PURPOSE: Intertrochanteric fracture (ITF) classification is crucial for surgical decision-making. However, orthopedic trauma surgeons have shown lower accuracy in ITF classification than expected. The objective of this study was to utilize an artificial intelligence (AI) method to improve the accuracy of ITF classification. METHODS: We trained a network called YOLOX-SwinT, which is based on the You Only Look Once X (YOLOX) object detection network with Swin Transformer (SwinT) as the backbone architecture, using 762 radiographic ITF examinations as the training set. Subsequently, we recruited 5 senior orthopedic trauma surgeons (SOTS) and 5 junior orthopedic trauma surgeons (JOTS) to classify the 85 original images in the test set, as well as the images with the prediction results of the network model in sequence. Statistical analysis was performed using the SPSS 20.0 (IBM Corp., Armonk, NY, USA) to compare the differences among the SOTS, JOTS, SOTS + AI, JOTS + AI, SOTS + JOTS, and SOTS + JOTS + AI groups. All images were classified according to the AO/OTA 2018 classification system by 2 experienced trauma surgeons and verified by another expert in this field. Based on the actual clinical needs, after discussion, we integrated 8 subgroups into 5 new subgroups, and the dataset was divided into training, validation, and test sets by the ratio of 8:1:1. RESULTS: The mean average precision at the intersection over union (IoU) of 0.5 (mAP50) for subgroup detection reached 90.29%. The classification accuracy values of SOTS, JOTS, SOTS + AI, and JOTS + AI groups were 56.24% ± 4.02%, 35.29% ± 18.07%, 79.53% ± 7.14%, and 71.53% ± 5.22%, respectively. The paired t-test results showed that the difference between the SOTS and SOTS + AI groups was statistically significant, as well as the difference between the JOTS and JOTS + AI groups, and the SOTS + JOTS and SOTS + JOTS + AI groups. Moreover, the difference between the SOTS + JOTS and SOTS + JOTS + AI groups in each subgroup was statistically significant, with all p < 0.05. The independent samples t-test results showed that the difference between the SOTS and JOTS groups was statistically significant, while the difference between the SOTS + AI and JOTS + AI groups was not statistically significant. With the assistance of AI, the subgroup classification accuracy of both SOTS and JOTS was significantly improved, and JOTS achieved the same level as SOTS. CONCLUSION In conclusion, the YOLOX-SwinT network algorithm enhances the accuracy of AO/OTA subgroups classification of ITF by orthopedic trauma surgeons.
Humans ; Hip Fractures/diagnostic imaging* ; Orthopedic Surgeons ; Algorithms ; Artificial Intelligence

Objective: To establish a machine learning-based precision blood donor recruitment model at the county level and assess its generalizability and applicability. Methods: A retrospective study was conducted using blood donation and SMS recruitment data from the Taicang Branch of the Suzhou Blood Center between 2019 and 2024. Multiple machine learning algorithms were employed, including extreme gradient boosting, support vector machine, k-nearest neighbor, logistic regression, decision tree, random forest, and multilayer perceptron. These were combined with techniques such as synthetic minority oversampling, undersampling, and cost-sensitive learning (using MFE and MSFE loss functions). Model parameters were optimized through grid search to identify the best-performing model. Results: In a prospective comparative study against conventional methods, the machine learning models increased the recruitment success rate among high-willingness donors by an average of 129.15%, and the recruitment efficiency per SMS improved by 125.02% compared with the traditional method. Under full-scale SMS sending, the recruitment rate per SMS increased by 42.61%, and SMS sending efficiency improved by 31.77%, significantly enhancing recruitment performance. Conclusion: This study represents the first application of a machine learning-based precision donor recruitment model at the county-level in China. The precise recruitment framework not only improves recruitment efficiency and reduces recruitment costs but also demonstrates strong scalability and generalizability. It provides a scientific and feasible intelligent pathway to ensure the safety and sustainability of the blood supply.

Objective A simple,sensitive and rapid ultra high performance liquid chromatography tandem mass spectrometry(UPLC-MS/MS)method was developed and validated for the determination of ertapenem in human plasma.Methods Using ertapenem-D4 as internal standard,the protein in plasma was precipitated with acetonitrile;chromatographic column:ACQUITY HSS T3(2.1 mm × 50.0 mm,1.8 μm);the mobile phase was 0.1％formic acid aqueous solution(containing 2 mmol·L-1 ammonium formate)-acetonitrile(0.1％formic acid),using a gradient elution;flow rate:0.4 mL·min-1,injection volume:1 μL,column temperature:45 ℃,the analysis time was 4.5 min,the scanning mode is positive ion selective reaction monitoring mode(SRM)with an electric spray ion source(ESI).The specificity,standard curve and lower limit of quantification,precision and recovery,matrix effect,dilution effect and stability were investigated.Results Ertapenem had a good linearity within 0.5-80.0μg·mL-1,and the standard curve was y=4.25 × 10-1x-2.64× 10-2(r2=0.999 0),the lower limit of quantification was 0.5 μg·mL-1,the relative standard deviation within and between batches is 1.39％-4.15％.The extraction recovery rate was 58.36％-64.57％,and the relative standard deviation of dilution effect was 3.30％,and the matrix effect was 99.71％-103.23％.The relative standard deviation of room temperature,repeated freeze-thaw,4 ℃,and long-term stability are all less than 10％.Conclusion The method is sensitive,rapid and specific,which is suitable for clinical monitoring of Ertapenem.

The effect of porcine SIRT5 on replication of foot and mouth disease virus type O(FMDV-O)and the underlying regulatory mechanism were investigated.Western blot and RT-qPCR analyses were employed to monitor expression of endoge-nous SIRT5 in PK-15 cells infected with FMDV-O.Three pairs of SIRT5-specific siRNAs were synthesized.Changes to SIRT5 and FMDV-O protein and transcript levels,in addition to virus copy numbers,were measured by western blot and RT-qPCR analyses.PK-15 cells were transfected with a eukaryotic SIRT5 expression plasmid.Western blot and RT-qPCR analyses were used to explore the impact of SIRT5 overexpression on FMDV-O replication.Meanwhile,RT-qPCR analysis was used to detect the effect of SIRT5 overexpression on the mRNA expression levels of type I interferon-stimulated genes induced by SeV and FMDV-O.The results showed that expression of SIRT5 was up-regulated in PK-15 cells infected with FMDV-O and siRNA interfered with SIRT5 to inhibit FMDV-O replication.SIRT5 overexpression promoted FMDV-O replication.SIRT5 over-expression decreased mRNA expression levels of interferon-stimulated genes induced by SeV and FMDV-O.These results suggest that FMDV-O infection stimulated expression of SIRT5 in PK-15 cells,while SIRT5 promoted FMDV-O rep-lication by inhibiting production of type I interferon-stimula-ted genes.These findings provide a reference to further ex-plore the mechanism underlying the ability of porcine SIRT5 to promote FMDV-O replication.

This study systematically reviewed the randomized controlled trial(RCT) of traditional Chinese medicine(TCM) treatment of coronary heart disease patients with angina pectoris after percutaneous coronary intervention(PCI). The basic elements of these RCTs, including sample size and estimation method, randomizing scheme, allocation concealment, blind method implementation, data integrity, statistical method, TCM syndrome, intervention measures, treatment course, follow-up time, and outcome indicators, were analyzed to provide reference for the design of future RCT and the clinical application of TCM in treating angina pectoris after PCI. CNKI, Wanfang, VIP, SinoMed, PubMed, EMbase, Cochrane Library, Web of Science, ClinicalTrials.gov, and Chinese Clinical Trial Registry were searched for the RCT about TCM treatment of coronary heart disease patients with angina pectoris after PCI according to pre-defined criteria, with the time interval from inception to January 31, 2024. A total of 188 RCTs were included, of which 184 were clinical research articles and 4 were clinical trial registration schemes. These RCTs involved a total of 15 521 patients, with an average sample size of 83 patients and a maximum sample size of 248 patients. Among them, 126 RCTs reported TCM syndromes, the top three of which were Qi deficiency and blood stasis(38.89%), phlegm combined with stasis(17.46%), and Qi stagnation and blood stasis(9.52%). The control group received guideline-directed medical therapy(GDMT) or GDMT combined with placebo, and the treatment group received GDMT combined with TCM. The treatment mainly lasted for 4-8 weeks, most of the RCTs did not set the follow-up period or the follow-up period was unknown. A total of 160 outcome indicators were used, with the total frequency of 1 348. According to functional attributes, the outcome indicators can be categorized into 6 groups: symptoms/signs(403, 29.90%), TCM syndromes/symptoms(182, 13.50%), physical and chemical examination(468, 34.72%), quality of life(89, 6.60%), long-term prognosis(5, 0.37%), and safety evaluation(201, 14.91%). The clinical trial design of TCM intervention in angina pectoris after PCI of coronary heart disease is becoming more and more rigorous, while it remains to be improved. It is expected that more clinical trial schemes with rigorous design and taking into account the TCM advantages can be adopted in the future to provide a basis for the TCM treatment of angina pectoris after PCI of coronary heart disease.
Humans ; Randomized Controlled Trials as Topic ; Angina Pectoris/drug therapy* ; Coronary Disease/drug therapy* ; Percutaneous Coronary Intervention ; Medicine, Chinese Traditional ; Drugs, Chinese Herbal/administration & dosage* ; Male ; Treatment Outcome ; Female

Objective: To identify the predisposing factors, clinical characteristics, and risk factors of disease progression to establish a novel predictive survival model and evaluate its application value for hepatitis B virus-related acute-on-chronic liver failure. Methods: 153 cases of HBV-ACLF were selected according to the guidelines for the diagnosis and treatment of liver failure (2018 edition) of the Chinese Medical Association Hepatology Branch. Predisposing factors, the basic liver disease stage, therapeutic drugs, clinical characteristics, and factors affecting survival status were analyzed. Cox proportional hazards regression analysis was used to screen prognostic factors and establish a novel predictive survival model. The receiver operating characteristic curve (ROC) was used to evaluate predictive value with the Model for End-Stage Liver Disease (MELD) and the Chronic Liver Failure Consortium Acute-on-Chronic Liver Failure score (CLIF-C ACLF). Results: 80.39% (123/153) based on hepatitis B cirrhosis had developed ACLF. HBV-ACLF's main inducing factors were the discontinuation of nucleos(t)ide analogues (NAs) and the application of hepatotoxic drugs, including Chinese patent medicine/Chinese herbal medicine, non-steroidal anti-inflammatory drugs, anti-tuberculosis drugs, central nervous system drugs, anti-tumor drugs, etc. 34.64% of cases had an unknown inducement. The most common clinical symptoms at onset were progressive jaundice, poor appetite, and fatigue. The short-term mortality rate was significantly higher in patients complicated with hepatic encephalopathy, upper gastrointestinal hemorrhage, hepatorenal syndrome, and infection (P < 0.05). Lactate dehydrogenase, albumin, the international normalized ratio, the neutrophil-to-lymphocyte ratio, hepatic encephalopathy, and upper gastrointestinal bleeding were the independent predictors for the survival status of patients. The LAINeu model was established. The area under the curve for evaluating the survival of HBV-ACLF was 0.886, which was significantly higher than the MELD and CLIF-C ACLF scores (P < 0.05), and the prognosis was worse when the LAINeu score ≥ -3.75. Conclusion: Discontinuation of NAs and the application of hepatotoxic drugs are common predisposing factors for HBV-ACLF. Hepatic decompensation-related complications and infection accelerate the disease's progression. The LAINeu model can predict patient survival conditions more accurately.
Humans ; Hepatitis B virus ; Hepatic Encephalopathy/complications* ; Acute-On-Chronic Liver Failure/diagnosis* ; End Stage Liver Disease/complications* ; Severity of Illness Index ; Risk Factors ; ROC Curve ; Prognosis ; Retrospective Studies

Objective: To explore the relationship between low density lipoprotein cholesterol (LDL-C)/high density lipoprotein cholesterol (HDL-C) ratio with the severity of coronary artery disease and 2-yeat outcome in patients with premature coronary heart disease. Methods: This prospective, multicenter, observational cohort study is originated from the PROMISE study. Eighteen thousand seven hundred and one patients with coronary heart disease (CHD) were screened from January 2015 to May 2019. Three thousand eight hundred and sixty-one patients with premature CHD were enrolled in the current study. According to the median LDL-C/HDL-C ratio (2.4), the patients were divided into two groups: low LDL-C/HDL-C group (LDL-C/HDL-C≤2.4, n=1 867) and high LDL-C/HDL-C group (LDL-C/HDL-C>2.4, n=1 994). Baseline data and 2-year major adverse cardiovascular and cerebrovascular events (MACCE) were collected and analyzed in order to find the differences between premature CHD patients at different LDL-C/HDL-C levels, and explore the correlation between LDL-C/HDL-C ratio with the severity of coronary artery disease and MACCE. Results: The average age of the low LDL-C/HDL-C ratio group was (48.5±6.5) years, 1 154 patients were males (61.8%); the average age of high LDL-C/HDL-C ratio group was (46.5±6.8) years, 1 523 were males (76.4%). The number of target lesions, the number of coronary artery lesions, the preoperative SNYTAX score and the proportion of three-vessel coronary artery disease in the high LDL-C/HDL-C group were significantly higher than those in the low LDL-C/HDL-C group (1.04±0.74 vs. 0.97±0.80, P=0.002; 2.04±0.84 vs. 1.85±0.84, P<0.001; 13.81±8.87 vs. 11.70±8.05, P<0.001; 36.2% vs. 27.4%, respectively, P<0.001). Correlation analysis showed that there was a significant positive correlation between LDL-C/HDL-C ratio and preoperative SYNTAX score, the number of coronary artery lesions, the number of target lesions and whether it was a three-vessel coronary artery disease (all P<0.05). The 2-year follow-up results showed that the incidence of MACCE was significantly higher in the high LDL-C/HDL-C group than that in the low LDL-C/HDL-C group (6.9% vs. 9.1%, P=0.011). There was no significant difference in the incidence of all-cause death, cardiac death, myocardial infarction, stroke, revascularization and bleeding between the two groups. Cox multivariate regression analysis showed that the LDL-C/HDL-C ratio has no correlation with 2-year MACCE, death, myocardial infarction, revascularization, stroke and bleeding events above BARC2 in patients with premature CHD. Conclusion: High LDL-C/HDL-C ratio is positively correlated with the severity of coronary artery disease in patients with premature CHD. The incidence of MACCE of patients with high LDL-C/HDL-C ratio is significantly higher during 2 years follow-up; LDL-C/HDL-C ratio may be an indicator for evaluating the severity of coronary artery disease and long-term prognosis in patients with premature CHD.
Male ; Humans ; Adult ; Middle Aged ; Female ; Coronary Artery Disease/complications* ; Cholesterol, HDL ; Cholesterol, LDL ; Prospective Studies ; Myocardial Infarction/etiology* ; Stroke ; Risk Factors

Objective: To construct a cervical cancer risk prediction model based on nested case-control study design and Yinzhou Health Information Platform in Ningbo, and provide reliable reference for self-risk assessment of cervical cancer in local women. Methods: In local women aged 25-75 years old who had no history of cervical cancer registered in Yinzhou before October 31, 2018, a follow up was conducted for at least three years, the patients who developed cervical cancer during the follow up period were selected as the case group and matched with a control group at a ratio of 1∶10. The prediction indicators before the onset was used in model construction. Variables were selected by Lasso-logistic regression, the variables with non-zero β were selected to fit the logistic regression model and Bootstrap was used for internal validation. The discrimination of the model was evaluated by area under the receiver operating characteristic curve(AUROC), and the calibration was evaluated by calibration curve and Hosmer-Lemeshow test. Results: The prediction indicators included in the final model were age, smoking status, history of cervicitis, history of adenomyosis, HPV testing, and thinprep cytologic test. The AUROC calculated in the internal validation was 0.740 (95%CI:0.739-0.740), and the calibration curve was almost identical with the ideal curve, P=0.991 in Hosmer-Lemeshow test, indicating that the model discrimination and calibration were good. Conclusions: In this study, a simple and practical cervical cancer risk prediction model was developed. The model can be used in general population with strong interpretability, good discrimination and calibration in internal validation, which can provide a reference for women to assess their risk of cervical cancer.

ObjectTo observe the clinical efficacy of Huangqin Beimutang on chronic rhinosinusitis in children. MethodA randomized controlled trial （RCT） was conducted on 70 children who met the criteria for chronic rhinosinusitis， with 35 cases in the Chinese medicine group and 35 cases in the western medicine group. In the western medicine group，children received mometasone furoate nasal spray，one spray per nostril，once a day for two weeks， and also received a small dose of azithromycin suspension at 4 mg·kg^-1·d^-1，once a day，3 days a week for 2 weeks. The children in the Chinese medicine group were treated with oral Huangqin Beimutang，one dose per day for 2 weeks. Before and after treatment，the scores of primary symptoms and signs of traditional Chinese medicine （TCM），visual analogue scale （VAS） symptom scores，sinus computed tomography （CT） efficacy scores，and clinical efficacy of TCM syndromes in the two groups were evaluated，and the occurrence of adverse events was recorded. ResultThe total effective rate of clinical efficacy of TCM syndrome in the Chinese medicine group was 88.57% （31/35）， which was higher than 71.43% （25/35） in the western medicine group（χ²=8.458，P<0.05）. The VAS scores， scores of TCM primary symptoms of nasal obstruction and runny nose， and physical sign scores in both groups were lower than those after treatment （P<0.01）. The above indicators in the Chinese medicine group were superior to those in the western medicine group after treatment （P<0.05， P<0.01）. Compared with the conditions before treatment， there was no significant improvement in headache in the western medicine group， while the headache score in the Chinese medicine group decreased after treatment （P<0.01）. The CT scores of the two groups showed a downward trend， but the difference was not statistically significant. There were no adverse reactions during treatment in both groups. ConclusionHuangqin Beimutang can effectively improve the clinical symptoms of patients with chronic rhinosinusitis， and it is safe and effective.