This paper has constructed a traditional Chinese medicine （TCM） specialized disease dataset platform for mixed hemorrhoids based on a multimodal large model， and the preliminary application has been validated. The platform uses StarRocks to establish a four-level data warehouse system， enabling the aggregation， cleaning， and standardization of multi-source heterogeneous data. Using DeepSeek-R1-Distill-Qwen-7B as the base model， domain fine-tuning is performed through low-rank adaptation （LoRA） technology. Combined with LLaMA-3.3 natural language processing and reasoning chain techniques， the platform enables intelligent parsing and structured extraction of unstructured TCM medical records. It accurately identifies six major categories and 28 subcategories of entities， including symptoms and syndromes， with a fine-tuned model F1 score of 93.8%. The platform has established a high-quality specialized disease dataset containing more than 50,000 medical records and has been applied in a real-world study involving 17,831 patients， preliminarily verifying the efficacy of TCM heritage surgery.

BACKGROUND:Lumbar degenerative disease is a disease of the musculoskeletal system that primarily affects the intervertebral structures,and the disease is treated with lumbar fusion and disc replacement.OBJECTIVE:To conduct comparative analysis of the differences between lumbar fusion,mechanical lumbar disc prosthesis replacement,and viscoelastic lumbar disc prosthesis replacement.METHODS:The computerized tomography images of a healthy adult were used to construct a finite element model of the L2-L5 normal lumbar spine with Mimic,Geomagic,and Ansys software.The equipment required for lumbar fusion and lumbar spine replacement was constructed using modeling software,and the L3-L4 segment of the lumbar spine was processed according to the surgical requirements for lumbar fusion and intervertebral disc replacement,creating the corresponding finite element model.Specific boundary conditions were applied to extract the mobility of each lumbar spine segment,the stresses on the neighboring intervertebral discs,and the stresses on the prosthesis lining.RESULTS AND CONCLUSION:(1)Compared with the preoperative period,the maximum stress in the upper neighboring discs increased by 64.09％and 39.79％in the forward flexion and lateral bending states if the original mobility was maintained after lumbar fusion surgery.The maximum stress in the lower neighboring discs increased by 24.39％and 20.98％in forward flexion and lateral bending.This suggested that the upper adjacent discs would suffer greater stress changes than the lower adjacent discs during heavy physical labor.(2)Disc replacement did not show significant changes in adjacent disc stress,with mechanical prosthesis replacement slightly reducing adjacent disc stress,while viscoelastic prosthesis replacement was more in line with the biological properties of the disc,with maximum adjacent disc stress similar to that of the preoperative period.(3)In terms of stability,the mechanical prosthesis replacement segment showed a 51.67％increase in range of motion in the lateral bending state and a 53.27％increase in range of motion in the posterior extension state,whereas the viscoelastic prosthesis was better able to maintain mobility in the replacement segment.(4)In addition,the stresses in the liner of the mechanical prosthesis were mainly concentrated in the edge region,and this stress distribution may lead to edge wear and thus affect the service life of the prosthesis.

BACKGROUND:Lumbar degenerative disease is a disease of the musculoskeletal system that primarily affects the intervertebral structures,and the disease is treated with lumbar fusion and disc replacement.OBJECTIVE:To conduct comparative analysis of the differences between lumbar fusion,mechanical lumbar disc prosthesis replacement,and viscoelastic lumbar disc prosthesis replacement.METHODS:The computerized tomography images of a healthy adult were used to construct a finite element model of the L2-L5 normal lumbar spine with Mimic,Geomagic,and Ansys software.The equipment required for lumbar fusion and lumbar spine replacement was constructed using modeling software,and the L3-L4 segment of the lumbar spine was processed according to the surgical requirements for lumbar fusion and intervertebral disc replacement,creating the corresponding finite element model.Specific boundary conditions were applied to extract the mobility of each lumbar spine segment,the stresses on the neighboring intervertebral discs,and the stresses on the prosthesis lining.RESULTS AND CONCLUSION:(1)Compared with the preoperative period,the maximum stress in the upper neighboring discs increased by 64.09％and 39.79％in the forward flexion and lateral bending states if the original mobility was maintained after lumbar fusion surgery.The maximum stress in the lower neighboring discs increased by 24.39％and 20.98％in forward flexion and lateral bending.This suggested that the upper adjacent discs would suffer greater stress changes than the lower adjacent discs during heavy physical labor.(2)Disc replacement did not show significant changes in adjacent disc stress,with mechanical prosthesis replacement slightly reducing adjacent disc stress,while viscoelastic prosthesis replacement was more in line with the biological properties of the disc,with maximum adjacent disc stress similar to that of the preoperative period.(3)In terms of stability,the mechanical prosthesis replacement segment showed a 51.67％increase in range of motion in the lateral bending state and a 53.27％increase in range of motion in the posterior extension state,whereas the viscoelastic prosthesis was better able to maintain mobility in the replacement segment.(4)In addition,the stresses in the liner of the mechanical prosthesis were mainly concentrated in the edge region,and this stress distribution may lead to edge wear and thus affect the service life of the prosthesis.

Background: and Purpose Vertebrobasilar fusiform aneurysms (VBFAs) carry substantial morbidity and mortality, but optimal management for unruptured VBFAs remains unclear. We compared the safety and efficacy of conservative management (CM), stent-assisted coiling (SAC), and flow diverters (FDs) in patients with unruptured VBFAs, focusing on long-term prognosis. Methods: This study included data from a nationwide Chinese cohort of patients with vertebrobasilar dissecting aneurysms. Inverse probability of treatment weighting (IPTW) balanced confounders across groups. The primary outcome was poor prognosis (modified Rankin Scale score >2). Secondary outcomes included aneurysm rupture, ischemic stroke, compression symptoms, and VBFA-related deaths. Logistic regression estimated odds ratios (ORs) and 95% confidence intervals (CIs). Subgroup and sensitivity analyses were performed. Results: Among 1,115 patients with unruptured VBFAs, 838 (median age, 54 years; 655 men) were included. After IPTW, baseline characteristics were balanced. Median follow-up was 54 months. FD was associated with a lower risk of poor prognosis than CM (OR, 0.48 [95% CI, 0.30 to 0.77]; p=0.002), with no difference between CM and SAC. FD also reduced aneurysm rupture (OR, 0.20 [95% CI, 0.07 to 0.60]; p=0.004) and compression symptoms (OR, 0.30 [95% CI, 0.13 to 0.68]; p=0.004) versus CM. Time-to-event analyses further revealed significant differences in vertebral artery lesions and Type I–II VBFAs, whereas no significant differences were observed in basilar or vertebrobasilar junction lesions or in Type III–IV VBFAs. Conclusions Compared with CM, FD was associated with improved long-term outcomes in unruptured VBFAs, particularly in vertebral artery lesions and Type I–II VBFAs, although residual confounding cannot be excluded.

Blood transfusion is an important life-support measure in modern medicine. As clinical demand for transfusion continues to rise, blood supply remains under persistent strain, making the efficient utilization of this precious medical resource a critical component of blood management. Accurate prediction of transfusion needs is of great significance for optimizing blood resource allocation and conserving blood products. Traditional transfusion decision-making relies on clinical experience and simplified scoring systems, which are insufficient to meet the demands of precision medicine. Machine learning (ML) technology can integrate multidimensional data—including demographic characteristics, laboratory indicators, surgical information, and dynamic physiological waveforms—to construct high-performance predictive models, offering a new approach to transfusion prediction. This article systematically reviews the application progress of ML in transfusion prediction across clinical scenarios such as trauma, the perioperative period, and obstetrics. In trauma, ML has been applied to early massive transfusion prediction, prehospital transfusion decision-making, and precise prediction in pediatric trauma. In the perioperative field, applications span specialties including traumatic brain injury, orthopedic surgery, cardiovascular and major vascular surgery, and hepatic surgery. In obstetrics, models can effectively predict postpartum hemorrhage and transfusion requirements associated with cesarean section. Studies have shown that algorithms such as random forest, gradient boosting machines, and deep neural networks achieve area under the receiver operating characteristic curve (AUC) values of 0.83-0.98 in massive transfusion prediction, 0.75-0.97 in perioperative scenarios, and 0.80-0.89 in obstetric transfusion prediction—significantly outperforming traditional scoring tools. However, current studies are generally limited by single-center retrospective designs, insufficient external validation, and inadequate reporting standards; limited model interpretability and challenges in clinical integration further constrain practical translation. Future research should focus on constructing multicenter data cohorts, integrating multimodal data, conducting prospective implementation studies, and deeply embedding models within electronic health record systems, thereby advancing the application of ML to optimize clinical transfusion decision-making.

ObjectiveTo investigate the association between sarcopenia and short-term prognosis in patients with acute-on-chronic liver failure （ACLF）， to assess the value of Model for End-Stage Liver Disease （MELD）， MELD combined with serum sodium concentration （MELD-Na）， MELD 3.0， and Chinese Group on the Study of Severe Hepatitis B （COSSH）-ACLF Ⅱ score in predicting the 90-day prognosis of ACLF patients， and to analyze the predictive gain of sarcopenia over traditional prognostic scoring models. MethodsA retrospective study was conducted among 219 patients with ACLF who were hospitalized in The Affiliated Hospital of Inner Mongolia Medical University， No. 2 Hospital of Hohhot， Hohhot First Hospital， and Inner Mongolia People’s Hospital from July 2018 to July 2024. L3 skeletal muscle index （L3-SMI） was measured and calculated based on abdominal computed tomography images， and sarcopenia was diagnosed based on L3-SMI. According to 90-day prognosis， the patients with ACLF were divided into survival group with 124 patients and death group with 95 patients. The chi-square test or the Fisher’s exact test was used for comparison of categorical data between two groups； the independent samples t-test was used for comparison of normally distributed continuous data between two groups， and the Mann-Whitney U test was used for comparison of non-normally distributed continuous data between two groups. The multivariate Cox regression analysis （stepwise backward approach） was used to identify independent risk factors for 90-day mortality in ACLF patients. The Kaplan-Meier method was used for survival analysis， and the Log-rank test was used for comparison between groups. The receiver operating characteristic curve was plotted to evaluate the predictive performance of each model， and the DeLong test， bootstrap internal validation， net reclassification improvement （NRI）， and integrated discrimination improvement （IDI） were used to assess the predictive gain of sarcopenia. ResultsThe multivariate Cox regression analysis showed that presence of sarcopenia （hazard ratio ［HR］=3.385， 95% confidence interval ［CI］： 1.722 — 6.657， P<0.05）， older age （HR=1.036， 95%CI： 1.017 — 1.056， P<0.05）， elevated alkaline phosphatase （HR=1.006， 95%CI： 1.004 — 1.009， P<0.05）， elevated total bilirubin （HR=1.003， 95%CI： 1.001 — 1.005， P<0.05）， elevated potassium （HR=1.581， 95%CI： 1.160 — 2.155， P<0.05）， elevated serum creatinine （HR=1.015， 95%CI： 1.007 — 1.024， P<0.05）， and prolonged prothrombin time （HR=1.035， 95%CI： 1.015 — 1.055， P<0.05） were independent risk factors for 90-day mortality in ACLF patients， while elevated albumin （HR=0.885， 95%CI： 0.837 — 0.935， P<0.05） was an independent protective factor against 90-day mortality. MELD， MELD-Na， MELD 3.0， and COSSH-ACLF Ⅱ scores had an area under the ROC curve （AUC） of 0.569， 0.570， 0.632， and 0.659， respectively， for predicting the 90-day prognosis of ACLF patients， suggesting that these scores had unsatisfactory performance； after they were respectively combined with sarcopenia， the AUC was increased to 0.702， 0.687， 0.723， and 0.728， respectively. The DeLong test， NRI， and IDI analyses showed the combined models had significantly better predictive performance （all P<0.05）. ConclusionSarcopenia is an independent risk factor for 90-day mortality in patients with ACLF. Traditional scoring models have limited predictive performance for 90-day prognosis in ACLF patients， and the combination with sarcopenia significantly improves predictive value， suggesting that sarcopenia can be used as an important supplementary indicator for prognostic evaluation of ACLF in clinical practice.

Objective: To investigate the coexistence of comorbidity of myopia, overweight/obesity and depressive symptoms among middle school students in Quzhou and its associated factors, so as to provide evidence for integrated prevention and control of common multiple health issues in students. Methods: From September to November 2023, a total of 5 867 middle school students from 6 counties (cities and districts) in Quzhou City were selected by stratified random cluster sampling. Physical and visual examinations were conducted, and the Center for Epidemiological Studies - Depression Scale (CES-D) along with a questionnaire on health status and influencing factors were completed. Multivariate Logistic regression was used to analyze the related factors of coexistence of myopia, overweight/obesity, and depressive symptoms among middle school students, and a nomogram model was constructed based on the results. Results: A total of 161 middle school students in Quzhou City were identified as having comorbid myopia, overweight/ obesity and depressive symptoms, with a detection rate of 2.74%. The results of multivariate Logistic regression analysis showed that the coexistence of myopia, overweight/obesity and depressive symptoms increased among middle school students with older age ( OR =1.11), a greater number unhealthy dietary behaviors (1,2,≥3; OR =2.40, 2.70, 4.63), insufficient sleep( OR =1.78) and alcohol consumption ( OR =2.11)(all P <0.05). Compared with no homework after class, those whose homework duration after class was 1 to < 2 hour had a lower risk of comorbidity of myopia, overweight/obesity and depressive symptoms ( OR =0.53, P <0.05). The results of the nomogram model showed that the AUC (95% CI ) was 0.71 (0.67-0.74). Conclusions The coexistence of myopia, overweight/obesity and depressive symptoms among middle school students in Quzhou City is related to age, sleeping, alcohol consumption, poor dietary behavior and the duration of after school homework. The nomogram model can assist in the early screening and intervention of multiple health issues among students.

OBJECTIVE To resolve account discrepancies caused by drug price adjustment in medical institution pharmacy management and reduce the time required for price adjustment. METHODS The problems existing in the drug price adjustment models of domestic medical institutions were investigated， and a drug price adjustment system was developed based on price- invoice synchronization mechanism. The system optimized the drug price adjustment process through batch number matching and real-time monitoring functionalities. The account consistency rate and price adjustment time were evaluated before and after system implementation. RESULTS A drug price adjustment system was successfully developed， featuring an innovative “synchronized entry and exit” mode， batch number matching， real-time monitoring， intelligent automation， and electronic traceability. After implementation， the account consistency rate for Western medicines increased from 86.89% （86.66%， 89.63%） to 100% （100%， 100%） （P＝0.005）， while Chinese patent medicines and herbal medicines maintained a 100% （100%， 100%） account consistency rate. Concurrently， the drug price adjustment time significantly decreased from 6.00 （5.00， 7.00）d to 2.50 （1.50， 3.00） d （P＜ 0.001）. CONCLUSIONS The developed system significantly improves account consistency， shortens price adjustment time， and demonstrates notable innovation and practical utility.

The Chinese Medical Association was established in 1915 and is an important social force for the development of medical science and technology and health care in China. The Hematology Branch of the Chinese Medical Association was established in 1980. With the support of the association's industry university research platform, it has made achievements such as the "Shanghai Protocol" for acute promyelocytic leukemia and the "Beijing Protocol" for hematopoietic stem cell transplantation, which have rewritten international guidelines and promoted China's hematology from its inception to international leadership. The article reviews the development process of diagnosis and treatment of hematological diseases, with a focus on the key role played by the Chinese Medical Association in the development of hematology in China.