With the widespread adoption of low-dose CT screening and the extensive application of high-resolution CT, the detection rate of sub-centimeter lung nodules has significantly increased. How to scientifically manage these nodules while avoiding overtreatment and diagnostic delays has become an important clinical issue. Among them, lung nodules with a consolidation tumor ratio less than 0.25, dominated by ground-glass shadows, are particularly worthy of attention. The therapeutic challenge for this group is how to achieve precise and complete resection of nodules during surgery while maximizing the preservation of the patient's lung function. The "watershed topography map" is a new technology based on big data and artificial intelligence algorithms. This method uses Dicom data from conventional dose CT scans, combined with microscopic (22-24 levels) capillary network anatomical watershed features, to generate high-precision simulated natural segmentation planes of lung sub-segments through specific textures and forms. This technology forms fluorescent watershed boundaries on the lung surface, which highly fit the actual lung anatomical structure. By analyzing the adjacent relationship between the nodule and the watershed boundary, real-time, visually accurate positioning of the nodule can be achieved. This innovative technology provides a new solution for the intraoperative positioning and resection of lung nodules. This consensus was led by four major domestic societies, jointly with expert teams in related fields, oriented to clinical practical needs, referring to domestic and foreign guidelines and consensus, and finally formed after multiple rounds of consultation, discussion, and voting. The main content covers the theoretical basis of the "watershed topography map" technology, indications, operation procedures, surgical planning details, and postoperative evaluation standards, aiming to provide scientific guidance and exploration directions for clinical peers who are currently or plan to carry out lung nodule resection using the fluorescent microscope watershed analysis method.

The rapid development of artificial intelligence （AI） technology provides new opportunities for the modernisation of traditional Chinese medicine （TCM） diagnosis. By analysing the foundation， research progress and difficulties of the combination of AI and TCM diagnosis， it is concluded that AI has made remarkable development in intelligence-driven modernization of TCM tongue diagnosis， pulse diagnosis， listening and smelling diagnosis and text processing， and there are useful explorations in the field of constructing data-driven TCM diagnostic model and multidisciplinary integration of TCM diagnostic models. However， the current integration of AI technology in TCM diagnosis still faces many challenges， such as the scarcity and uneven quality of clinical data， the limited ability of AI algorithms to express TCM thinking model of syndrome differentiation and empirical knowledge， and the possible existence of ethical and privacy issues. By systematically sorting out the current research status and development direction of AI-empowered TCM diagnostics， it is proposed to promote the application of AI technology in TCM diagnostics in four aspects， namely， strengthening the construction of TCM big data and talent cultivation， encouraging cross-disciplinary cooperation， improving the legal and ethical framework， and promoting the popularity of the technology in primary care， so as to enhance the modernisation of TCM diagnostics.

Objective: To analyze the chemical constituents of Shanxiangyuanye (Turpiniae Folium) through liquid chromatography-tandem mass spectrometry (LC-MS/MS) method, and to evaluate their anti-oxidant, hypoglycemic, and anti-glycation activities related to diabetic complications. Methods: The supernatant of Shanxiangyuanye (Turpiniae Folium) (TFS), obtained following water extraction and alcohol precipitation, was analyzed by LC-MS/MS. Antioxidant activity of TFS in vitro was evaluated using three experimental approaches: the 1,1-diphenyl-2-picrylhydrazyl (DPPH) radical scavenging assay, the 2,2’-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS+) radical cation decolorization assay, and the hydroxyl (·OH) radical scavenging assay. To comprehensively evaluate hypoglycemic potential, α-glucosidase inhibition was measured to analyze in vitro hypoglycemic activity. Subsequently, in vitro models were developed to examine anti-glycation activity through the bovine serum albumin (BSA)-fructose (Fru), BSA-methylglyoxal (MGO), BSA-glyoxal (GO), and D-arginine (Arg)-MGO systems, with particular attention to the inhibitory effects of TFS. Furthermore, the concentrations of fructosamine, protein carbonyls, sulfhydryl groups, and β-amyloid in the glycation solution were quantified using the BSA-Fru model following 7-d of incubation at 37 °C. Results: Using LC-MS/MS analysis in both positive and negative ion modes, we identified 750 chemical components in TFS, primarily including organic acids, amino acids, and their derivatives. In vitro activity studies demonstrated that TFS exhibited remarkable free radical scavenging capacity, with half-maximal inhibitory concentrations (IC50) of 0.47, 1.56, and 0.36 mg/mL against DPPH, ABTS+, and ·OH radicals, respectively. Regarding hypoglycemic activity, TFS dose-dependently inhibited α-glucosidase activity (IC50 = 0.21 mg/mL), displaying comparable efficacy to the clinical drug acarbose (IC50 = 0.23 mg/mL). Notably, TFS intervened in the glycation process: IC50 values were 0.22, 1.91 – 4.96, and 4.09 mg/mL in the BSA-Fru, BSA-MGO/GO, and Arg-MGO models, respectively, with the most prominent inhibitory effects observed in the BSA-Fru model. Furthermore, although TFS may not effectively preserve thiol groups in BSA or reduce thiol oxidation during glycation, it significantly reduces fructosamine levels (in a dose-dependent manner), decreases β-amyloid formation, and inhibits protein carbonylation (P < 0.000 1). Conclusion The findings demonstrate that TFS exhibits a complex chemical composition with potent antioxidant, hypoglycemic, and anti-glycation activities. These results provide compelling scientific evidence supporting TFS’s potential as a natural adjuvant for diabetes prevention and complication management, while laying a solid foundation for its applications in functional food development and adjunctive antidiabetic therapeutics.

With the widespread use of antimicrobial agents, bacterial drug resistance has become an increasingly severe issue, posing significant challenges to global healthcare. Traditional Chinese medicine (TCM) has emerged as a research focus in the field of bacterial resistance due to its broad sources, high safety profile, low toxicity, and antimicrobial mechanisms distinct from those of chemical drugs. Studies have shown that various TCM herbs, such as Scutellaria baicalensis, exert antibacterial effects through multiple pathways, including disrupting the integrity of bacterial cell walls and membranes, inhibiting nucleic acid and protein synthesis, and impairing energy production and metabolism. Additionally, certain TCM herbs, including Scutellaria baicalensis, Coptis chinensis, and Fritillaria thunbergii, can reverse antimicrobial resistance by eliminating resistant plasmids, inhibiting bacterial efflux pump function, and suppressing β-lactamase activity. TCM holds promising potential for antibacterial applications and synergistically reversing antimicrobial resistance, though systematic analyses remain limited. This review summarizes the mechanisms of antibacterial action of TCM and current research on its synergistic use with antimicrobial agents to reverse drug resistance, aiming to provide insights for developing novel TCM-based antimicrobials and addressing bacterial resistance.

OBJECTIVE To construct ensemble learning models for predicting high-use days of budesonide based on meteorological factors， thereby providing reference for hospital pharmacy management. METHODS Meteorological data for 2024 and outpatient budesonide usage data from the jurisdiction of Sanming Hospital of Integrated Traditional Chinese and Western Medicine were collected. High-use days were defined as the 75th percentile of outpatient budesonide usage， and a corresponding dataset was established. The prediction task was formulated as a classification problem， and three ensemble learning models were developed： Random Forest， Extreme Gradient Boosting （XGBoost）， and Histogram-based Gradient Boosting Classifier. Model performance was evaluated using accuracy， precision， recall， F1-score， and log-loss. Model interpretability was analyzed using Shapley Additive Explanations （SHAP）. RESULTS The Histogram-based Gradient Boosting Classifier achieved the best performance （accuracy＝0.75， F1-score＝0.48）， followed by XGBoost （accuracy＝0.74， F1-score＝0.43） and Random Forest （accuracy＝0.72， F1-score＝0.22）. SHAP results suggested that the prediction results of the last two models have the highest correction. CONCLUSIONS Ensemble learning models can effectively predict high-use days of budesonide， with the Histogram- based Gradient Boosting Classifier demonstrating the best predictive performance. Low temperature， high humidity， and low atmospheric pressure show significant positive impacts on the prediction of daily budesonide usage.

OBJECTIVE: To develop an artificial intelligence-assisted system for the automatic detection of the features of common 21 auricular points based on the YOLOv8 neural network. METHODS: A total of 660 human auricular images from three research centers were collected from June 2019 to February 2024. The rectangle boxes and features of images were annotated using the LabelMe5.3.1 tool and converted them into a format compatible with the YOLO model. Using these data, transfer learning and fine-tuning training were conducted on different scales of pretrained YOLO neural network models. The model's performance was evaluated on validation and test sets, including the mean average precision (mAP) at various thresholds, recall rate (recall), frames per second (FPS) and confusion matrices. Finally, the model was deployed on a local computer, and the real-time detection of human auricular images was conducted using a camera. RESULTS: Five different versions of the YOLOv8 key-point detection model were developed, including YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x. On the validation set, YOLOv8n showed the best performance in terms of speed (225.736 frames per second) and precision (0.998). On the external test set, YOLOv8n achieved the accuracy of 0.991, the sensitivity of 1.0, and the F1 score of 0.995. The localization performance of auricular point features showed the average accuracy of 0.990, the precision of 0.995, and the recall of 0.997 under 50% intersection ration (mAP⁵⁰). CONCLUSION The key-point detection model of 21 common auricular points based on YOLOv8n exhibits the excellent predictive performance, which is capable of rapidly and automatically locating and classifying auricular points.
Humans ; Neural Networks, Computer ; Artificial Intelligence ; Acupuncture Points

OBJECTIVES: To develop a heterogeneous graph prediction method based on the fusion of multi-layer semantics and topological information for addressing the challenges in drug-target interaction prediction, including insufficient modeling of high-order semantic dependencies, lack of adaptive fusion of semantic paths, and over-smoothing of node features. METHODS: A heterogeneous graph network with multiple types of entities such as drugs, proteins, side effects, and diseases was constructed, and graph embedding techniques were used to obtain low-dimensional feature representations. An adaptive metapath search module was introduced to automatically discover semantic path combinations for guiding the propagation of high-order semantic information. A semantic aggregation mechanism integrating multi-head attention was designed to automatically learn the importance of each semantic path based on contextual information and achieve differentiated aggregation and dynamic fusion among paths. A structure-aware gated graph convolutional module was then incorporated to regulate the feature propagation intensity for suppressing redundant information and redcuing over-smoothing. Finally, the potential interactions between drugs and targets were predicted through an inner product operation. RESULTS: Compared with existing drug-target interaction prediction methods, the proposed method achieved an average improvement of 3.4% and 2.4%, 3.0% and 3.8% in terms of the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUPRC) on public datasets, respectively. CONCLUSIONS The drug-target interaction prediction method developed in this study can effectively extract complex high-order semantic and topological information from heterogeneous biological networks, thereby improving the accuracy and stability of drug-target interaction prediction. This method provides technical support and theoretical foundation for precise drug target discovery and targeted treatment of complex diseases.
Semantics ; Humans ; Drug Interactions ; Neural Networks, Computer ; Algorithms

Zebrafish larvae are useful for identifying chemicals against lateral line (LL) hair cell (HC) damage and this type of chemical screen mainly focuses on searching for protectors against cell death. To expand the candidate pool of HC protectors, a self-built acoustic escape response (AER)-detecting system was developed to apply both low-frequency near-field sound transmission and AER image acquisition/processing modules. The device quickly confirmed the changed LL HC functions caused by most known ototoxins, protectors, and neural transmission modifiers, or knockdown of LL HC-expressing genes. With ten devices wired in tandem, five 'hit' chemicals were identified from 124 cyclin-dependent kinase inhibitors to partially restore cisplatin-damaged AER in less than a day. AS2863619, ribociclib, and SU9516 among the hits, protected the HCs in the mouse cochlea. Therefore, using free-swimming larval zebrafish, the self-made AER-detecting device can efficiently identify compounds that are protective against HC damage, including cell death and loss-of-function.
Animals ; Zebrafish ; Hair Cells, Auditory/physiology* ; Lateral Line System/cytology* ; Escape Reaction/physiology* ; Larva ; Mice ; Cisplatin/toxicity* ; Drug Evaluation, Preclinical/methods*

Microglial functions are linked to Ca²⁺ signaling, with endoplasmic reticulum (ER) calcium stores playing a crucial role. Microglial abnormality is a hallmark of Alzheimer's disease (AD), but how ER Ca²⁺ receptors regulate microglial functions under physiological and AD conditions remains unclear. We found reduced ryanodine receptor 2 (Ryr2) expression in microglia from an AD mouse model. Modulation of RyR2 using S107, a RyR-Calstabin stabilizer, blunted spontaneous Ca²⁺ transients in controls and normalized Ca²⁺ transients in AD mice. S107 enhanced ATP-induced migration and phagocytosis while reducing ramification in control microglia; however, these effects were absent in AD microglia. Our findings indicate that RyR2 stabilization promotes an activation state shift in control microglia, a mechanism impaired in AD. These results highlight the role of ER Ca²⁺ receptors in both homeostatic and AD microglia, providing insights into microglial Ca²⁺ malfunctions in AD.
Animals ; Microglia/pathology* ; Alzheimer Disease/pathology* ; Phagocytosis/drug effects* ; Ryanodine Receptor Calcium Release Channel/metabolism* ; Disease Models, Animal ; Mice ; Cell Movement/drug effects* ; Mice, Transgenic ; Calcium Signaling/physiology* ; Calcium/metabolism* ; Mice, Inbred C57BL ; Male ; Endoplasmic Reticulum/metabolism*

Objective: To investigate the association between emotional intelligence and sleep problems at the symptom level among junior and senior high school students, so as to provide new insights for interventions targeting junior and senior high school students sleep disorders. Methods: From November 2023 to May 2024, a stratified cluster random sampling method was employed to select 3 531 first year junior high school and first year senior high school students from 6 schools in Guangyuan City and Liangshan Yi Autonomous Prefecture in Sichuan Province, as well as Lhasa City in Tibet Autonomous Region. The Insomnia Severity Index Scale and the Wong and Law Emotional Intelligence Scale(WLEIS) were used to assess sleep problems and emotional intelligence. A network analysis was performed to explore the relationship between emotional intelligence and sleep disorders, and a gender based network comparison analysis was conducted. Results: The reported rate of sleep problems among junior and senior high school students was 47.3%, with severe sleep problems of 2.2%. Difficulty maintaining sleep, worry about sleep, and emotional application were the core symptoms in the network (node strength values: 1.11, 0.98, and 0.82, respectively). Dissatisfaction with sleep and emotional application served as bridge symptoms connecting emotional intelligence and sleep problems (bridge strength values: 1.77 and 1.59, respectively). The edge weights of the emotional intelligence and sleep problems network differed significantly between genders (maximum difference in edge weight values was 0.13， P <0.05). Conclusions Emotional application ability and dissatisfaction with sleep are the key nodes in the network connecting emotional intelligence and sleep problems. Targeted efforts to enhance emotional application ability may effectively reduce the risk of sleep problems among junior and senior high school students.