Intelligent prescription recommendation has become an important research direction in traditional Chinese medicine (TCM), offering new opportunities to support clinical decision-making and promote the modernization of TCM practice. With the rapid development of artificial intelligence (AI), a variety of computational approaches have been proposed to learn prescription patterns from clinical data and generate personalized treatment recommendations. However, despite increasing research activity, systematic and comprehensive reviews of AI-driven methods for TCM prescription recommendation remain limited. In this study, we present a comprehensive review of computational approaches for herbal prescription recommendation (HPR) in TCM. Existing methods are systematically categorized into several major paradigms, including traditional machine learning methods, topic model methods, sequential generative methods, deep learning and graph-based methods, and large language model–based frameworks. In addition to summarizing methodological developments, we also review commonly used public datasets and evaluation metrics in this field. Furthermore, representative models with publicly available implementations are experimentally evaluated on multiple benchmark datasets to provide a comparative analysis of their performance on the HPR task. Finally, we discuss the key challenges that hinder the practical deployment of intelligent prescription recommendation systems, including data heterogeneity, limited interpretability, and insufficient integration of TCM domain knowledge. Future research directions are outlined to facilitate the development of more reliable, interpretable, and clinically applicable AI-assisted HPR systems for TCM.

OBJECTIVE:Based on different algorithms of machine learning,the prediction model of lumbar disc herniation has become a trend and hot spot in the development of precision medicine.However,there is limited evidence on the reporting quality and methodological quality of prediction models of lumbar disc herniation outcomes using machine learning.This article is aimed to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation by comprehensively analyzing the report quality and risk of bias of previous studies that developed and validated prognosis prediction models based on machine learning through a comprehensive literature search,in order to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation.METHODS:The databases of CNKI,WanFang,VIP,SinOMED,PubMed,Web of Science,Embase,and The Cochrane Library were searched by computer.Studies on the use of machine learning to develop(and/or validate)prognostic prediction models for lumbar disc herniation were collected from the inception of the database to December 31,2023.Two researchers independently screened the literature,extracted data,and assessed the risk of bias of the included studies.The reporting quality and risk of bias of the included studies were assessed by the Multivariable Transparent Reporting of Predictive Models(TRIPOD)statement and the Predictive Model Risk of Bias Assessment Tool(PROBAST).The results of the evaluation were analyzed using descriptive statistics and visual charts.RESULTS:(1)A total of 23 articles were included,and the TRIPOD compliance of each study ranged from 11％to 87％,with a median compliance of 54％.The quality of reporting of titles,detailed descriptions of treatment measures,blinding of predictors,handling of missing data,details of risk stratification,specific procedures for enrollment,model interpretation,and model performance was mostly poor,with TRIPOD adherence rates ranging from 4％to 35％.(2)Of all included studies,61％had a high risk of bias and 39％had an unclear overall risk of bias.The area under the curve,accuracy,sensitivity and specificity were used to evaluate the performance of the model.The areas under the curve of 20 models were reported,ranging from 0.561 to 0.999.Three models reported the accuracy of the model,ranging from 82.07％to 89.65％.(3)Among all included studies,the statistical analysis domain was most often assessed as having a high risk of bias,mainly due to the small number of valid samples,the selection of predictors based on univariate analysis and the lack of calibration and discrimination assessment of the model in the study.CONCLUSION:These results indicate that machine learning can achieve good predictive ability in the development and validation of prognostic models for lumbar disc herniation.The commonly used algorithms include regression algorithm,support vector machine,decision tree,random forest,artificial neural network,naive Bayes and other algorithms.Reasonable algorithms combined with clinical practice can improve the accuracy of prognosis prediction of lumbar disc herniation.However,the reporting and methodological quality of prognosis prediction models based on machine learning are poor,the prediction performance of different models varies greatly,and the generalization and extrapolation of research models are unclear.There is an urgent need to improve the design,implementation and reporting of such studies.To promote the application of machine learning in the clinical practice of lumbar disc herniation prediction models,it is necessary to comprehensively consider various predictors related to the prognosis of the disease before modeling,and strictly follow the relevant standards of PROBAST tool during modeling.

Objective To explore the effect of remote ischemic preconditioning (RIPC) on preoperative heart rate variability in patients with heart valves. Methods Patients scheduled to undergo on-pump cardiac valve surgery in the Department of Cardiovascular Surgery, General Hospital of Northern Theater Command, between January and July 2022 were initially enrolled. Eligible patients were randomly assigned at a 1 : 1 ratio to either the RIPC group or the control group. Relevant indicators of heart rate variability [standard deviation of NN interval (SDNN), standard deviation of mean value of NN interval in every five minutes (SDANN), mean square root of difference between consecutive NN intervals (RMSSD), percentage of adjacent RR interval>50 ms (PNN50), low frequency (LF) component, high frequency (HF) component and LF/HF] at 8 hours in the morning on the surgical day between two groups were compared. Results A total of 118 patients were initially assessed. After screening, 58 patients were excluded, and 60 patients provided written informed consent and were enrolled in the trial, with 30 allocated to the RIPC group and 30 to the control group. Seven patients in the control group and 5 patients in the RIPC group were subsequently excluded due to missing heart rate variability data resulting from cancelled operations. Finally, 23 patients in the control group and 25 patients in the RIPC group were included in the analysis. There was no statistical difference in baseline characteristics between the two groups, and there was no significant difference in heart rate variability 24 hours before intervention (P>0.05). After the intervention measures were taken, the comparison of the results of heart rate variability at 8 hours on the day of operation showed that SDNN and SDANN of patients in the RIPC group were higher than those in the control group, with statistical differences (P<0.05). Conclusion RIPC can stabilize the preoperative heart rate variability of patients undergoing cardiac valve surgery.

OBJECTIVE:Based on different algorithms of machine learning,the prediction model of lumbar disc herniation has become a trend and hot spot in the development of precision medicine.However,there is limited evidence on the reporting quality and methodological quality of prediction models of lumbar disc herniation outcomes using machine learning.This article is aimed to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation by comprehensively analyzing the report quality and risk of bias of previous studies that developed and validated prognosis prediction models based on machine learning through a comprehensive literature search,in order to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation.METHODS:The databases of CNKI,WanFang,VIP,SinOMED,PubMed,Web of Science,Embase,and The Cochrane Library were searched by computer.Studies on the use of machine learning to develop(and/or validate)prognostic prediction models for lumbar disc herniation were collected from the inception of the database to December 31,2023.Two researchers independently screened the literature,extracted data,and assessed the risk of bias of the included studies.The reporting quality and risk of bias of the included studies were assessed by the Multivariable Transparent Reporting of Predictive Models(TRIPOD)statement and the Predictive Model Risk of Bias Assessment Tool(PROBAST).The results of the evaluation were analyzed using descriptive statistics and visual charts.RESULTS:(1)A total of 23 articles were included,and the TRIPOD compliance of each study ranged from 11％to 87％,with a median compliance of 54％.The quality of reporting of titles,detailed descriptions of treatment measures,blinding of predictors,handling of missing data,details of risk stratification,specific procedures for enrollment,model interpretation,and model performance was mostly poor,with TRIPOD adherence rates ranging from 4％to 35％.(2)Of all included studies,61％had a high risk of bias and 39％had an unclear overall risk of bias.The area under the curve,accuracy,sensitivity and specificity were used to evaluate the performance of the model.The areas under the curve of 20 models were reported,ranging from 0.561 to 0.999.Three models reported the accuracy of the model,ranging from 82.07％to 89.65％.(3)Among all included studies,the statistical analysis domain was most often assessed as having a high risk of bias,mainly due to the small number of valid samples,the selection of predictors based on univariate analysis and the lack of calibration and discrimination assessment of the model in the study.CONCLUSION:These results indicate that machine learning can achieve good predictive ability in the development and validation of prognostic models for lumbar disc herniation.The commonly used algorithms include regression algorithm,support vector machine,decision tree,random forest,artificial neural network,naive Bayes and other algorithms.Reasonable algorithms combined with clinical practice can improve the accuracy of prognosis prediction of lumbar disc herniation.However,the reporting and methodological quality of prognosis prediction models based on machine learning are poor,the prediction performance of different models varies greatly,and the generalization and extrapolation of research models are unclear.There is an urgent need to improve the design,implementation and reporting of such studies.To promote the application of machine learning in the clinical practice of lumbar disc herniation prediction models,it is necessary to comprehensively consider various predictors related to the prognosis of the disease before modeling,and strictly follow the relevant standards of PROBAST tool during modeling.

Objective To investigate the causes and management strategies for lower limb ischemic necrosis following xenogeneic heterotopic heart transplantation from a multigene-edited pig to a rhesus monkey. Methods A xenogeneic heterotopic heart transplantation was performed on December 16, 2023, at the Institute of Experimental Animals of Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital, using a quintuple-gene-edited pig as the donor and a rhesus monkey as the recipient. On postoperative day (POD) 9, the recipient monkey underwent left lower limb amputation due to ischemic necrosis. Blood samples were collected at various time points after transplantation for analysis of hematologic parameters, liver and renal function, myocardial enzymes, and coagulation profiles. Ultrasound and computed tomography (CT) were used to evaluate anastomotic patency and cardiac structure. Immunological assays, including complement-dependent cytotoxicity (CDC) and IgG/IgM antibody detection, combined with clinical observations, were employed to assess rejection type and therapeutic response. Results The recipient monkey survived for 46 days after transplantation. Echocardiography demonstrated preserved biventricular systolic function in the recipient’s native heart, with left ventricular ejection fraction (LVEF) consistently exceeding 50%. In the donor pig heart, left ventricular endocardial thickening was noted on POD 9, followed by right ventricular endocardial thickening on POD 24, while LVEF remained around 35%. No hyperacute or acute rejection was detected immunologically. CDC positivity ranged between 3.4% and 5.1%, with IgG/IgM antibody binding trends consistent with CDC results. Following amputation, the recipient exhibited elevated inflammatory markers, coagulopathy, and reactive thrombocytosis, which later normalized. Immunohistochemical staining of the necrotic limb revealed arterial and venous thrombosis; however, no T-cell or B-cell infiltration was observed in vascular structures, thrombi, nerves, muscles, fascia, or skin tissues, with CD3 and CD20 staining both negative. Conclusion Limb ischemia after xenogeneic heart transplantation may be associated with lower extremity vascular thrombosis triggered by local trauma in the context of transplantation-induced inflammatory activation and coagulation dysfunction. While no clear lymphocyte-mediated rejection was observed, further studies are needed to explore the potential role of non-lymphocyte-mediated immune mechanisms.

Hepatic encephalopathy is a difficult and critical disease with rapid progression and limited treatment methods in the field of liver disease， and it is urgently needed to make breakthroughs in its pathogenesis. Selection of appropriate prevention and treatment strategies is of great importance in delaying disease progression and reducing the incidence and mortality rates. This article reviews the theory of “turbid toxin pathogenesis” and related prevention and treatment strategies for hepatic encephalopathy in traditional Chinese medicine/Zhuang medicine， proposes a new theory of “turbid toxin pathogenesis”， analyzes the scientific connotations of “turbid”， “toxin”， and the theory of “turbid toxin pathogenesis”， and constructs the “four-step” prevention and treatment strategies for hepatic encephalopathy， thereby establishing the new clinical prevention and treatment regimen for hepatic encephalopathy represented by “four prescriptions and two techniques” and clarifying the effect mechanism and biological basis of core prescriptions and techniques in the prevention and treatment of hepatic encephalopathy， in order to provide a reference for the prevention and treatment of hepatic encephalopathy.

Objective To compare the mid- and long-term clinical results of mitral valve plasty (MVP) and mitral valve replacement (MVR) in the treatment of functional mitral regurgitation (FMR). Methods Patients with FMR who underwent surgical treatment in the Department of Cardiovascular Surgery of the General Hospital of Northern Theater Command from 2012 to 2021 were collected. The patients who underwent MVP were divided into a MVP group, and those who underwent MVR into a MVR group. The clinical data and mid-term follow-up efficacy of two groups were compared. Results Finally 236 patients were included. There were 100 patients in the MVP group, including 53 males and 47 females, with an average age of (61.80±8.03) years. There were 136 patients in the MVR group, including 72 males and 64 females, with an average age of (61.29±8.97) years. There was no statistical difference in baseline data between the two groups (P＞0.05). There was no statistical difference between the two groups in the extracorporeal circulation time, aortic occlusion time, postoperative hospital and ICU stay, intraoperative blood loss, or hospitalization death (P＞0.05), but the time of mechanical ventilation in the MVP group was significantly shorter than that in the MVR group (P=0.022). The total follow-up rate was 100.0%, the longest follow-up was 10 years, and the average follow-up time was (3.60±2.55) years. There were statistical differences in the left atrial diameter, left ventricular end-diastolic diameter, left ventricular end-systolic diameter and cardiac function between the two groups compared with those before surgery (P<0.05). The postoperative left ventricular ejection fraction in the MVP group was statistically higher than that before surgery (P=0.002), but there was no statistical difference in the MVR group before and after surgery (P=0.658). The left atrial diameter in the MVP group was reduced compared with the MVR group (P=0.026). The recurrence rate of mitral regurgitation in the MVP group was higher than that in the MVR group, and the difference was statistically significant (10.0% vs. 1.5%, P=0.003). There were 14 deaths in the MVP group and 19 in the MVR group. The cumulative survival rate (P=0.605) and cardiovascular events-free survival rate (P=0.875) were not statistically significant between the two groups by Kaplan-Meier survival analysis. Conclusion The safety, and mid- and long-term clinical efficacy of MVP in the treatment of FMR patients are better than MVR, and the left atrial and left ventricular diameters are statistically reduced, and cardiac function is statistically improved. However, the surgeon needs to be well aware of the indications for the MVP procedure to reduce the rate of mitral regurgitation recurrence.

Objective:To investigate the impact of postoperative complications on adverse outcomes following curative-intent resection for gallbladder cancer (GBC).Methods:The multi-center real-world study was conducted. The clinicopathological data of 629 patients with GBC, who were admitted to 14 medical centers including The First Affiliated Hospital of Army Medical University from the national multicenter database of Biliary Surgery Group of Elite Group of Chinese Journal of Digestive Surgery, from April 2020 to April 2024 were collected. There were 225 males and 404 females, aged (64±10)years. Patients underwent open curative-intent resection for GBC. Observation indicators: (1)surgery, postoperative complica-tions and adverse outcomes; (2) analysis of risk factors affecting postoperative adverse outcomes in patients and population attributable fraction (PAF). Missing data in predictor variables were addressed using multiple imputation with chained equations, while cases with missing outcome variables were addressed using the "multiple imputation then deletion (MID)" strategy. The severity of multicollinearity among independent variables was assessed using the variance inflation factor (VIF) test. Multivariable possion regression models with log link and robust error variance were construc-ted incorporating restricted cubic splines (3 knots) to address nonlinear relationships in continuous variables, calculating adjusted relative risk ( RR) with corresponding 95% confidence interval ( CI). Adjusted PAF was calculated for each imputed dataset using the AF package of R software, with subsequent pooling performed according to Rubin's rules. Results:(1) Surgery, postoperative complications and adverse outcomes. All 629 patients underwent curative-intent resection for GBC, of which 143 cases had postoperative complications, including 68 cases of intra-abdominal ascites, 39 cases of pulmonary infection, 21 cases of bile leakage, 12 cases of intra-abdominal hemorrhage, 11 cases of liver failure, 10 cases of pan-creatic fistula, 10 cases of wound infection, 10 cases of gastroparesis, 7 cases of cholangitis, 7 cases of sepsis. The same patient could have more than one kind of complication. Of 629 patients, there were 19 cases of postoperative 90-day death and 11 cases of missing data, 42 cases with post-operative 90-day reoperation and 7 cases with missing data, 44 cases with postoperative 90-day readmission and 3 cases with missing data, 155 cases with prolonged postoperative hospital stay and 3 cases with missing data. (2) Analysis of risk factors affecting the postoperative adverse outcomes in patients and PAF. Results of multivariate analysis showed that pulmonary infection and liver failure were independent risk factors for postoperative 90-day mortality ( RR=3.74, 12.15, 95% CI as 1.18-11.83, 1.98-74.48, P<0.05). Pulmonary infection demons-trated the highest PAF as 4.61% (95% CI as 3.94%-5.28%, P<0.05). Intra-abdominal ascites, pulmonary infection, bile leakage, and intra-abdominal hemorrhage were independent risk factors for post-operative 90-day reoperation ( RR=4.80, 3.62, 3.46, 4.99, 95% CI as 2.49-9.26, 1.42-9.21, 1.34-8.92, 1.55-16.06, P<0.05). Intra-abdominal ascites demonstrated the highest PAF as 8.65% (95% CI as 8.22%-9.08%, P<0.05). Intra-abdominal ascites, bile leakage, and liver failure were independent risk factors for postoperative 90-day readmission ( RR=6.20, 3.33, 14.33, 95% CI as 3.21-11.95, 1.33-8.35, 3.72-55.28, P<0.05). Intra-abdominal ascites demonstrated the highest PAF as 9.11% (95% CI as 8.85%-9.37%, P<0.05). Intra-abdominal ascites, pulmonary infection, bile leakage, liver failure, and wound infection were independent risk factors for prolonged postoperative hospital stay ( RR=2.29, 2.21, 2.26, 2.14, 3.35, 95% CI as 1.63-3.23, 1.41-3.46, 1.32-3.86, 1.11-4.13, 1.70-6.60, P<0.05). Intra-abdominal ascites demonstrated the highest PAF as 6.03% (95% CI as 5.71%-6.35%, P<0.05). Conclusion:Pulmonary infection is the most significant risk factor for postoperative 90-day mortality after curative-intent resection for GBC, while intra-abdominal ascites is the most significant risk factor for postoperative 90-day reoperation, postoperative 90-day readmission, and prolonged postoperative hospital stay.

Objective To investigate the effect of dexmedetomidine(Dex)on bone loss in tail-suspended rats and primarily explore its regulatory mechanism on bone metabolism.Methods A total of 30 male rats were randomly divided into a control group,a model group,and a Dex group,with 10 animals in each group.Rat model of osteoporosis was established by hind limb suspension for 4 weeks.Dex at a dose of 10 μg/kg was given intraperitoneally,once every other day from the day of tail suspension.And equal amount of normal saline was given to the control and model group.Bone histological staining was used to observe the trabecular bone area fraction.Biomechanical three-point bending test was employed to measure the maximum load,stiffness,and fracture energy.Dual calcein/alizarin red fluorescence labeling and tartrate resistant acid phosphatase(TRAP)staining were applied respectively to detect the mineral apposition rate and bone formation rate as well as the number of osteoclasts on bone surfaces.Secondly,after primary osteoblasts were isolated from the tibiae of tail-suspended rats and then treated with 1 nmol/L Dex,the proportion of alkaline phosphatase(ALP)-positive osteoblasts and the activity of the enzyme were detected by ALP staining and activity test.qRT-PCR was applied to measure the expression of osteogenic activity-related factors,including osteocalcin(Ocn),Runt related transcription factor 2(Runx2),Osterix protein(Osx),and type 1 collagen(Col1).Results The animal experiments revealed that Dex treatment significantly increased the tibial trabecular bone area fraction,inhibited the decrease in bone mechanical strength,and enhanced the mineralization deposition rate and new bone formation rate of trabecular bone in the tail-suspended rats(all P＜0.001).The in vitro experiments showed that Dex treatment obviously improved ALP activity and the number of ALP-positive osteoblasts in primary osteoblasts isolated from tail-suspended rats(P＜0.01),and up-regulated the expression levels of osteogenic differentiation-related genes,such as Ocn,Runx2,Osx and Col1(P＜0.01).Conclusion Dex exerts anti-bone loss effect in tail-suspended rats,which may be associated with its stimulation on osteoblast-mediated bone formation.

Objective:To assess the safety of a novel domestically developed direct visualization system of peroral cholangiopancreatoscopy for the exploration of biliary tract.Methods:Clinical data from 384 patients with biliary tract diseases who underwent endoscopic retrograde cholangiopancreatography (ERCP) at the Endoscopy Center of Shanghai Xuhui District Central Hospital from November 2017 to December 2022 were retrospectively analyzed. Patients were categorized into 2 groups based on the type of cholangioscope: the novel cholangiopancreatoscopy system group ( n=159) and the SpyGlass group ( n=225). In the novel cholangiopancreatoscopy system group, the new direct visualization system of China-made peroral cholangiopancreatoscopy was used for bile duct exploration, while the SpyGlass group utilized the SpyGlass system for bile duct inspection. Propensity score matching (PSM) was used as a nearest-neighbor method with a caliper of 0.01 to minimize confounding factors, resulting in a balanced sample of 122 patients in each group after matching. The primary outcome was the incidence of short-term complications, with secondary outcomes including technical success rates and post-treatment outcomes. Results:After PSM, there were no significant differences in baseline characteristics between the two groups ( P>0.05). Regarding short-term postoperative complications, pancreatitis occurred in 1.6% (2/122) of patients in the novel cholangiopancreatoscopy system group and 7.4% (9/122) in the SpyGlass group. The new system significantly reduced the incidence of post-procedure pancreatitis ( χ2=4.665, P=0.031). The cholecystitis was absent in the novel cholangiopancreatoscopy system group, while it occurred in 0.8% (1/122) cases in the SpyGlass group, with no significant difference between the two groups after the procedure ( P=1.000). Regarding technical success rate, the novel system group achieved a rate of 99.2% (121/122), while the SpyGlass group achieved 97.5% (119/122) ( P=0.622). A slightly higher success rate was observed in the novel system group.There were 81 cases of postoperative biliary drainage in the novel cholangiopancreatoscopy system group and 74 cases in the SpyGlass group. Conclusion:The novel direct visualization system of peroral cholangiopancreatoscopy is safer than SpyGlass in the exploration of biliary system diseases. Endoscopists are encouraged to choose the appropriate cholangioscopy system based on individual patient characteristics for the direct visualization, diagnosis, and treatment of biliary diseases.