable accountability—to define the rights, authority, and responsibilities of patients, physicians, agents, and healthcare systems. We further introduce the FADA clinical loop—Frame, Analyse, Deliberate, and Authorise—together with a four-stage translational pathway extending from human review to human–AI symbiotic medicine. Human–AI symbiotic gain (HASG) and symbiosis-related harm (SRH) are proposed as dual-anchor evaluation endpoints. The SCC does not grant agents unrestricted authority to practise medicine. Instead, it embeds task-level autonomy within revocable authorisation, risk stratification, continuous monitoring, and institutional accountability. Future research should move beyond static model validation towards real-world evaluation of integrated human–AI systems, and beyond average accuracy towards patient outcomes, subgroup fairness, relational quality, professional competence, and lifecycle safety. The goal of human–AI symbiotic medicine is to enable agents to manage informational and procedural complexity, physicians to focus on judgment, responsibility, and compassionate care, patients to become genuine partners in medical decision making, and healthcare systems to evolve from episodic service providers into continuously learning, traceable health partners.

Key Words: medical agents; large language models; human–AI collaboration; shared decision making; patient autonomy; clinical governance; traceable accountability; artificial intelligence ethics