Objectives: This study aimed to identify acupoint selection patterns for breast cancer-related pain using the Knowledge Discovery in Databases (KDD) method, construct a data-informed candidate acupoint prescription, and preliminarily evaluate its clinical efficacy when combined with the World Health Organization three-step analgesic ladder. Methods: Databases including China National Knowledge Infrastructure, VIP Information, WanFang, PubMed, and Web of Science were searched from inception to May 2024. An Excel-based dataset was developed to analyze acupoint frequency and meridian attribution. Acupuncture prescriptions for cancer pain without specifying cancer type were retained as potentially informative references for breast cancer-related pain. Sixty eligible patients were randomized into two groups. The control group received standard three-step analgesics, including celecoxib, tramadol sustained-release, or oxycodone sustained-release according to pain severity. The intervention group received the same regimen plus a KDD-derived acupuncture prescription consisting of bilateral Hegu (LI4), Zusanli (ST36), Neiguan (PC6), Taichong (LR3), Sanyinjiao (SP6), and Ashi points. Needles were retained for 30 minutes using balanced stimulation, five sessions per week for three weeks. Outcomes included pain intensity, breakthrough pain frequency, duration of pain relief, Karnofsky Performance Status, sleep quality, depressive symptoms, analgesic efficacy, quality of life, and safety. Results: The KDD-derived candidate prescription was associated with a higher overall response rate than analgesics alone. Patients receiving adjunctive acupuncture showed greater reductions in pain intensity and breakthrough pain episodes, as well as improvements in functional status, sleep quality, and depressive symptoms. Fewer adverse events were reported in the acupuncture group. Conclusions: This study proposes a potential acupoint combination for relieving breast cancer-related pain based on distal meridian points and local tender points. Combined acupuncture and conventional pharmacotherapy may improve analgesic outcomes, quality of life, and psychological status, with a favorable safety profile.

In contrast to conventional oximeters, near-infrared spectroscopy-based brain tissue oximetry monitoring devices are capable of non-invasive, continuous, and real-time quantitative monitoring of cerebral oximetry parameters. Initially, these devices were utilized for intensive care or surgical monitoring of oxygen saturation. Due to the rapid advancement of optoelectronic sensing and measurement technologies over the past decade, the derived functional near-infrared brain imaging devices have been widely used in a variety of fields. This paper first introduces the basic principles of near-infrared spectroscopy-based cerebral oxygenation parameter detection, then focuses on the most recent developments in this field of study. Finally, a prospect on their future application in practical settings is also provided.

Medical artificial intelligence is evolving from single-output models into agents capable of maintaining contextual coherence, performing multi-step planning, invoking tools, and initiating or drafting clinical actions. Compared with traditional models, the risk of agents is no longer measured solely by whether a single output is correct; it depends more on how they perform task planning, invoke permissions, write to memory, select tools, and coordinate with the clinical team. Once an error propagates through any of these links, it may translate from a deviation at the level of recommendation into consequences at the level of action. Therefore, evaluation before medical agents enter clinical settings cannot rely only on the model’s own performance metrics; it must cover the complete system formed by the human–agent–workflow. The core question of this paper is: according to the severity of the consequences of medical agent actions, what level of system evidence is required to determine whether an agent can safely enter and continuously operate in clinical settings. Through a narrative review, this study integrates interdisciplinary literature from medical artificial intelligence, human factors engineering, safety engineering, cybersecurity, implementation science, health economics, reporting standards, and regulatory science, and constructs MAAM–MAAE, a risk-adaptive conceptual methodology. We map existing standards to agent-specific attributes and risks and organize unresolved requirements into interconnected R&D and evaluation cycles. It should be noted that this study uses purposive rather than systematic evidence synthesis and has not conducted a formal expert consensus process or prospective validation. Medical Agent Architecture and Maturation (MAAM) divides R&D activities into four domains: clinical mission, system architecture, human–agent collaboration (including action authority), and safety and maturity assurance. At the assessment level, MAAM introduces Medical Agent Assessment and Evaluation (MAAE) to organize evidence across four hierarchical dimensions: capability, safety, human–agent and clinical performance, and health system and full-lifecycle value. The unit of evaluation is the complete human–agent–workflow system. Four risk tiers and five stage gates—the gates are set according to potential harm, the physical proximity of actions to patients, the degree of autonomy, error detectability, and reversibility—so that supervision intensity matches the required level of evidence. In addition, this paper proposes clinical task success (CTS) and clinically consequential unsafe action rate (CCUAR) as dual anchoring metrics; however, their measurement properties and decision thresholds still require empirical testing. MAAM–MAAE transforms clinical authorization from a one-time model validation decision into a version-specific full-lifecycle contract. By incorporating actions, longitudinal operation, change control, and exit mechanisms, this framework complements existing reporting and regulatory frameworks. MAAM–MAAE is a testable proposal, not a validated checklist, reporting guideline, or claim of clinical effectiveness.

Key Words: medical agents; agentic artificial intelligence; clinical evaluation; human–medical agent collaboration; patient safety; full-lifecycle governance; methodology

Sepsis is a systemic inflammatory response syndrome triggered by infection. It presents with simultaneous overactive immune activation and immune paralysis, leading to a cytokine storm, tissue injury, and multiple organ failure. The molecular mechanisms and pathological characteristics of the septic cytokine storm are comprehensively interpreted from multiple perspectives, including immune regulation, signaling pathways, cellular interactions, metabolic state reprogramming, and microcirculatory dysfunction. The cross-activation of signaling pathways, including NF-κB, JAK/STAT, mitogen-activated protein kinase (MAPK), and NLRP3 inflammasome, underlies the core mechanism for the enhancement of the inflammatory response via continued release of proinflammatory cytokines and also is involved in maintaining immune balance. In the latestage immunosuppressive phase, Treg cells, myeloid-derived suppressor cells (MDSCs) and regulatory macrophages play pivotal roles in reestablishing host homeostasis through negative feedback, and their dysfunction is closely associated with secondary infections and high mortality. This review consolidates the latest developments in precision medicine and multidimensional biomarkers, emphasizing the prospective value of several markers such as lactate and CD64, pentraxin 3 (PTX3), and BMP9 for early diagnosis and rognosis evaluation. Moreover, it reviews novel immunomodulators, for instance, bee venom peptides, GDF15, N-(1,3,4-oxadiazol-2-yl) guanidine (NWG), 4-octyl itaconate  (4-OI), and nanoparticle drug delivery systems that inhibit inflammatory signaling cascades, restore energy metabolism, and provide organ protection. Taken together, the pathogenic mechanisms of sepsis are non-linear and dynamic, which may render single-target therapy insufficient for successful management. Personalized interventions targeting multi-target network regulation based on omics and AI models may accomplish precision monitoring and stratified treatment of inflammatory responses, also providing new theoretical and clinical strategies to reduce sepsis-related mortality.

Ultrasound-guided nerve block is a safe and effective regional anesthesia technique; however, accurate identification of the brachial plexus remains challenging due to its small size and low contrast in ultrasound images. Recent advances in deep learning offer promising solutions to enhance brachial plexus segmentation and improve perioperative regional anesthesia precision and safety. This review systematically summarizes current deep learning approaches applied to ultrasound-based brachial plexus segmentation. We highlight key models, including Convolutional Neural Networks, the U-shaped Convolutional Neural Networks and their variants, Mask RegionBased Convolutional Neural Networks, and Generative Adversarial Network-based architectures, and compare their reported performances, with Dice Similarity Coefficients ranging from 0.5865 to 0.882 and Intersection over Union values up to 0.6957. Among them, U-Net remains the most frequently employed due to its balance of accuracy and computational efficiency. Moreover, novel models such as multi-objective brachial plexus segmentation network and BPMSegNet have demonstrated superior segmentation performance by incorporating attention mechanisms and spatial contrast features. Notwithstanding these advancements, challenges persist, particularly limited dataset availability and insufficient model generalization. This review provides a comprehensive overview of recent progress, evaluates comparative performance metrics, and outlines future directions to improve model robustness and clinical applicability and clinical applicability in the perioperative setting.

Key Words: medical agents; trustworthy artificial intelligence; large language models; clinical evaluation; human–machine collaboration; risk stratification; lifecycle governance; patient safety

Screening with low-dose helical computed tomography (LDCT) has substantially reduced lung cancer mortality in high-risk populations, but it has also led to the detection of large numbers of pulmonary nodules that require further risk stratification and long-term follow-up. Existing imaging artificial intelligence (AI) tools have focused primarily on nodule detection or prediction of malignancy risk, and smart reminder tools can reduce missed follow-up in some patients. However, evidence from single AI models has not yet answered whether multi-module medical agents can improve patient-level follow-up outcomes. Therefore, this study aims to determine whether a medical agent equipped with six capabilities—perception, comprehension, prediction, decision-making, execution, and learning—can improve whole-process follow-up management of pulmonary nodules and patient clinical outcomes. BAIMGPT-PN-RWE is a multicenter, prospective, active-controlled real-world study enrolling patients with newly detected nodules. We plan to enroll 6,000 adults with newly detected pulmonary nodules measuring 4– 30 mm from healthcare institutions at different tiers. The primary comparison is between patients who initiate the BAIMGPT six-element closed-loop follow-up management system within 7 days after time zero and those who initiate routine manual follow-up or an existing Internet of Things (IoT)–assisted management system. The follow-up period is 12 months (extended to 24 months in a subset of the cohort). The primary analysis emulates a target trial: propensity score overlap weighting will be used to estimate the average treatment effect in the overlap population; a difference-in-differences approach will be used to assess the effect of the staggered rollout across centers; and marginal structural models will be constructed to control for time-dependent confounding arising from the actual intensity of system use. The primary outcome is the completion rate of guideline-concordant follow-up management during the 12-month follow-up period, i.e., the proportion of patients in whom risk stratification, follow-up planning, follow-up execution, reporting of follow-up results, and next-step decision-making are all completed within prespecified time windows. Key safety endpoints include missed diagnosis of malignant nodules, excessive invasive examinations of benign nodules, failure to escalate follow-up for high-risk nodules, and follow-up delays attributable to the system itself. This study evaluates, in the real world, the value of a six-capability medical agent for follow-up management of patients with pulmonary nodules. Based on the study data, we will further delineate the conditions under which six-element closed-loop medical agents can be generalized, should be restricted, or should be discontinued.

Key Words: pulmonary nodules; medical agents; closed-loop management; real-world evidence; target trial emulation; clinical artificial intelligence

Objective: To compare the efficacy and adverse reactions between 0.15% ropivacaine combined with sufentanil and 0.1% ropivacaine combined with sufentanil for labor analgesia in primiparous women with severe pain. Method: 195 full-term singleton primiparous women with severe pain (visual pain assessment [VAS] ≥6) were randomly allocated to two epidural analgesia groups using different drug formulations. One group received 0.1%  ropivacaine + 0.3 μg/mL sufentanil (control group, n=98). The other group was treated with 0.15% ropivacaine and 0.3 μg/mL sufentanil (experiment group, n=97). The following parameters were recorded: analgesia onset time; maximum VAS scores before analgesia, at 20 min after epidural administration, and during labor; number of analgesic pump presses; number of rescue analgesia events; total analgesic drug consumption; modified Bromage score; maternal satisfaction; duration of labor stages; mode of delivery; neonatal Apgar scores at 1 min and 5 min; and incidence of adverse reactions during labor analgesia, such as skin itching, nausea and vomiting, urinary retention, and fever. Result: The onset time of analgesia in the experimental group was significantly shorter than that in the control group (P<0.05). While the maximum VAS scores in both groups were significantly lower at 20 minutes post-epidural administration and during labor than before delivery analgesia (P<0.05), no statistically significant inter-group differences were observed in VAS scores or in the number of pump compressions, rescue analgesia events, dosage of anesthetic drugs, modified Bromage score, or satisfaction ratings. Similarly, no significant differences were found between the two groups in the duration of labor, mode of delivery, and Apgar scores of newborns at 1 and 5 minutes, or the incidence of pruritus, nausea/vomiting, urinary retention, or intrapartum fever. Conclusion: For primiparous women with severe labor pain, initial use of 0.15% ropivacaine combined with sufentanil significantly shortens the onset time, provides more comprehensive analgesic effects, achieves higher satisfaction, and does not increase short-term adverse reactions (including motor block) compared to the conventional 0.1% concentration regimen.