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.

Objectives:To clarify the biomechanical stress rebalancing mechanism at the bone tissue-cement interface and the dynamic stability reconstruction effect on the spine after cement reinforcement treatment of osteoporotic vertebral compression fractures(OVCF).Methods:An OVCF patient(injured vertebrae,T12 and L1)treated in the Department of Spine Surgery of the Affiliated Hospital of Gansu University of Traditional Chinese Medicine was selected as the object of study,and thin-layer,high-precision thoracic and lumbar vertebral CT imaging data of the patient was extracted.A 3D digitally simulated biomechanical model was established through the finite-element biomechanical modeling platforms of Mimics,Geomagic,Solidworks,and Ansys Workbench,in order to quantitatively study the equivalent stress at bone tissue-cement interface of motion segment of the injured vertebral body under different motion conditions such as axial,flexion,extension,lateral bending,and rotation.Results:The extreme value and distribution range of equivalent stress at the bone tissue-bone cement interface after spinal OVCF were significantly optimized compared with those before surgery.Under the motion conditions of axial,forward flexion,posterior extension,lateral bending and rotation conditions,the maximum principal stress after spinal cement reinforcement for T12 vertebra decreased significantly compared with that before surgery,which was 33.002MPa,35.639MPa,35.98MPa,60.458MPa,65.396MPa,60.177MPa,and 42.249MPa under the same working conditions,especially under the forward flexion working conditions,the maximum principal stress of T12 decreased from 77.995MPa before surgery to 35.639MPa after surgery;Under the same motion conditions,the maximum principal stress of L1 vertebra after reinforcement treatment was 24.91 1MPa,34.705MPa,26.514MPa,60.144MPa,32.797MPa,30.259MPa,and 32.894MPa,respectively,and under axial and foiward flexion conditions,the maximum principal stress of L1 vertebra decreased from 74.798MPa and 99.232MPa before surgery to 24.911 MPa and 34.705MPa after surgery.The maximum principal stress at T12 and L1 bone cement interface distributed evenly.The extreme value of principal stress at T12 cancellous bone was 1.004MPa to 3.0758MPa,which at L1 cancellous bone was 1.8075MPa to 2.3355MPa.The stress distribution cloud map showed that the stress distribution at hone interface shifted to the middle and posterior columns after the reinforcement treatment,and the stress concentration was corrected.The stress distribution at the bone tissue-bone cement interface tended to be balanced and stabilized.Conclusions:The dynamic biomechanical stability of the spine is reconstructed after cemented reinforcement of the injured vertebrae in the thoracolumbar segment,and the biomechanical stress-strain stimulus at the bone tissue-cement interface is significantly decreased compared with the preoperative period,and the stresses are distributed evenly,which reconstruct the stress rebalancing at the bone tissue-cement interface.

There are many occupational risk factors in operating room work. Polymethyl methacrylate (PMMA) , as a kind of common bone filling and repairing material, is widely used in the fixation of artificial joints, oral braces and orthopedic prosthesis. However, PMMA will release methyl methacrylate (MMA) monomer when it is implanted into human tissues and polymerized to harden, which is toxic to the body. This paper analyzes harmful factors in using PMMA bone cement, and then explores corresponding occupational protection knowledge, in order to reduce the occurrence of occupational hazards related to PMMA bone cement and enhance the self-protection ability of the operation room medical staff.
Bone Cements/adverse effects* ; Humans ; Operating Rooms ; Polymethyl Methacrylate/adverse effects*

Objective:To observe the adhesion, growth and differentiation of rat neural stem cells (NSCs) on spinal cord acellular scaffold (SCAS) to evaluate its feasibility for spinal cord tissue engineering. Methods:NSCs derived from neonatal Sprague-Dawley rat cerebral cortex were cultured and identified. SCAS were prepared from female Sprague-Dawley rat spinal cord tissues using modified chemical extraction and physical oscillation, and evaluated. The third generation NSCs were planted on SCAS and co-cultured, the morphology of the cells on the scaffold was observed with immunofluorescence, immunohistochemistry and scanning electron microscope. Results:The cultured cells were NSCs, which could proliferate and differentiate. The porosity, water content and enzymatic hydrolysis rates of the prepared SCAS were significantly higher than that of normal spinal cord (|t| > 4.679, P < 0.01). The matrix structure of SCAS was loosely network-like, with few residual nuclei. NSCs adhered and grew well, and differentiated into neurons and glial cells on SCAS. Conclusion:This kind of SCAS shapes multi-channel spatial structure and is suitable for NSCs adhesion, growth and differentiation, which can be used for spinal cord tissue engineering.

Objective: To investigate awareness of digestive system injury caused by corona virus disease 2019 (COVID-19) in gastroenterologists. Methods: From February 21 to 23 in 2020, the electronic questionnaire was sent out to explore the condition of the basic knowledge of COVID-19 and knowledge of digestive system injury caused by COVID-19 grasped by gastroenterologists. Chi-square test was used for statistical analysis. Results: A total of 2 216 gastroenterologists from 31 provinces, autonomous regions and municipalities nationwide completed the survey. 99.7% (2 209/2 216) of gastroenterologists stated that they had read the COVID-19 diagnosis and treatment guidelines. The percentage of physicians who well knew the diagnostic criteria of suspected and confirmed cases of COVID-19 was 34.9% (774/2 216) and 39.4% (874/2 216), respectively. The percentage of physician who gave the right answer of COVID-19 detectable methods and lung imaging was 68.4% (1 516/2 216) and 71.6% (1 586/2 216), respectively. The percentage of correct answer of digestive system injury caused by COVID-19 in residents, attending physicians, associate chief physicians and chief physicians was 30.9% (134/433), 33.9% (234/691), 32.4% (213/657) and 34.9% (152/435), respectively, however there were no statistically significant differences among physicians of different level (χ²=6.60, P> 0.05). 95.6% (2 119/2 216) of gastroenterologists believed that probiotics could effectively improve bowel function, and 94.0% (2 082/2 216) of gastroenterologists considered that enteral nutrition support could improve patients’ prognosis. Conclusions The knowledge and dynamic progress of the digestive system injury caused of COVID-19 are still insufficiently grasped by gastroenterologists in China. So it is necessary to carry out systematic and pertinent training for them.

Objective:To observe the changes in acromiaohumeral distance(AHD) in patients undergoing the modified arthroscopic double-button Latarjet procedure for recurrent anterior shoulder dislocation complicated with glenoid bone defect.Methods:A retrospective study was performed of the 52 patients who had undergone the modified arthroscopic double-button Latarjet procedure from October 2014 to October 2016 at Department of Sports Medicine, The First Affiliated Hospital to Shenzhen University for recurrent anterior shoulder dislocation complicated with glenoid bone defect. They were 33 males and 19 females, having 30 left and 22 right shoulders affected. Their ages ranged from 19 to 45 years(mean, 29.6 years). Their glenoid bone defects ranged from 17% to 30%(mean, 23.4%). CT scans were performed on the surgery side to observe the healing and reshaping of the bone grafts and to measure the AHDs of healthy shoulder, immediately, 6, 18 and 36 months after operation. Their American Shoulder and Elbow Surgeons(ASES), Rowe and Walch-Duplay scores were recorded before operation and at the final follow-up for comparison.Results:The follow-up time for this series ranged from 37 to 44 months (mean, 40.6 months). The AHDs at immediate postoperation(9.6 mm ± 0.7 mm), 6 months postoperation(8.6 mm ± 0.9 mm), 18 months postoperation (8.0 cm ± 0.8 cm) and 36 months postoperation(7.9 cm ± 0.8 cm) were significantly wider than the healthy side value (7.8 mm ± 0.8 mm)( P<0.05). The ASES, Rowe and Walch-Duplay scores at the final follow-up (93.9±3.2, 94.5±2.7 and 95.7±3.6) were significantly improved than the preoperative values (67.3±9.1, 40.1±4.2 and 63.5±9.0) ( P<0.05). The final follow-ups observed no symptoms or signs of chronic shoulder pain, rotator cuff injury or acromion impingement. Conclusion:As the AHD becomes wider rather than narrower after arthroscopic double-button Latarjet procedure for recurrent anterior shoulder dislocation complicated with glenoid bone defect, no subsequent rotator cuff injury may happen due to the uplift of the humeral head after the modified arthroscopic double-button Latarjet procedure.

Objective To evaluate the clinical effects of multi-detector computed tomography (MDCT) multi-postprocessing techniques in the evaluation of small bowel obstruction (SBO). Methods Clinical and MDCT imaging data of 90 patients with SBO were collected. Three radiologists respectively applied two protocols (protocol 1 consisted of conventional axial and coronal reformations and protocol 2 involved integration of multiple post-processing techniques) to image post-processing and interpretation of patients' MDCT volume data, and completed condition evaluation reports. Two protocols were compared regarding relevant diagnostic self-confidence, clinical satisfaction, clinical treatment decisions, and radiological adverse events. Results In the same protocol, the diagnostic self-confidence showed no significant difference between three radiologists for any evaluation parameter (P>0.05), but the diagnostic self-confidence of three radiologists was significantly higher in the protocol 2 than in the protocol 1 (P<0.01). The clinical satisfaction was also significantly higher in the protocol 2 than in the protocol 1 for all the individual and compositive illness assessment reports (P<0.01). After protocol 2 was applied clinically, it changed the previous treatment decisions based on protocol 1 in 11 patients (12.22%). About radiological adverse events, regardless of minor, major, or the sum of them, protocol 1 was significantly higher than protocol 2 (P<0.05). Conclusion Integration of multi-postprocessing techniques can improve diagnostic self-confidence and clinical satisfaction of MDCT for assessing SBO and effectively reduce radiological adverse events.