Objective: To investigate the factors influencing intraoperative blood transfusion in patients with hip fractures and to develop a machine learning (ML) model for predicting this risk. Methods: A total of 424 patients with hip fractures who underwent surgical treatment between November 2022 and March 2025 in our hospital were selected. Key feature variables of intraoperative blood transfusion risk were identified using the Boruta algorithm. Four different ML algorithms—support vector machine (SVM), linear discriminant analysis (LDA), mixed discriminant analysis (MDA), and extreme gradient boosting (XGBoost)—were used to develop predictive models for intraoperative blood transfusion risk. The predictive performance of the four ML models were evaluated using accuracy, precision, receiver operating characteristic (ROC) curves, precision-recall curves (PRC), precision-recall gain curves (PRGC), and F1 scores. Shapley additive interpretation (SHAP) was used to interpret the final model. Results: Among the 424 patients, 77(18.2%) received intraoperative blood transfusion. The Boruta algorithm identified albumin (ALB), activated partial thromboplastin time (APTT), types of anesthesia, types of fracture, and hemoglobin (Hb) as key feature variables for predicting intraoperative blood transfusion risk. In model evaluation, the SVM model outperforms the other three models across multiple metrics, including the area under the receiver operating characteristic curve (AUC), recall, recall gain, accuracy, precision, F1 score, and the area under the precision-recall curve (PRC-AUC). The SVM model, interpreted and visualized based on SHAP values, effectively predicted intraoperative blood transfusion risk in patients with hip fracture. A visual online application was developed based on the SVM model (https://pbo-nomogram.shinyapps.io/blood/). Conclusion: Preoperative low ALB and Hb levels, prolonged APTT, general anesthesia, and intertrochanteric fractures are risk factors for intraoperative blood transfusion in hip fracture patients. The risk prediction model for intraoperative blood transfusion constructed based on the SVM algorithm has optimal performance, which provides new ideas and methods for the clinical early identification of hip fracture patients with high transfusion risk and the implementation of targeted interventions.

Jiegeng decoction is a classic prescription composed of two Chinese medicinal herbs： Platycodon grandiflorum and Glycyrrhiza uralensis. It has the efficacy of diffusing lung qi， resolving phlegm， relieving sore throat and discharging pus， and is commonly used in the treatment of respiratory diseases such as cough and pharyngodynia. This article reviews the chemical components， pharmacological mechanisms and clinical applications of Jiegeng decoction. It was found that Jiegeng decoction contains triterpenoid saponins， flavonoids， glycosides， acids， and other components， with platycodin D， platycodin D2， glycyrrhizic acid， glycyrrhetinic acid， liquiritin， etc.， serving as the main active pharmaceutical ingredients. Jiegeng decoction and its chemical constituents exert anti-inflammatory effects by inhibiting signaling pathways such as nuclear factor-κB and mitogen- activated protein kinases， and demonstrate anti-tumor activities through mechanisms like modulating the tumor immune microenvironment and promoting cancer cell apoptosis. Additionally， it exhibits various pharmacological actions including antibacterial， antiviral， and antioxidant effects. Clinically， Jiegeng decoction， its modified prescription and compound combinations are widely used in the treatment of respiratory diseases such as cough， pneumonia， and pharyngitis， as well as digestive system disorders like constipation.

Purpose: The genomic characteristics of uterine sarcomas have not been fully elucidated. This study aimed to explore the genomic landscape of the uterine sarcomas (USs). Materials and Methods: Comprehensive genomic analysis through RNA-sequencing was conducted. Gene fusion, differentially expressed genes (DEGs), signaling pathway enrichment, immune cell infiltration, and prognosis were analyzed. A deep learning model was constructed to predict the survival of US patients. Results: A total of 71 US samples were examined, including 47 endometrial stromal sarcomas (ESS), 18 uterine leiomyosarcomas (uLMS), three adenosarcomas, two carcinosarcomas, and one uterine tumor resembling an ovarian sex-cord tumor. ESS (including high-grade ESS [HGESS] and low-grade ESS [LGESS]) and uLMS showed distinct gene fusion signatures; a novel gene fusion site, MRPS18A–PDC-AS1 could be a potential diagnostic marker for the pathology differential diagnosis of uLMS and ESS; 797 and 477 uterine sarcoma DEGs (uDEGs) were identified in the ESS vs. uLMS and HGESS vs. LGESS groups, respectively. The uDEGs were enriched in multiple pathways. Fifteen genes including LAMB4 were confirmed with prognostic value in USs; immune infiltration analysis revealed the prognositic value of myeloid dendritic cells, plasmacytoid dendritic cells, natural killer cells, macrophage M1, monocytes and hematopoietic stem cells in USs; the deep learning model named Max-Mean Non-Local multi-instance learning (MMN-MIL) showed satisfactory performance in predicting the survival of US patients, with the area under the receiver operating curve curve reached 0.909 and accuracy achieved 0.804. Conclusion USs harbored distinct gene fusion characteristics and gene expression features between HGESS, LGESS, and uLMS. The MMN-MIL model could effectively predict the survival of US patients.

Purpose: The genomic characteristics of uterine sarcomas have not been fully elucidated. This study aimed to explore the genomic landscape of the uterine sarcomas (USs). Materials and Methods: Comprehensive genomic analysis through RNA-sequencing was conducted. Gene fusion, differentially expressed genes (DEGs), signaling pathway enrichment, immune cell infiltration, and prognosis were analyzed. A deep learning model was constructed to predict the survival of US patients. Results: A total of 71 US samples were examined, including 47 endometrial stromal sarcomas (ESS), 18 uterine leiomyosarcomas (uLMS), three adenosarcomas, two carcinosarcomas, and one uterine tumor resembling an ovarian sex-cord tumor. ESS (including high-grade ESS [HGESS] and low-grade ESS [LGESS]) and uLMS showed distinct gene fusion signatures; a novel gene fusion site, MRPS18A–PDC-AS1 could be a potential diagnostic marker for the pathology differential diagnosis of uLMS and ESS; 797 and 477 uterine sarcoma DEGs (uDEGs) were identified in the ESS vs. uLMS and HGESS vs. LGESS groups, respectively. The uDEGs were enriched in multiple pathways. Fifteen genes including LAMB4 were confirmed with prognostic value in USs; immune infiltration analysis revealed the prognositic value of myeloid dendritic cells, plasmacytoid dendritic cells, natural killer cells, macrophage M1, monocytes and hematopoietic stem cells in USs; the deep learning model named Max-Mean Non-Local multi-instance learning (MMN-MIL) showed satisfactory performance in predicting the survival of US patients, with the area under the receiver operating curve curve reached 0.909 and accuracy achieved 0.804. Conclusion USs harbored distinct gene fusion characteristics and gene expression features between HGESS, LGESS, and uLMS. The MMN-MIL model could effectively predict the survival of US patients.

Purpose: The genomic characteristics of uterine sarcomas have not been fully elucidated. This study aimed to explore the genomic landscape of the uterine sarcomas (USs). Materials and Methods: Comprehensive genomic analysis through RNA-sequencing was conducted. Gene fusion, differentially expressed genes (DEGs), signaling pathway enrichment, immune cell infiltration, and prognosis were analyzed. A deep learning model was constructed to predict the survival of US patients. Results: A total of 71 US samples were examined, including 47 endometrial stromal sarcomas (ESS), 18 uterine leiomyosarcomas (uLMS), three adenosarcomas, two carcinosarcomas, and one uterine tumor resembling an ovarian sex-cord tumor. ESS (including high-grade ESS [HGESS] and low-grade ESS [LGESS]) and uLMS showed distinct gene fusion signatures; a novel gene fusion site, MRPS18A–PDC-AS1 could be a potential diagnostic marker for the pathology differential diagnosis of uLMS and ESS; 797 and 477 uterine sarcoma DEGs (uDEGs) were identified in the ESS vs. uLMS and HGESS vs. LGESS groups, respectively. The uDEGs were enriched in multiple pathways. Fifteen genes including LAMB4 were confirmed with prognostic value in USs; immune infiltration analysis revealed the prognositic value of myeloid dendritic cells, plasmacytoid dendritic cells, natural killer cells, macrophage M1, monocytes and hematopoietic stem cells in USs; the deep learning model named Max-Mean Non-Local multi-instance learning (MMN-MIL) showed satisfactory performance in predicting the survival of US patients, with the area under the receiver operating curve curve reached 0.909 and accuracy achieved 0.804. Conclusion USs harbored distinct gene fusion characteristics and gene expression features between HGESS, LGESS, and uLMS. The MMN-MIL model could effectively predict the survival of US patients.

As a patented characteristic medicine of Yi ethnic minority， Pingxuan capsules have the effects of nourishing the liver and kidney， pacifying the liver， and subduing Yang. With the main indications of dizziness， headache， palpitations， tinnitus， insomnia， dreaminess， waist and knee soreness caused by liver-kidney deficiency and liver Yang upward disturbance， Pingxuan capsules are widely used in the treatment of posterior circulation ischemic vertigo， vestibular migraine， benign paroxysmal positional vertigo. However， the current knowledge is limited regarding the efficacy， syndrome differentiation， and safety of this medicine. On the basis of summarizing the experience of clinicians and the existing evidence， this study invites clinical experts of traditional Chinese and Western medicine， pharmaceutical experts， and methodological experts from relevant fields across China to conduct evidence-based evaluation of Pingxuan capsules. The evaluation follows the Specifications for the Development of Clinical Expert Consensus on Chinese Patent Medicines issued by the Standardization Office of the China Association of Chinese Medicine， and reaches 5 recommendations and 16 consensus suggestions. The consensus clarifies the clinical applications， efficacy， dose， course of treatment， combination of medicines， precautions， and contraindications of Pingxuan capsules in the treatment of vertigo and explains the safety of clinical application. This consensus is applicable to clinicians （traditional Chinese medicine， Western medicine， and integrated traditional Chinese and Western medicine） and pharmacists in tertiary hospitals， secondary hospitals， and community-level medical and health institutions across China， providing a reference for the rational use of Pingxuan capsules in the treatment of vertigo. It is hoped that the promotion of this consensus can facilitate the rational use of drugs in clinical practice， reduce the risk of drug use， and give full play to the advantages of Pingxuan capsules in the treatment of vertigo diseases. This consensus has been reviewed and published by the China Association of Chinese Medicine， with the number GS/CACM330-2023.

Jiegengtang is a basic formula for treating sore throat and cough. By means of bibliometrics， this study conducted a textual research and analysis on the key information such as formula origin， decocting methods， and clinical application of Jiegengtang. After the research， it can be seen that Jiegengtang is firstly contained in Treatise on Febrile and Miscellaneous Disease， which is also known as Ganjietang， and it has been inherited and innovated by medical practitioners of various dynasties in later times. The origins of Chinese medicines in this formula is basically clear， Jiegeng is the dried roots of Platycodon grandiflorum， Gancao is the dried roots and rhizomes of Glycyrrhiza uralensis， the two medicines are selected raw products. The dosage is 27.60 g of Glycyrrhizae Radix et Rhizoma and 13.80 g of Platycodonis Radix， decocted with 600 mL of water to 200 mL， taken warmly after meals， twice a day， 100 mL for each time. In ancient times， Jiegengtang was mainly used for treating Shaoyin-heat invasion syndrome， with cough and sore throat as its core symptoms. In modern clinical practice， Jiegengtang is mainly used for respiratory diseases such as pharyngitis， esophagitis， tonsillitis and lung abscess， especially for pharyngitis and lung abscess with remarkable efficacy. This paper can provide literature reference basis for the modern clinical application and new drug development of Jiegengtang.

Jiegengtang is a basic formula for treating sore throat and cough. By means of bibliometrics， this study conducted a textual research and analysis on the key information such as formula origin， decocting methods， and clinical application of Jiegengtang. After the research， it can be seen that Jiegengtang is firstly contained in Treatise on Febrile and Miscellaneous Disease， which is also known as Ganjietang， and it has been inherited and innovated by medical practitioners of various dynasties in later times. The origins of Chinese medicines in this formula is basically clear， Jiegeng is the dried roots of Platycodon grandiflorum， Gancao is the dried roots and rhizomes of Glycyrrhiza uralensis， the two medicines are selected raw products. The dosage is 27.60 g of Glycyrrhizae Radix et Rhizoma and 13.80 g of Platycodonis Radix， decocted with 600 mL of water to 200 mL， taken warmly after meals， twice a day， 100 mL for each time. In ancient times， Jiegengtang was mainly used for treating Shaoyin-heat invasion syndrome， with cough and sore throat as its core symptoms. In modern clinical practice， Jiegengtang is mainly used for respiratory diseases such as pharyngitis， esophagitis， tonsillitis and lung abscess， especially for pharyngitis and lung abscess with remarkable efficacy. This paper can provide literature reference basis for the modern clinical application and new drug development of Jiegengtang.

Objective To investigate the value of enhanced MRI image features combined with apparent diffusion coefficient(ADC)in the differential diagnosis of primary hepatic mucosa-associated lymphoid tissue(MALT)lymphoma and hepatocellular carcinoma(HCC).Methods The clinical data of 10 patients with pathology-confirmed primary MALT lymphoma admitted in our hospital from January 1997 to May 2025 were retrospectively collected.Their enhanced MRI images were analyzed,mainly including the number of lesions,morphology,signal characteristics,enhancement methods,and presence or absence of vessel floating signs,and the ADC value was calculated in order to screen statistically significant variables.Firth regression analysis was used to screen independent predictors of primary MALT lymphoma in the liver.Receiver operating characteristic(ROC)curve was plotted,and the area under the curve(AUC)was calculated to evaluate the diagnostic efficacy.Results Compared with the HCC group,the primary MALT lymphoma group had significantly higher incidence in the females(P=0.026),alpha-fetoprotein(AFP)<8 ng/mL(P<0.001),lower T2WI signal(P=0.001),lower ADC value(P<0.001),and mostly continuously enhanced lesions(P<0.001),and more vessel floating signs(P=0.008).Univariate Firth regression analysis showed that sex(95%CI:1.36～52.10,P=0.020),T2 value(95%CI:3.89～5 121.00,P<0.001),AFP(95%CI:0～0.21,P<0.001),ADC value(95%CI:0～0.21,P<0.001),and dynamic reinforcement(95%CI:0～0.23,P<0.001),and vessel floating sign(95%CI:0～0.40,P=0.004)were diagnostic predictors for primary MALT lymphoma of the liver.Multivariate Firth regression analysis indicated that ADC value(95%CI:0～0.62,P=0.006),AFP(95%CI:0～0.047,P=0.01),and dynamic reinforcement(95%CI:0～0.39,P=0.005)were independent predictors for primary MALT in the liver.ROC curve analysis indicated that the AUC value of ADC value in diagnosing primary MALT lymphoma was 0.96,with a sensitivity of 0.8 and a specificity of 1.0,and the AUC value of AFP level in diagnosing primary MALT lymphoma was 0.85,with a sensitivity of 1.0 and a specificity of 0.7.The AUC value of dynamic reinforcement in diagnosing primary MALT lymphoma was 0.85,with a sensitivity of 0.8,and a specificity of 0.9.Conclusion Dynamic reinforcement and ADC value can be used as differential markers for primary MALT lymphoma and HCC,providing reliable reference for clinical preoperative evaluation.

Objective To investigate the relationship between preoperative blood glucose control and perioperative insulin resistance(IR)in patients with diabetes mellitus(DM)complicated by cervical cancer(CC)and its effect on prognosis.Methods A total of 100 patients were categorized into IR(n=61)and non-IR(n=39)groups based on their IR levels.Additionally,patients were classified into poor prognosis(n=34)and good prognosis(n=66)groups according to the occurrence of adverse events during the follow-up period.The clini-cal data of each group were compared to evaluate the association of glycosylated hemoglobin(HbA1c),fasting plasma glucose(FPG),and two-hour postprandial plasma glucose(2hPG)with perioperative IR,as well as correlation between HbA1c,FPG,and 2hPG levels and the homeostasis model assessment(HOMA)of IR with the risk of poor prognosis.Results HbA1c,FPG,2hPG,and HOMA-IR were identi-fied as risk factors for the prognosis of patients with DM and CC(P＜0.05).Compared with the respective control groups,the IR group and poor prognosis group had higher preoperative levels of HbA1C,FPG,and 2hPG(P＜0.05).Conclusion Poor preoperative blood glucose control is positively correlated with the risk of perioperative IR in patients with DM and CC.Moreover,HOMA-IR,HbA1c,FPG,and 2hPG are independent risk factors for poor prognosis in patients with DM and CC.