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.

In recent years, hybrid brain-computer interfaces (BCIs) have gained significant attention due to their demonstrated advantages in increasing the number of targets and enhancing robustness of the systems. However, Existing studies usually construct BCI systems using intense auditory stimulation and strong central visual stimulation, which lead to poor user experience and indicate a need for improving system comfort. Studies have proved that the use of peripheral visual stimulation and lower intensity of auditory stimulation can effectively boost the user's comfort. Therefore, this study used high-frequency peripheral visual stimulation and 40-dB weak auditory stimulation to elicit steady-state visual evoked potential (SSVEP) and auditory steady-state response (ASSR) signals, building a high-comfort hybrid BCI based on weak audio-visual evoked responses. This system coded 40 targets via 20 high-frequency visual stimulation frequencies and two auditory stimulation frequencies, improving the coding efficiency of BCI systems. Results showed that the hybrid system's averaged classification accuracy was (78.00 ± 12.18) %, and the information transfer rate (ITR) could reached 27.47 bits/min. This study offers new ideas for the design of hybrid BCI paradigm based on imperceptible stimulation.
Brain-Computer Interfaces ; Humans ; Evoked Potentials, Visual/physiology* ; Acoustic Stimulation ; Photic Stimulation ; Electroencephalography ; Evoked Potentials, Auditory/physiology* ; Adult

Objective To explore the characteristics of fluid flow within loaded osteons under different boundary conditions.Methods The COMSOL Multiphysics software was used to establish a three-dimensional(3D)finite element model of osteons with different boundary conditions,and the variation rules of pore pressure and flow velocity of osteons under different inner wall pulsating blood pressures and outer wall elastic constraint conditions were analyzed.Results As the pulsatile blood pressure inside the osteon increased from 0 mmHg(1 mmHg=0.133 kPa)to 300 mmHg,the peak pore pressure within the osteon correspondingly increased from 26 kPa to 68 kPa.As the elastic constraint on the outer wall of osteons changed from being completely elastic to completely constrained,the peak pore pressure within osteons increased from 15 kPa to 26 kPa,and the peak flow velocity increased from 0.04 um/s to 0.07 um/s.Conclusions This study reveals the influence laws of changes in boundary conditions such as the pulsatile blood pressure on the inner wall and the elastic constraint on the outer wall of osteons on fluid flow characteristics within loaded osteons.These findings are conducive to a deeper understanding of the mechanical response mechanisms of bone tissues in both physiological and pathological states,and provide an important theoretical basrs for further researches on bone mechanotransduction.

Objective:To investigate the clinical efficacy of a self-detachable single-J internal stent drainage tube in the laparoscopic primary suture of the common bile duct for hepatolithiasis.Methods:Clinical data of 36 patients with hepatobiliary duct stones who underwent laparoscopic common bile duct primary suture combined with self-detached single J-type internal stent drainage at the First Affiliated Hospital of Xiamen University from April 2022 to April 2025 were retrospectively analyzed, including 17 males and 19 females, aged (54.3±8.7) years. All 36 patients underwent choledochoscopic stone extraction, primary common bile duct suture, and drainage with the self-expelling single-J internal stent. Total bilirubin, aspartate transaminase, and alanine transaminase before and 3 days after operation, as well as operation time, intraoperative blood loss, postoperative hospital stay, postoperative complications (bile leakage, cholangitis, intestinal obstruction, and stent retention), and stent expulsion time were collected.Results:All 36 patients successfully underwent the operation. Total bilirubin, aspartate transaminase, and alanine transaminase 3 days after operation showed significant improvement compared to preoperative levels (all P<0.05). The operation time was (86.5±22.6) min, intraoperative blood loss was 34.2 (13.7, 56.8) ml, and the postoperative hospital stay was (6.6±1.8) days. All single-J internal stents were spontaneously expelled via the anus between 6 and 21 days postoperatively, with the expulsion time of (10.7±2.1) days. No single J-type internal stent drainage tube was displaced into the bile duct in all cases, and there were no complications such as intestinal obstruction, bile leakage, cholangitis, or residual internal stent drainage tube. Conclusion:The self-detachable single-J internal stent drainage tube has been applied in the laparoscopic primary suture of the common bile duct for patients with hepatolithiasis, which demonstrated a good safety and effectiveness.

Objective To investigate the clinical prognosis value of the positivity rate of oligoclonal bands(OCB)and immunoglobulin G(IgG)level of cerebrospinal fluid(CSF)in severe encephalitis.Methods A total of 699 cases of encephalitis patients admitted to the Department of Neurology of the First Affiliated Hospital of Air Force Military Medical University,and Xijing 986 Hospital from January 2016 to October 2020 were enrolled.According to the severity of their diseases,these patients were divided into a mild(n=360)group and a severe(n=339)group.CSF and serum samples were collected from the patient at the time of admission,and the differences in cerebrocyte count,glucose contem,glucose content,chlorine content,IgG of CSF and OCB of CSF and serum were compared.According to the GOS score of patients with severe encephalitis at discharge,the patients were divided into good prognosis group(n=259)and poor prognosis group(n=80),and multivariate Logistic regression analysis was used to analyze factors that affected the prognosis of severe encephalitis patients,and the correlation between the OCB and IgG of CSF and prognosis of patients with severe encephalitis.The predictive value of CSF IgG for the prognosis of patients with severe encephalitis was tested,and receiver operating characteristic(ROC)curve was plotted.Results Compared to patients with mild encephalitis,patients with severe encephalitis had a higher proportion of fever,pulmonary infection,status epilepticus,and mechanical ventilation,and were more likely to be complicated by stroke and hydrocephalus,and the differences were statistically significant(χ2=5.319～245.179,all P<0.05).There were significant differences in the positive rate of cerebrocyte count,chlorine content,IgG content and OCB in cerebrospinal fluid between the two groups(Z=-3.623,-4.875,-3.518,χ2=6.581,all P<0.05).CSF OCB and CSF IgG were independent risk factors for poor prognosis in patients with severe encephalitis(Wald χ2=7.295,0.001,all P<0.05).A restrictive cubic spline plot showed a linear relationship between CSF IgG and poor prognosis.The AUC(95%CI)of CSF IgG was 0.754(0.632～0.876).Conclusion The CSF IgG content and positive rate of CSF OCB in patients with severe encephalitis with poor prognosis are higher than those in patients with good prognosis,and detecting these two indicators has certain reference value for the prognosis prediction of patients with severe encephalitis.

ObjectiveTo evaluate the effects of Tongnaoyin on the blood-brain barrier status and neurological impairment in acute ischemic stroke （AIS） patients with the syndrome of phlegm-stasis blocking collaterals by dynamic contrast-enhanced magnetic resonance imaging （DCE-MRI）. MethodsA total of 63 patients diagnosed with AIS in the Jiangsu Province Hospital of Chinese Medicine from October 2022 to December 2023 were enrolled in this study. According to random number table method，the patients were assigned into a control group （32 cases） and an observation group （31 cases）. The control group received conventional Western medical treatment，and the observation group took 200 mL Tongnaoyin after meals，twice a day from day 2 of admission on the basis of the treatment in the control group. After 7 days of treatment，the patients were examined by DCE-MRI. The baseline data for two groups of patients before treatment were compared. The National Institute of Health Stroke Scale （NIHSS） score and modified Rankin Scale （mRS） score were recorded before treatment and after 90 days of treatment for both groups. The rKtrans，rKep，and rVe values were obtained from the region of interest （ROI） of the infarct zone/mirror area and compared between the two groups. ResultsThere was no significant difference in the NIHSS or mRS score between the two groups before treatment. After 90 days of treatment，the NIHSS and mRS scores declined in both groups，and the observation group had lower scores than the control group （P<0.05）. After treatment，the rKtrans and rVe in the observation group were lower than those in the control group （P<0.01）. ConclusionCompared with conventional Western medical treatment alone，conventional Western medical treatment combined with Tongnaoyin accelerates the repair of the blood-brain barrier in AIS patients，thereby ameliorating neurological impairment after AIS to improve the prognosis.

Aortic dissection is a life-threatening cardiovascular disease with devastating complications and high mortality. It requires rapid and accurate diagnosis and a focus on prognosis. Many laboratory tests are routinely performed in patients with aortic dissection including D-dimer, brain natriuretic peptide, cardiac troponin I, C-reactive protein, and procalcitonin. D-dimer shows vital performance in the diagnosis of aortic dissection, and brain natriuretic peptide, cardiac troponin I, C-reactive protein, and procalcitonin exhibits important value in risk stratification and prognostic effect in aortic dissection patients. Our review summarized the clinical utility of these laboratory tests in patients with aortic dissection, aiming to provide advanced and comprehensive evidence for clinicians to better understand these laboratory tests and help their clinical practice.

Objective: To analyze the unregistered treatment situation and its influencing factors among pulmonary tuberculosis patients in Quzhou City, Zhejiang Province from 2017 to 2023, so as to provide a basis for promoting the management of tuberculosis patients and optimizing disease prevention and control strategies. Methods: Data of pulmonary tuberculosis patients including demographic information, etiological results, and mortality status were collected through the China Disease Prevention and Control Information System Infectious Disease Reporting and Surveillance System and the Tuberculosis Management Information System. Pulmonary tuberculosis patients not matched in the Tuberculosis Management Information System were defined as unregistered treatment patients, and the unregistered treatment rate was analyzed. Factors affecting unregistered treatment among pulmonary tuberculosis patients were analyzed using a multivariable logistic regression model. Results: A total of 10 779 pulmonary tuberculosis patients were reported in Quzhou City from 2017 to 2023, including 7 700 males (71.44%) and 3 079 females (28.56%). There were 5 484 cases aged <65 years, accounting for 50.88%. Among them, 630 cases were unregistered treatment, with an unregistered treatment rate of 5.84% (95%CI: 5.42%-6.38%). Multivariable logistic regression analysis showed pulmonary tuberculosis patients aged ≥65 years (OR=1.829, 95%CI: 1.512-2.212) had a higher risk of being unregistered treatment than those aged <65 years; patients with non-local household registration (OR=5.710, 95%CI: 4.724-6.901) had a higher risk than local patients; and patients engaged in housework/unemployed (OR=2.001, 95%CI: 1.421-2.818) or other occupations (OR=2.396, 95%CI: 1.789-3.137) had a higher risk than farmers. The mortality of unregistered treatment pulmonary tuberculosis patients was higher than the registered treatment patients (26.67% vs. 5.02%),with a significantly elevated mortality risk (OR=7.147, 95%CI: 5.738-8.902). Conclusions The unregistered treatment rate among pulmonary tuberculosis patients was well controlled in Quzhou City from 2017 to 2023, but the elderly, patients with non-local household registration, and those engaged in housework/unemployed had a higher risk of unregistered treatment. It is recommended to improve medical and social security policies, strengthen health education on tuberculosis prevention, enhance treatment adherence, and reduce mortality risk.

BACKGROUND: Fibrosis of the connective tissue in the vaginal wall predominates in pelvic organ prolapse (POP), which is characterized by excessive fibroblast-to-myofibroblast differentiation and abnormal deposition of the extracellular matrix (ECM). Our study aimed to investigate the effect of ECM stiffness on vaginal fibroblasts and to explore the role of methyltransferase 3 (METTL3) in the development of POP. METHODS: Polyacrylamide hydrogels were applied to create an ECM microenvironment with variable stiffness to evaluate the effects of ECM stiffness on the proliferation, differentiation, and expression of ECM components in vaginal fibroblasts. METTL3 small interfering RNA and an overexpression vector were transfected into vaginal fibroblasts to evaluate the effects of METTL3 silencing and overexpression on matrix stiffness-induced vaginal fibroblast-to-myofibroblast differentiation and abnormal modulation of the ECM. Both procedures were detected by 5-ethynyl-2'-deoxyuridine (EdU) staining, Western blotting (WB), quantitative real-time polymerase chain reaction (RT-qPCR), and immunofluorescence (IF). RESULTS: Vaginal fibroblasts from POP patients exhibited increased proliferation ability, increased expression of α-smooth muscle actin (α-SMA), decreased expression of collagen I/III, and significantly decreased expression of tissue inhibitors of matrix metalloproteinases (TIMPs) in the stiff matrix ( P <0.05). Compared with those from non-POP patients, vaginal wall tissues from POP patients demonstrated a significant increase in METTL3 content ( P <0.05). However, silencing METTL3 expression in vaginal fibroblasts with high ECM stiffness resulted in decreased proliferation ability, decreased α-SMA expression, an increased ratio of collagen I/III, and increased TIMP1 and TIMP2 expression. Conversely, METTL3 overexpression significantly promoted the process of increased proliferation ability, increased α-SMA expression, decreased ratio of collagen I/III and decreased TIMP1 and TIMP2 expression in the soft matrix ( P <0.05). CONCLUSIONS Elevated ECM stiffness can promote excessive proliferation, differentiation, and abnormal ECM modulation, and the expression of METTL3 plays an important role in alleviating or aggravating matrix stiffness-induced vaginal fibroblast-to-myofibroblast differentiation and abnormal ECM modulation.
Humans ; Female ; Extracellular Matrix/metabolism* ; Cell Differentiation/genetics* ; Methyltransferases/metabolism* ; Pelvic Organ Prolapse/pathology* ; Fibroblasts/metabolism* ; Myofibroblasts/metabolism* ; Vagina/metabolism* ; Cell Proliferation/physiology* ; Cells, Cultured ; Middle Aged