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.

Objectives:To compare the clinical efficacy and safety of uni-portal endoscopic lumbar interbody fusion by using larger-diameter endoscope for single-level lumbar disease via transforaminal approach versus transfacet approach.Methods:46 patients underwent single-level uni-portal endoscopic lumbar interbody fu-sion from June 2018 to February 2022 were enrolled.18 of the patients were male and 28 were female.The mean age was 60.9±10.5 years old(40-80 years).The follow-up time was 3-47 months.Patients were divided into two groups according to the surgical approach,18 of which were included in the transforaminal group,and the remaining 28 were included in the transfacet group,and a full spinal endoscope of 7.1mm inner-di-ameter working-channel was applied to all the patients.The clinical result was evaluated before surgery,at 3d after surgery and the final follow-up,by Oswestry disability index(ODI),visual analogue scale(VAS)for back pain and leg pain,and Japanese Orthopaedic Association(JO A)score.The decompression and implant were evaluated by anteroposterior and lateral X-ray plain film and lumbar CT at 3d after operation.Bridwell criteria were used to evaluate the fusion rate based on CT images for patients followed up for more than 6 months after surgery.Results:No significant differences were found in age,gender,diagnosis,preoperative in-tervertebral height,surgical segment,preoperative ODI,VAS and JOA score between the two groups(P＞0.05).72.2％of the patients in transforaminal group complained unilateral radicular symptom,while 64.3％of the patients in transfacet group suffered from bilateral radicular symptoms(P=0.020).The average operation time was 327.7±89.9min in the transforaminal group,significantly longer than the 385.9±96.7min in the transfacet group(P=0.047),and the mean length of hospital stay in the transforaminal group was 14.8±6.0d,shorter than that of 19.5±7.8d in the transfacet group(P=0.038).75％of the patients in transfacet group underwent unilater-al laminotomy with bilateral spinal canal decompression(ULBD).The ODI scores,back and leg pain VAS scores and JOA score were significantly improved postoperatively and at the final follow-up in both groups(P＜0.05),while no statistical differences between groups(P＞0.05).Postoperative intervertebral height significantly increased in both group(P＜0.001),but no statistical difference was found between groups(P＞0.05).The compli-cation rate was comparable between two groups,without severe intraoperative or postoperative complication.A-mong the 21 patients who were followed up for more than 6 months and received CT examinations,20(95.2％)presented bony fusion at surgical segment,and there was no statistical difference between the two groups in fusion rate.Conclusions:Both the transforaminal approach and the transarticular protrusion ap-proach are safe and effective for the single-level lumbar interbody fusion under single-hole coaxial large channel endoscopy,and the transforaminal approach results in shorter operation time and shorter hospital stay.

Objectives:To explore the clinical outcomes of single-level full-endoscopic lumbar interbody fu-sion for degenerative lumbar spine disorders combined with osteoporosis.Methods:24 consecutive patients with degenerative lumbar spine disorders who underwent single-level full-endoscopic lumbar interbody fusion and were detected by dual-energy X-ray absorptiometry(DXA)during hospitalization for bone mineral density(BMD)from June 2018 to February 2022 were enrolled,including 7 males and 17 females with an average age of 66.0±9.9 years old(range 44-80 years).The follow-up period was 21.6±12.6(3-47)months after oper-ation.And the patients were divided into two groups of osteoporosis group(containing 8 osteoporotic cases)and control group(containing 16 non-osteoporotic cases).Anti-osteoporosis therapy was initiated on the diagnosis of osteoporosis.The surgery was performed using a 7.1mm inner-diameter full-endoscope.The general data and perioperative parameters were compared between the two groups.Before operation,on 3d after operation and at final follow-up,visual analogue scale(VAS)score for back and leg pain,Japanese Orthopaedic Association(JOA)score and Oswestry disability index(ODI)were used for evaluating clinical outcomes.Digital radiography(DR)and computed tomography(CT)were performed on postoperative 3d for neural decompression and implant position assessment.For patients who received DR examination,cage subsidence and screw loosening were recorded at the final follow-up;For patients who were followed-up for 6 months and more and examined with CT,fusion rate was evaluated.The complications were recorded and compared between the two groups.Re-sults:No significant differences were found in age,gender,diagnosis,preoperative intervertebral height,surgi-cal segment,preoperative VAS scores,JOA scores and ODI between the two groups.The average of the low-est T value was-3.2±0.6 for osteoporosis group,lower than the-1.4±0.8 for control group(P=0.000).The mean operative time was 429.9±135.2min for osteoporosis group,more than the 327.4±68.2min for the controls(P=0.020).There was no significant difference in intraoperative imaging assistance,bleeding,number of cases received unilateral laminotomy for bilateral decompression(ULBD),postoperative intervertebral height and length of hospital stay between groups.The VAS scores for back and leg pain,JOA scores and ODI improved post-operatively and at the final follow-up in both groups comparing with those values before operation(P＜0.05),and there was no significant difference between groups,respectively.The postoperative 3d intervertebral height in both groups increased after surgery(P＜0.01),and none significant difference was found between groups.In the osteoporosis group,asymptomatic cage subsidence happened in 1 case with severe osteoporosis(T=-4.4)due to intraoperative endplate damage during cage implantation,but no symptoms were observed,therefore no spe-cial treatment was given;And dural tear and subsequent incomplete nerve root injury happened to another case in the osetoporosis group,whose symptoms were relieved after symptomatic treatment such as neurotro-phy.18 patients received lumbar DR at final follow-up,and 10 patients received CT evaluation at more than 6 months'follow-up,no significant difference was found in cage subsidence and screw loosening rate and fusion conditions between groups(P=1.000).Conclusions:Single-level full-endoscopic lumbar interbody fusion is safe and effective in the short-term for the treatment of degenerative lumbar spine disorder combined with osteoporosis.

According to the International League Against Epilepsy (ILAE) standards, the Newborn Working Group of the ILAE put forward 6 necessary questions about the management of neonatal anti-seizure medication and gave evidence-based recommendations in 2023. The basic framework is systematic review+expert consensus. The clinical recommendations of ILAE guidelines 2023 and the similarities and differences between ILAE guidelines 2023 and ILAE guidelines 2011 were analyzed and interpreted in this paper, in order to provide reference for colleagues involved in neonatal convulsion management in China.

Objective:To compare the efficacy and safety of transjugular intrahepatic portosystemic shunt (TIPS) and endoscopic treatment for liver cirrhosis with esophageal gastric variceal bleeding (EGVB) and portal vein thrombosis (PVT).Methods:A total of 183 liver cirrhosis patients with EGVB and PVT in Nanjing Drum Tower Hospital, the Affiliated Hospital of Nanjing University Medical School and the First Affiliated Hospital of Wenzhou Medical University were selected from January 2017 to December 2019, and 66 patients were assigned to the endoscopic group (received endoscopi treatment) and 117 the TIPS group (received TIPS treatment). Propensity score matching was performed according to the 1∶1 ratio, yielding 58 patients in each group for analysis, with a median follow-up time of 36 months in both groups. Postoperative survival, postoperative rebleeding rate, and postoperative hepatic encephalopathy incidence were assessed using Kaplan-Meier survival curves.Results:During the follow-up, the rebleeding rate in the endoscopic group was significantly higher [39.7% (23/58) VS 17.2% (10/58), P=0.005], and the TIPS group had a higher incidence of postoperative hepatic encephalopathy [29.3% (17/58) VS 13.8% (8/58), P=0.048], and no significant difference in survival rate was observed between the two groups [74.1% (43/58) VS 75.9% (44/58), P=0.769]. In the subgroup analysis of mild degree of PVT, there was no significant difference in survival [88.0% (22/25) VS 72.0% (18/25), P=0.164], rebleeding rate [28.0% (7/25) VS 12.0% (3/25), P=0.164], or incidence of hepatic encephalopathy [8.0% (2/25) VS 20.0% (5/25), P=0.202] between the endoscopic group and the TIPS group. In the subgroup analysis of severe degree of PVT, the rebleeding rate in the endoscopic group was significantly higher than that in the TIPS group [48.5% (16/33) VS 21.2% (7/33), P=0.010], while there was no significant difference in the incidence of hepatic encephalopathy [18.2% (6/33) VS 36.4% (12/33), P=0.133], or the survival rate [63.6% (21/33) VS 78.8% (26/33), P=0.154]. Conclusion:For liver cirrhosis patients with mild PVT and EGVB, combining endoscopic therapy with anticoagulation may be superior to TIPS. Conversely, in patients with severe PVT, TIPS may be a more suitable option due to a significantly reduced rebleeding risk without a notable increase in hepatic encephalopathy incidence.

Objective To develop deep learning models for colonoscopy quality control using various deep learning architectures,and to delve into the decision-making mechanisms.Methods The colonoscopy images were selected from two datasets separately constructed by the HyperKvasir and Changshu Hospital Affiliated to Soochow University,encompassing intestines of varying degrees of cleanliness,polyps,and cecums.After image preprocessing and enhancement,transfer learning was carried out using the pre-trained models based on convolutional neural network(CNN)and Transformer.The model training adopted cross-entropy loss functions and Adam optimizer,and simultaneously implemented learning rate scheduling.To enhance model transparency,a thorough interpretability analysis was conducted using Grad-CAM,Guided Grad-CAM,and SHAP.The final model was converted to ONNX format and deployed on various equipment terminals to achieve real-time colonoscopy quality control.Results In a dataset of 3 831 colonoscopy images,EfficientNet model outperformed the other models on the test set,achieving an accuracy of 0.992 which was higher than those of the other models based on CNN(DenseNet121,ResNet50,VGG19)and Transformer(ViT,Swin,CvT),with a precision,recall rate,and F1 score of 0.991,0.989,and 0.990.On an external test set of 358 images,EfficientNet model had an average AUC,precision,and recall rate of 0.996,0.948,and 0.952,respectively.Although EfficientNet model is high-performing,some misjudgments still occurred.Interpretability analysis highlighted key image areas affecting decision-making.In addition,EfficientNet model was successfully converted to ONNX format and deployed on multiple platforms and devices,and it ensured real-time colonoscopy quality control with an inference speed of over 60 frames per second.Conclusion Among the 7 models developed for colonoscopy quality control based on CNN and Transformer,EfficientNet demonstrated exemplary performance across all categories and is deployed for real-time predictions on multiple terminals,aiming to provide patients with better medical care.