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: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 application effect of prone position ventilation combined with veno-venous extracorporeal membrane oxygenation (VV-ECMO) in the treatment of severe primary graft dysfunction (PGD) after lung transplantation. Methods The clinical data of 75 lung transplant recipients who developed severe PGD after lung transplantation and were treated with VV-ECMO from January 2021 to June 2024 at Wuxi People's Hospital Affiliated to Nanjing Medical University were collected. The patients with severe graft dysfunction after lung transplantation were divided into VV-ECMO group (control group, 45 cases) and prone position ventilation combined with VV-ECMO group (treatment group, 30 cases). The general data of the two groups of patients were compared, including the donors' clinical data (age, gender and oxygenation index, etc) and the recipients' clinical data [gender, age and body mass index (BMI), etc]. Cox regression analysis was used to analyze the influencing factors of the recipients' 30-day, 90-day and 180-day survival after surgery. The survival curves of the two groups of recipients were drawn using Kaplan-Meier method and compared using the log-rank test. Results The intensive care unit (ICU) stay time, ECMO application time and ventilator use time of control group were longer than those of treatment group. The proportion of male recipients and the BMI of control group were lower than those of treatment group. The 30-day, 90-day and 180-day survival of control group was worse than that of treatment group, and the differences were statistically significant (all P<0.05). The univariate Cox regression analysis of the recipients' 30-day survival after surgery showed that the recipients' BMI, history of diabetes, enlargement of the right atrium and right ventricle, intraoperative blood transfusion volume and intraoperative red blood cell transfusion volume were statistically significant (all P<0.05). The multivariate Cox regression analysis showed that the history of diabetes and enlargement of the right atrium and right ventricle were risk factors affecting the 30-day survival of lung transplant recipients (all P<0.05). The univariate Cox regression analysis of the recipients' 90-day survival after surgery showed that the recipients' BMI, history of diabetes, enlargement of the right atrium and right ventricle, intraoperative blood transfusion volume, intraoperative red blood cell transfusion volume and group variable were statistically significant (all P<0.05). The multivariate Cox regression analysis showed that the history of diabetes, enlargement of the right atrium and right ventricle and group variable were risk factors affecting the 90-day survival of lung transplant recipients (all P<0.05). The univariate Cox regression analysis of the recipients' 180-day survival after surgery showed that the recipients' BMI, history of diabetes, right atrium and right ventricle enlargement, intraoperative blood transfusion volume, intraoperative red blood cell transfusion volume and group variable were statistically significant (all P<0.05). The multivariate Cox regression analysis showed that the history of diabetes, enlargement of the right atrium and right ventricle and group variable were risk factors affecting the 180-day survival of lung transplant recipients (all P<0.05). The 30-day, 90-day and 180-day survival rates of control group were lower, and the differences between the two groups were statistically significant (all P<0.05), with a median survival time of 100 days in control group. Conclusions In the clinical treatment of severe PGD after lung transplantation, prone position ventilation combined with VV-ECMO may shorten ECMO application time, invasive ventilation time and ICU stay time, and improve the short-term prognosis of lung transplantation.

OBJECTIVE: To observe the effects of point-moxibustion with Zhuang medicinal thread on differentially expressed genes (DEGs) in the dorsal root ganglion (DRG), tissue morphology, and the expression of Fc epsilon RI (FcεRI) pathway proteins spleen tyrosine kinase (Syk) and membrane spanning 4-domain A2 (MS4A2) in rat model of postherpetic neuralgia (PHN), and to explore the potential mechanism by which this therapy alleviates pain sensitization. METHODS: Thirty-nine male Sprague-Dawley (SD) rats were randomly divided into a control group, a model group, and a moxibustion group, with 13 rats in each group. The PHN model was established in the model and moxibustion groups by intraperitoneal injection of resiniferatoxin. In the moxibustion group, bilateral L₄-L₆ "Jiaji" (EX-B2) points were treated with point-moxibustion with Zhuang medicinal thread from day 7 post-modeling, with two cones per acupoint per session, every other day for a total of 10 sessions. Mechanical withdrawal threshold (MWT) and thermal withdrawal latency (TWL) were measured at 1 day before modeling and on days 1, 4, 7, 13, 19, and 25 after modeling. After intervention, HE staining was used to observe DRG morphology. RNA sequencing was performed to analyze DEGs in DRG and conduct bioinformatics analysis. The expression of Syk and MS4A2 mRNA and proteins in the FcεRI pathway in DRG was detected by quantitative PCR and Western blot. RESULTS: Compared with the control group, the model group exhibited decreased MWT (P<0.05) and increased TWL (P<0.05); histopathological analysis revealed neuronal atrophy, nuclear displacement, and intracellular vacuoles, with a slightly loose arrangement; the RNA-Seq identified 3,207 DEGs (1,997 upregulated and 1,210 downregulated); the mRNA and protein expression levels of Syk and MS4A2 were significantly increased (P<0.01). Compared with the model group, the moxibustion group showed increased MWT (P<0.05) and decreased TWL (P<0.05), with relatively normal neuronal morphology; the RNA-Seq identified 426 DEGs (250 upregulated and 176 downregulated); the mRNA and protein expression levels of Syk and MS4A2 were significantly decreased (P<0.05). Venn diagram analysis identified 156 DEGs that showed a reversal in expression trends after treatment, including Syk and MS4A2, which are associated with pain sensitization. KEGG pathway analysis indicated that these DEGs were primarily enriched in the FcεRI pathway. CONCLUSION Point-moxibustion with Zhuang medicinal thread could alleviate pain sensitization in PHN rats, possibly by inhibiting the FcεRI signaling pathway and downregulating the expression of Syk and MS4A2.
Animals ; Rats, Sprague-Dawley ; Male ; Rats ; Moxibustion ; Neuralgia, Postherpetic/physiopathology* ; Syk Kinase/metabolism* ; Acupuncture Points ; Humans ; Ganglia, Spinal/metabolism* ; Signal Transduction

ObjectiveTo analyze the evolutionary characteristics and genetic variations of the HA (hemagglutinin) and NA (neuraminidase) genes of influenza A(H1N1) viruses in Shanghai during 2024, to investigate their transmission patterns, and to evaluate their potential impact on vaccine effectiveness. MethodsFrom January to October 2024, throat swab specimens were collected from influenza like illness (ILI) patients at 4 hospitals in Shanghai. Real-time fluorescence ploymerase chain reaction (RT-PCR) was used for virus detection and isolation of H1N1 influenza viruses. Forty influenza A(H1N1) virus strains were sequenced using Illumina NovaSeq 6000 platform, followed by phylogenetic analyses, genetic distance analysis, and amino acid variation analyses of HA and NA genes. ResultsPhylogenetic tree of the HA and NA genes revealed that the 40 influenza A(H1N1) virus strains circulating in Shanghai in 2024 exhibited no significant geographic clustering, with a broad origin of strains and complex transmission chains. Genetic distance analyses demonstrated that the average intra-group genetic distances of HA and NA genes among the Shanghai strains were 0.005 1±0.000 6 and 0.004 6±0.000 6, respectively, which were comparable to or higher than those observed in global surveillance strains. Both HA and NA genes displayed frequent mutations. Compared to the 2023‒2024 and 2024‒2025 Northern Hemisphere A(H1N1) vaccine strains (WHO-recommended), the HA proteins of 40 Shanghai strains exhibited amino acid substitutions at positions 120, 137, 142, 169, 216, 223, 260, 277, 356 and 451, with critical mutations at positions 137 and 142 located within the Ca2 antigenic determinant. Furthermore, mutations in the NA protein were observed at positions 13, 50, 200, 257, 264, 339 and 382. ConclusionThe genetic background of the 2024 Shanghai influenza A(H1N1) virus strains is complex and diverse, and antigenic variation may affect vaccine effectiveness. Therefore, it is recommended to enhance genomic surveillance of influenza viruses, evaluate vaccine suitability, and implement more targeted prevention and control strategies against imported influenza viruses.

Objective To explore the effects of Shuanglu Tongnao Formula on neuroinflammation in ischemic stroke (IS) rats via the P2X purinoceptor 7 receptor (P2X7R)/NLR family pyrin domain-containing 3 (NLRP3) pathway. Methods The rats were divided into five groups: the IS group, control group, Shuanglu Tongnao Formula group, P2X7R inhibitor brilliant blue G (BBG) group, and Shuanglu Tongnao Formula combined with P2X7R activator adenosine triphosphate (ATP) group, with 18 rats in each group. Except for the control group, rats in all other groups were used to construct an IS model using the suture method. After successful modeling, the drug was given once a day for 2 weeks. Neurological function scores and cerebral infarction volume ratios were measured in rats. Pathological examination of the ischemic penumbra brain tissue was performed. Immunofluorescence staining was used to quantify the proportions of microglia co-expressing both inducible nitric oxide synthase (iNOS) and ionized calcium-binding adapter molecule 1 (Iba1), as well as arginase 1 (Arg1) and Iba1, in the ischemic penumbra brain tissue. ELISA was used to detect tumor necrosis factor-alpha (TNF-α), transforming growth factor-beta (TGF-β), interleukin 6 (IL-6) and IL-10 in the ischemic penumbra brain tissue. Western blotting was used to measure P2X7R, NLRP3, and IL-1β proteins in the ischemic penumbra brain tissue. Results Compared with the control group, the IS group showed disordered neuronal arrangement, nuclear condensation, and obvious infiltration of inflammatory cells in the ischemic penumbra; significantly elevated neurological function scores, cerebral infarction volume ratios, proportions of microglia co-expressing iNOS and Iba1, and levels of TNF-α, IL-6, and P2X7R, NLRP3, IL-1β proteins; along with reduced proportions of microglia co-expressing Arg1 and Iba1 and levels of TGF-β and IL-10. Compared with the IS group, the Zhuang medicine Shuanglu Tongnao Formula and BBG groups demonstrated alleviated brain tissue damage; reduced neurological function scores, cerebral infarction volume ratios, proportions of microglia co-expressing iNOS and Iba1, and levels of TNF-α, IL-6, and P2X7R, NLRP3, IL-1β proteins; along with increased proportions of microglia co-expressing Arg1 and Iba1 and levels of TGF-β and IL-10. ATP reversed the effects of Zhuang medicine Shuanglu Tongnao Formula on microglial polarization and neuroinflammation in IS rats. Conclusion Zhuang medicine Shuanglu Tongnao Formula may promote the transformation of microglia from M1 type to M2 type by inhibiting the P2X7R/NLRP3 pathway, thereby improving neuroinflammation in IS rats.
Animals ; NLR Family, Pyrin Domain-Containing 3 Protein/metabolism* ; Receptors, Purinergic P2X7/metabolism* ; Male ; Drugs, Chinese Herbal/pharmacology* ; Rats ; Ischemic Stroke/pathology* ; Rats, Sprague-Dawley ; Disease Models, Animal ; Signal Transduction/drug effects* ; Neuroinflammatory Diseases/metabolism* ; Tumor Necrosis Factor-alpha/metabolism* ; Nitric Oxide Synthase Type II/metabolism* ; Interleukin-10/metabolism* ; Brain Ischemia/drug therapy* ; Microglia/metabolism*

Objective To discuss the clinical efficacy of catheter-directed thrombolysis(CDT)in treating acute pulmonary embolism(APE).Methods A total of 215 patients with APE,who were admitted to the Second Affiliated Hospital of Shandong First Medical University of China,were enrolled in this study.Pulmonary angiography was performed in all the patients.After the location of the thrombus was identified,the pigtail catheter was rotated so as to break the thrombus into small pieces,which was followed by local infusion of thrombolytic agent urokinase to make recanalization of the occluded pulmonary artery.The postoperative clinical symptoms,blood oxygen saturation,mean pulmonary artery pressure,BNP,D-dimer,RV/LV diameter ratio were compared with their preoperative values.PESI scoring was used to evaluate the severity of the pulmonary embolism.Patients with PESI grade-Ⅲ and PESI grade-Ⅳ were classified into medium-risk group,and patients with PESI grade-V were classified into higher-risk group.Results Symptom relief immediately after surgery was observed in 210 patients,complete recanalization of pulmonary artery was achieved in 200 patients,and partial recanalization of pulmonary artery was seen in 15 patients.The preoperative mean pulmonary artery pressure,blood oxygen saturation,BNP,D-dimer,RV/LV diameter ratio were(46.24±5.32)mmHg,(90.36±3.23)％,(8 000.12±750.56)pg/mL,(7.5±2.3)mg/L and(1.63±0.22)respectively;at one week after surgery the above indicators were(26.12±3.36)mmHg,(98.74±2.12)％,(240.35±33.52)pg/mL,(1.75±0.36)mg/L and(1.11±0.13)respectively;the differences were statistically significant(all P＜0.05).In the patients who had symptoms of hemoptysis,shock and syncope before surgery,all these symptoms were completely disappeared in one week after CDT,and the symptoms of dyspnea,chest pain,and palpitations were significantly relieved after CDT,the differences were statistically significant(all P＜0.05).The difference in survival time between different PESI grade groups was statistically significant(P＜0.05).No serious postoperative complications such as severe arrhythmia,cerebral hemorrhage,or gastrointestinal bleeding occurred.Postoperative 3-month CT pulmonary angiography(CTPA)showed that the main pulmonary artery was well visualized and no thrombus-produced filling defect shadow was detected.Conclusion For the treatment of APE,CDT can promptly and rapidly open the obstructed pulmonary artery lumen,restore pulmonary artery hemodynamics,and correct hypoxemia.Therefore,CDT is a safe,effective and quick treatment for APE.

Objective To evaluate the current radiation doses in pediatric non-cardiac interventional procedures, and analyze the associated clinical factors, and to provide data references for reducing pediatric radiation exposure. Methods We conducted a retrospective analysis of the radiation doses of children who had undergone non-cardiac interventional procedures at the interventional department of a tertiary pediatric hospital in Jinan from January 2022 to October 2024. The collected data included basic demographic information, surgical date, anatomical site, disease type, and radiation dose parameters (cumulative fluoroscopy time, cumulative dose area product in cine mode, cumulative air kerma, and the number of images acquired). The Kruskal-Wallis H test was used for comparative analysis between groups (P < 0.05 was considered statistically significant). Results Among the 475 included children, 99 cases (20.8%) had infantile hemangioma (median P_ka, 0.136 Gy·cm²; median K_a,r, 0.38 mGy), 235 cases (49.5%) had venous malformation (median P_ka, 9.82 Gy·cm²; median K_a,r, 40.99 mGy), 75 cases (15.8%) had lymphatic malformation (median P_ka, 0.06 Gy·cm²; median K_a,r, 0.18 mGy), 32 cases (6.7%) had retinoblastoma (median P_ka, 6.58 Gy·cm²; median K_a,r, 52.34 mGy), 12 cases (2.5%) had arteriovenous malformation (median P_ka, 42.3 Gy·cm²; median K_a,r, 162.87 mGy), and 22 cases (4.6%) had other vascular malformations (median P_ka, 21.7 Gy·cm²; median K_a,r, 89.1 mGy). There were significant differences between children with different disease types in the cumulative fluoroscopy time, cumulative dose area product in cine mode, cumulative air kerma at the patient entrance reference point, and the number of images acquired during non-cardiac interventional procedures (all P < 0.01). Conclusion This study presented the types and proportions of pediatric non-cardiac interventional procedures, evaluated the radiation dose levels of different surgical types, and analyzed the effects of weight and anatomical site on radiation exposure, which can be useful for preliminary assessment of radiation doses in pediatric non-cardiac interventional procedures.

Objective To analyze the medication rules and clinical experience of Qin Zujie in treating virtual labor based on data mining.Methods Outpatient medical records of Qin Zujie,diagnosed with deficiency syndrome at Ethnic Medicine Characteristic Diagnosis and Treatment Center,Guangxi International Zhuang Medical Hospital from January to December 2024 were selected.A standardized database was established and processed,yielding 148 clinical prescriptions containing 171 herbal ingredients.Frequency analysis,association rule analysis,and cluster analysis were employed to examine medication rules and clinical experience.Results The 20 Chinese herbal ingredients used more than 30 times each,with the first three being Zhigancao,Baizhu,Danggui.These herbs are primarily warm in nature,neutral in temperature,and slightly cold in effect,characterized by sweet,pungent,and bitter flavors.They mainly affect the spleen meridian and function to tonify deficiency,with Qi-tonifying herbs being the most common.Through association rule analysis,the most frequently combined pairs were Baizhu-Dangshen.Cluster analysis identified three core prescription clusters.Conclusion Qin Zujie's academic thought of treating virtual labor is to supplement deficiency as the main,detoxification as the auxiliary,and treat both the symptoms and the causes.

Objective To evaluate the effects of low-dose intrathecal morphine(ITM)combined with liposomal bupivacaine adductor canal block(LB-ACB)on postoperative analgesia and opioid-sparing efficacy in patients undergoing total knee arthroplasty(TKA).Methods In this randomized,double-blind,controlled trial,80 TKA patients were allocated to either an intervention group(ITM 0.1 mg+LB-ACB,n=40)or a control group(intrathecal saline+LB-ACB,n=40).Primary outcomes included resting/movement visual analog scale(VAS)scores at 6,12,24,48,and 72 hours postoperatively,48-hour morphine consumption,time to first rescue analgesia,and incidence of complications.Results(1)The intervention group showed significantly lower resting and movement VAS scores at 6,12,24,and 48 hours postoperatively compared with controls(all P<0.05),except at 72 hours(P>0.05).(2)The intervention group had a significant reduction in 48-hour morphine consumption(4.58±1.0 mg vs.9.34±4.8 mg,P=0.027),a significantly lower rescue analgesia rate(15.0%vs.47.5%,P=0.002),and a significantly prolonged time to first rescue analgesia(48.8±7.5 h vs.14.5±5.5 h,P<0.001).(3)The intervention group demonstrated a significant decrease in the incidence of nausea(from 15.0%to 35.0%,P=0.039)and vomiting(from 10.0%to 27.5%,P=0.045),but no significant differences were observed in the incidences of pruritus,urinary retention,or motor block(all P>0.05).Conclusion Low-dose ITM(0.1 mg)combined with LB-ACB significantly enhances early postoperative analgesia,reduces opioid consumption,and decreases nausea/vomiting risk,without increasing the risks of other complications.This regimen aligns with enhanced recovery after surgery(ERAS)principles.