Developing an intelligent agent for integrated traditional Chinese and western medicine diagnosis and treatment based on clinical practice guidelines is a key approach to advancing the standardization and intelligent deve-lopment of traditional Chinese medicine （TCM） and to supporting clinical decision-making. This paper argues for the necessity of building a knowledge base using guidelines as the sole data source， systematically identifies five core methodological challenges across the entire process， and proposes corresponding solutions. An ontology framework capable of distinguishing between TCM and western medicine concepts should be designed to address the difficulty of knowledge integration. A closed-loop "algorithm-based extraction-expert review" model is adopted to reduce data extraction errors. Expert consensus is incorporated to address decision gaps in specific clinical scenarios outlined in the guidelines， while a multi-stage， standardized output process for the AI system is established to eliminate model hallucinations. Furthermore， an evaluation framework reflecting clinical applicability is developed to enhance the AI system's accuracy and stability. Throughout the research process， it is essential to ensure the in-depth and continuous participation of multidisciplinary experts， strictly control the selection and quality evaluation of guidelines， and rely on the expert consensus method to address decision gaps in the knowledge base. Additionally， continuous validation and iterative optimization of intelligent agents are required to ensure the accuracy and stability of generated outputs. Limitations remain in the mechanisms for real-time knowledge synchronization in intelligent diagnostic and treatment systems， and further validation through large-scale real-world studies is warranted.

Objective To explore the pathological features of bronchiolar adenoma(BA)and its specific high-resolution computed tomography(HRCT)signs,and to differentiate BA from minimally invasive adenocarcinoma(MIA)using a non-invasive preoperative method.Methods A total of 80 patients with BA and 130 patients with MIA were retrospectively selected,and the clinical information and HRCT features were compared.All cases were divided into development set and test set at a 7︰3 ratio.Logistic regression analysis was used to screen the independent predictors of MIA and construct a model.Results There were significant differences in age,lobe distribution,density,vacuole sign,tumor-related vessels number(TVN),and distance to pleura(DTP)between BA and MIA patients(P<0.05).Age,density,TVN,DTP and long diameter were identified as independent predictors of MIA.A model was constructed,with area under the curve(AUC)of 0.887 and 0.884 in the development and test sets,respectively.Conclusion The model based on HRCT morphological features of BA and MIA demonstrates superior diagnostic performance compared to individual CT morphological features.

Objective To analyze the current status of clinical trial registration in the TCM treatment of diabetic nephropathy(DN);To provide references for the registration and implementation of relevant clinical trials.Methods Clinical trials about TCM treatment for DN registered in the Chinese Clinical Trial Registry(ChiCTR)and the U.S.Clinical Trial Registry(ClinicalTrials.gov)from their inception to August 18,2024 were retrieved.The following information was analyzed:registration year,geographical distribution,funding sources,TCM syndrome patterns of participants,number of research centers,sample size,study type,study design,randomization method,blinding method,intervention measures,outcome indicators and safety indicators.Results A total of 88 clinical trials were included,comprising 79 interventional studies and 9 observational studies.The number of registrations has increased annually.The domestic registered trials were distributed across 17 provincial-level administrative regions in China,with Beijing and Shanghai having the highest number of registrations.The primary sources of funding were local and national government funds.The most common TCM syndrome pattern among participants was qi-yin deficiency with blood stasis.Most trials were single-center studies,with the majority having a sample size between 31 and 60.The predominant study type was interventional,mostly randomized controlled trials(RCTs),with simple randomization being the most frequently used method.31 trials reported blinding methods,with double-blinding being the most common.The intervention measures were mostly oral Chinese patent medicines or TCM compounds,and the outcome indicators were mainly efficacy indicators,with less safety indicators.Conclusion The number of registered clinical trials on TCM treatment for DN has increased annually;however,the overall number remains limited.There is uneven regional distribution and incomplete registration information for various factors such as randomization methods,blinding methods,number of research centers,intervention measures,and outcome indicators.

Objective To analyze the current status of clinical trial registration in the TCM treatment of diabetic nephropathy(DN);To provide references for the registration and implementation of relevant clinical trials.Methods Clinical trials about TCM treatment for DN registered in the Chinese Clinical Trial Registry(ChiCTR)and the U.S.Clinical Trial Registry(ClinicalTrials.gov)from their inception to August 18,2024 were retrieved.The following information was analyzed:registration year,geographical distribution,funding sources,TCM syndrome patterns of participants,number of research centers,sample size,study type,study design,randomization method,blinding method,intervention measures,outcome indicators and safety indicators.Results A total of 88 clinical trials were included,comprising 79 interventional studies and 9 observational studies.The number of registrations has increased annually.The domestic registered trials were distributed across 17 provincial-level administrative regions in China,with Beijing and Shanghai having the highest number of registrations.The primary sources of funding were local and national government funds.The most common TCM syndrome pattern among participants was qi-yin deficiency with blood stasis.Most trials were single-center studies,with the majority having a sample size between 31 and 60.The predominant study type was interventional,mostly randomized controlled trials(RCTs),with simple randomization being the most frequently used method.31 trials reported blinding methods,with double-blinding being the most common.The intervention measures were mostly oral Chinese patent medicines or TCM compounds,and the outcome indicators were mainly efficacy indicators,with less safety indicators.Conclusion The number of registered clinical trials on TCM treatment for DN has increased annually;however,the overall number remains limited.There is uneven regional distribution and incomplete registration information for various factors such as randomization methods,blinding methods,number of research centers,intervention measures,and outcome indicators.

Objective To observe the ultrasonic manifestations of local recurrence(LR)of breast cancer after surgery.Methods Totally 82 female breast cancer patients with local hypoechoic in surgical area who underwent ultrasound follow-up were enrolled and divided into LR group(n=18)and non LR group(n=64)according to the local hypoechoic was LR or not.Clinical data and ultrasonic manifestations of primary lesion before operation and postoperative local hypoechoic were observed and compared between groups.Results Significant differences of surgical resection type,molecular subtype,status of smooth muscle actin,Calponin status,Ki-67 status,clinical staging,the maximum diameter and posterior echo of the primary lesion,as well as of involved tissue layer,location,long axis parallel to the skin or not,edge,internal echo,posterior echo,skin change and Adler blood flow grading of local hypoechoic in resection area were found between groups(all P＜0.05).Conclusion Ultrasonic manifestations of LR of breast cancer after surgery had certain characteristics.

Objective To observe the ultrasonic manifestations of local recurrence(LR)of breast cancer after surgery.Methods Totally 82 female breast cancer patients with local hypoechoic in surgical area who underwent ultrasound follow-up were enrolled and divided into LR group(n=18)and non LR group(n=64)according to the local hypoechoic was LR or not.Clinical data and ultrasonic manifestations of primary lesion before operation and postoperative local hypoechoic were observed and compared between groups.Results Significant differences of surgical resection type,molecular subtype,status of smooth muscle actin,Calponin status,Ki-67 status,clinical staging,the maximum diameter and posterior echo of the primary lesion,as well as of involved tissue layer,location,long axis parallel to the skin or not,edge,internal echo,posterior echo,skin change and Adler blood flow grading of local hypoechoic in resection area were found between groups(all P＜0.05).Conclusion Ultrasonic manifestations of LR of breast cancer after surgery had certain characteristics.

Objective To explore the pathological features of bronchiolar adenoma(BA)and its specific high-resolution computed tomography(HRCT)signs,and to differentiate BA from minimally invasive adenocarcinoma(MIA)using a non-invasive preoperative method.Methods A total of 80 patients with BA and 130 patients with MIA were retrospectively selected,and the clinical information and HRCT features were compared.All cases were divided into development set and test set at a 7︰3 ratio.Logistic regression analysis was used to screen the independent predictors of MIA and construct a model.Results There were significant differences in age,lobe distribution,density,vacuole sign,tumor-related vessels number(TVN),and distance to pleura(DTP)between BA and MIA patients(P<0.05).Age,density,TVN,DTP and long diameter were identified as independent predictors of MIA.A model was constructed,with area under the curve(AUC)of 0.887 and 0.884 in the development and test sets,respectively.Conclusion The model based on HRCT morphological features of BA and MIA demonstrates superior diagnostic performance compared to individual CT morphological features.

Objective:To quantitatively evaluate the accuracy of data obtained from liquid-interference surfaces using an intraoral 3D scanner(IOS)integrated with a compressed airflow system,so as to pro-vide clinical proof of accuracy for the application of the compressed airflow system-based scanning head in improving data quality on liquid-interference surfaces.Methods:The study selected a standard model as the scanning object,adhering to the"YY/T 1818-2022 Dental Science Intraoral Digital Impression Scanner"guidelines,a standard that defined parameters for intraoral scanning.To establish a baseline for accuracy,the ATOS Q 12M scanner,known for its high precision,was used to generate true reference values.These true values served as the benchmark for evaluating the IOS performance.Building on the design of an existing scanner,a new scanning head was developed to integrate with a compressed airflow system.This new design aimed to help the IOS capture high-precision data on sur-faces where liquid-interference,such as saliva,might otherwise degrade scanning accuracy.The tradi-tional scanning method,without airflow assistance,was employed as a control group for comparison.The study included five groups in total,one control group and four experimental groups,to investigate the effects of scanning lens obstruction,airflow presence,liquid media,and the use of the new scan-ning head on scanning process and accuracy.Each group underwent 15 scans,generating ample data for a robust statistical comparison.By evaluating trueness and precision in each group,the study as-sessed the impact of the compressed airflow system on the accuracy of IOS data collected from liquid-interference surfaces.Additionally,we selected Elite and Primescan scanners as references for numeri-cal accuracy values.Results:The scanning accuracy on liquid-interference surfaces was significantly reduced in terms of both trueness and precision[Trueness:18.5(6.5)vs.38.0(6.7),P＜0.05;Preci-sion:19.1(8.5)vs.31.7(15.0),P＜0.05].The use of the new scanning head assisted by the com-pressed airflow system significantly improved the scanning accuracy[Trueness:22.3(7.6)vs.38.0(6.7),P＜0.05;Precision:25.8(9.6)vs.31.7(15.0),P＜0.05].Conclusion:The scanning head based on the compressed airflow system can assist in improving the accuracy of data obtained from liquid-inter-ference surfaces by the IOS.

When partial nephrectomy is performed by posterior abdominal approach, the surgical field is poorly exposed, resulting in increased surgical difficulty and risk of injury.In this study, 28 patients with T 1a stage kidney tumors underwent retroperitoneal laparoscopic partial nephrectomy. Intraoperatively, exposure of the surgical field was achieved using the percutaneous puncture of the renal fascia suspension technique. There were no dissatisfactory exposures due to peritoneal damage during the surgery, no additional tubes were inserted, and no conversions to open surgery were needed. The operation time was (76.5±20.3) minutes, blood loss was (92.1±18.7) ml, renal artery clamping time was (19.5±4.3) minutes. Postoperatively, there were no complications such as bleeding, infection, or hematuria.

Objective:To explore the factors associated with vascular luminal dilatational remodeling (VLDR) following balloon angioplasty for intracranial atherosclerotic stenosis (ICAS).Methods:A case-control study was conducted to analyze the data of symptomatic severe ICAS patients who received either paclitaxel-coated balloon angioplasty (PCBA) or plain balloon angioplasty (POBA) at our center from January 2019 to January 2022 and completed the six-month follow-up. The patients were divided into VLDR group and non-VLDR group according to whether VLDR occurred on follow-up digital subtraction angiography (DSA). The baseline data, preoperative and postoperative lesion characteristics (DSA), and perioperative related information were collected. The definition of VLDR was a decrease in luminal stenosis rate by more than 10% at the time of follow-up compared to the immediate postoperative period. Multivariate logistic regression was performed to analyze possible factors affecting VLDR such as balloon type, balloon length, and expansion time.Results:A total of 88 patients were included in this study, with 16 in the VLDR group and 72 in the non-VLDR group. The follow-up time for all included patients was 6.00 (5.00, 7.00) months. VLDR occurred in 18.2% (16/88) of cases, with a VLDR incidence of 30.4% (14/46) after PCBA and 4.8% (2/42) after POBA. Univariate logistic regression analysis revealed that treatment balloon type, balloon length, inflated time, immediate postoperative stenosis rate, follow-up time and Mori classification may affect the occurrence of VLDR. Multivariate logistic regression analysis showed that the use of paclitaxel-coated balloon (PCB) ( OR=9.82, 95% CI 1.99-48.49, P=0.005) and postoperative immediate stenosis rate ( OR=1.07, 95% CI 1.00-1.14, P=0.042) were independently associated with VLDR. Conclusion:The occurrence of VLDR following balloon angioplasty in ICAS was associated with the use of PCB and immediate postoperative stenosis rates, which will provide guidance for the clinical application of PCB.