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 value of different Trocar layouts in retroperitoneal laparoscopic partial nephrectomy for localized renal cell carcinoma, so as to provide reference for the layout of Trocar during operation. Methods The data of 137 patients with localized renal cell carcinoma who underwent retroperitoneal laparoscopic partial nephrectomy in our hospital during Sep. 2021 and Sep. 2024 were retrospectively collected, including 68 patients with umbrella layout(umbrella group)and 69 with trapezoidal layout(trapezoidal group). The operation-related indexes, renal function(glomerular filtration rate, serum creatinine), traumatic stress indexes including C-reactive protein(CRP), cortisol, and interleukin-6(IL-6), complications and recurrence rate were compared between the two groups. Results There were no significant differences in pathological results, negative rate of surgical margins, hospitalization time, complications, 1-year recurrence rate, 6-month glomerular filtration rate and serum creatinine between the two groups(P＞0.05). Compared with the trapezoidal group, the umbrella group had less intraoperative blood loss [(72.11±18.30)mL vs.(87.59±20.63)mL], shorter operation time [(88.15±16.92)min vs.(99.40±20.78)min], renal warm ischemia time [(14.68±4.60)vs.(19.27±6.11)min], bowel sound recovery time [(21.00±5.75)h vs.(25.78±4.89)h] and ambulation time [(1.72±0.48)d vs.(2.04±0.55)d](P＜0.05). The umbrella group had lower CRP [(10.02±2.78)mg/ L vs.(12.00±3.15)mg/ L] on the first day after surgery, lower CRP [(7.89±0.76)vs.(8.77±1.25)mg/L] on the third day after surgery, lower cortisol [(0.67±0.20)μmol/L vs.(0.89±0.28)μmol/L] on the first day after surgery, lower cortisol [(0.58±0.15)μmol/L vs.(0.69±0.12)μmol/L] on the third day after surgery, lower IL-6 [(28.20±6.74)ng/L vs.(35.16±7.30)ng/L] on the first day after surgery, and lower IL-6[(21.25±5.39)ng/L vs.(29.78±4.26)ng/L] on the third day after surgery(P＜0.05). Conclusion Compared with the trapezoidal Trocar layout, the umbrella Trocar layout for retroperitoneal laparoscopic partial nephrectomy in patients with localized renal cell carcinoma offers advantages such as minimal surgical trauma, shorter operation and renal warm ischemia time, and faster postoperative recovery.

ObjectiveTo elucidate the potential mechanism of modified Sinisan （MSNS） in alleviating anxiety-like behaviors induced by chronic restraint stress （CRS） in mice at the metabolic level based on serum untargeted metabolomics and identify key metabolites and metabolic pathways regulated by MSNS. MethodsSeventy-two male C57BL/6 mice were randomly assigned into six groups： control， model， high-dose （2.4 g·kg^-1） MSNS， medium-dose （1.2 g·kg^-1） MSNS， low-dose （0.6 g·kg^-1） MSNS， and positive control （fluoxetine， 2.6 mg·kg^-1）. Except the control group， the other groups were subjected to CRS for the modeling of anxiety. Mice were administrated with corresponding agents by gavage 2 h before daily restraint for 14 days. Anxiety-like behaviors were evaluated by the open field test （OFT）， elevated plus maze （EPM） test， and light/dark box （LDB） test. Serum levels of corticotropin-releasing hormone （CRH）， adrenocorticotrophic hormone （ACTH）， and corticosterone （CORT） were measured via ELISA to assess stress levels. Ultra-performance liquid chromatography-tandem mass spectrometry （UPLC-MS/MS） was employed to detect 9 metabolites in the brain tissue and serum metabolites. Orthogonal partial least squares-discriminant analysis （OPLS-DA） was adopted to identify differential metabolites （VIP>1.0， P<0.05）. MetaboAnalyst 5.0 was used for metabolic pathway enrichment analysis of the differential metabolites. ResultsCompared with the control group， the model group showed reductions in the central activity time and central distance in the OFT （P<0.05）， the proportions of open-arm residence time and open-arm residence times in the EPM test （P<0.01）， and the proportions of open box activity time and open box activity distance in the LDB test （P<0.05）， which were increased in the medium- and high-dose MSNS groups compared with the model group （P<0.05）. Compared with the control group， the model group showed elevated levels of CRH， ACTH， and CORT in the serum （P<0.01）， and the elevations were diminished in the medium- and high-dose MSNS groups （P<0.05）. UPLC-MS results indicated that compared with the control group， the model group presented declined DA， GABA， 5-HIAA， 5-HT， and 5-HT/Trp levels （P<0.05， P<0.01） and raised Glu， NE， Kyn， and Kyn/Trp levels （P<0.05）. Compared with the model group， high-dose MSNS increased the GABA， 5-HIAA， and 5-HT/Trp levels （P<0.05） and lowered the Glu and Kyn/Trp levels （P<0.05）. Untargeted metabolomics identified that 16 CRS-induced metabolic disturbances were reversed by MSNS. KEGG pathway analysis indicated that MSNS primarily modulated eight core pathways including alanine/aspartate/glutamate metabolism， butyrate metabolism， arginine-proline metabolism， TCA cycle， unsaturated fatty acid biosynthesis， and tryptophan metabolism. The mechanisms involved multidimensional biological processes， including neurotransmitter homeostasis regulation， TCA cycle energy metabolism optimization， and inflammatory response suppression. ConclusionMSNS alleviates CRS-induced anxiety-like behaviors in mice by mitigating hypothalamic-pituitary-adrenal axis hyperactivity， improving hippocampal neurotransmitter and tryptophan metabolic pathways， and regulating alanine/aspartate/glutamate metabolism， butyrate metabolism， arginine-proline metabolism， and TCA cycle.

ObjectiveTo elucidate the potential mechanism of modified Sinisan （MSNS） in alleviating anxiety-like behaviors induced by chronic restraint stress （CRS） in mice at the metabolic level based on serum untargeted metabolomics and identify key metabolites and metabolic pathways regulated by MSNS. MethodsSeventy-two male C57BL/6 mice were randomly assigned into six groups： control， model， high-dose （2.4 g·kg^-1） MSNS， medium-dose （1.2 g·kg^-1） MSNS， low-dose （0.6 g·kg^-1） MSNS， and positive control （fluoxetine， 2.6 mg·kg^-1）. Except the control group， the other groups were subjected to CRS for the modeling of anxiety. Mice were administrated with corresponding agents by gavage 2 h before daily restraint for 14 days. Anxiety-like behaviors were evaluated by the open field test （OFT）， elevated plus maze （EPM） test， and light/dark box （LDB） test. Serum levels of corticotropin-releasing hormone （CRH）， adrenocorticotrophic hormone （ACTH）， and corticosterone （CORT） were measured via ELISA to assess stress levels. Ultra-performance liquid chromatography-tandem mass spectrometry （UPLC-MS/MS） was employed to detect 9 metabolites in the brain tissue and serum metabolites. Orthogonal partial least squares-discriminant analysis （OPLS-DA） was adopted to identify differential metabolites （VIP>1.0， P<0.05）. MetaboAnalyst 5.0 was used for metabolic pathway enrichment analysis of the differential metabolites. ResultsCompared with the control group， the model group showed reductions in the central activity time and central distance in the OFT （P<0.05）， the proportions of open-arm residence time and open-arm residence times in the EPM test （P<0.01）， and the proportions of open box activity time and open box activity distance in the LDB test （P<0.05）， which were increased in the medium- and high-dose MSNS groups compared with the model group （P<0.05）. Compared with the control group， the model group showed elevated levels of CRH， ACTH， and CORT in the serum （P<0.01）， and the elevations were diminished in the medium- and high-dose MSNS groups （P<0.05）. UPLC-MS results indicated that compared with the control group， the model group presented declined DA， GABA， 5-HIAA， 5-HT， and 5-HT/Trp levels （P<0.05， P<0.01） and raised Glu， NE， Kyn， and Kyn/Trp levels （P<0.05）. Compared with the model group， high-dose MSNS increased the GABA， 5-HIAA， and 5-HT/Trp levels （P<0.05） and lowered the Glu and Kyn/Trp levels （P<0.05）. Untargeted metabolomics identified that 16 CRS-induced metabolic disturbances were reversed by MSNS. KEGG pathway analysis indicated that MSNS primarily modulated eight core pathways including alanine/aspartate/glutamate metabolism， butyrate metabolism， arginine-proline metabolism， TCA cycle， unsaturated fatty acid biosynthesis， and tryptophan metabolism. The mechanisms involved multidimensional biological processes， including neurotransmitter homeostasis regulation， TCA cycle energy metabolism optimization， and inflammatory response suppression. ConclusionMSNS alleviates CRS-induced anxiety-like behaviors in mice by mitigating hypothalamic-pituitary-adrenal axis hyperactivity， improving hippocampal neurotransmitter and tryptophan metabolic pathways， and regulating alanine/aspartate/glutamate metabolism， butyrate metabolism， arginine-proline metabolism， and TCA cycle.

Objective To use imaging features of pulmonary nodules to predict the risk of lymph node metastasis in patients with cT1-stage non-small cell lung cancer (NSCLC), providing a reference for clinical decision-making. Methods A retrospective analysis was conducted on the imaging features and postoperative pathological results of cT1 NSCLC patients who underwent surgical treatment at Linyi People’s Hospital from July 2019 to July 2022. Patients were grouped and analyzed according to lymph node metastasis status. Results A total of 1 123 patients were included, comprising 471 males and 652 females, with a median age of 59 (52, 66) years. Comparative analysis revealed that sex, age, nodule location, nodule size on imaging, solid component size, consolidation tumor ratio (CTR), average CT value, and tumor proximity to the pleura all influenced lymph node metastasis. A nomogram was constructed, indicating that the probability of lymph node metastasis in cT1 NSCLC was positively correlated with solid component size, CTR, and average CT value of the pulmonary nodule, and negatively correlated with patient age. The area under the receiver operating characteristic curve was 0.929. Conclusion For cT1 NSCLC patients, the probability of lymph node metastasis can be predicted by measuring the solid component size, CTR, and average CT value of the pulmonary nodule, in conjunction with patient age. However, relying solely on pulmonary nodule imaging characteristics is insufficient to determine a specific lymph node dissection strategy.

[Purpose]To analyze the lifetime risk of developing and dying from lung cancer at global and regional levels.[Methods]Data of lung cancer incidence and mortality were obtained from GLOBOCAN 2022 and the population and all-cause mortality data were obtained from the United Nations.The lifetime risk of developing and dying from lung cancer globally and across different regions was estimated by multiple primary adjustment method.[Results]The global lifetime risk of developing lung cancer was 3.59％[95％confidence interval(CI):3.58％～3.59％],ranking third among all cancer types.There were significant gender and regional differences in lifetime risk values.The risk for male was 4.43％(95％CI:4.42％～4.44％),which was higher than that for female(2.71％,95％CI:2.70％～2.72％),with a male-to-female ratio of 1.63.Among regions with varying human development index(HDI)levels,the risk increased with HDI levels,in very high HDI re-gions risk was 5.36％(95％CI:5.34％～5.37％),while in low HDI regions the risk was 0.34％(95％CI:0.33％～0.34％).Among the 20 global regions,East Asia had the highest lifetime risk of 7.53％(95％CI:7.52％～7.55％),while West Africa had the lowest risk of 0.16％(95％CI:0.16％～0.17％).The global lifetime risk of dying from lung cancer was 2.78％(95％CI:2.78％～2.78％),ranking the first among all cancer types.There were significant sex and regional differ-ences in lifetime death risk values.The risk for male was 3.64％(95％CI:3.63％～3.64％),which was higher than that for female(1.89％,95％CI:1.89％～1.90％),with a male-to-female ratio of 1.93.Among regions with varying HDI levels,the risk increased with HDI levels,in very high HDI re-gions the risk was 3.98％(95％CI:3.97％～3.99％),while in low HDI regions the risk was 0.31％(95％CI:0.31％～0.31％).Among the 20 global regions,the Federated States of Micronesia/Poly-nesia had the highest death risk of 5.80％(95％CI:4.98％～6.62％),while West Africa had the lowest risk of 0.15％(95％CI:0.15％～0.16％).The lifetime risk of developing and dying from lung cancer in China was 7.54％(95％CI:7.52％～7.56％)and 5.88％(95％CI:5.87％～5.90％),respec-tively,both ranking the first among all cancer types.[Conclusion]The lifetime risk of developing and dying from lung cancer remains high globally and across different regions,with a particularly heavy burden in high-HDI areas.In China,both the lifetime risk of developing and dying from lung cancer are higher than the global average.This highlights the need for continued enhance-ment of comprehensive prevention and control measures,including addressing lung cancer-related risk factors,as well as improving screening,early diagnosis,and treatment efforts to reduce the lung cancer burden.

[Purpose]To analyze the incidence and mortality rates of female breast cancer in Henan Province in 2020 and the trends from 2010 to 2020.[Methods]Breast cancer incidence and mor-tality data stratified by urban and rural areas and age groups were collected from Henan Provincial tumor registry,and the province's household population statistics were used.The crude incidence/mortality rate,age-standardized incidence/mortality rate by Chinese standard population(ASIRC/ASMRC)and world standard population(ASIRW/ASMRW),cumulative rate(0～74 year old)were calculated.The annual percentage change(APC),average annual percentage change(AAPC)and 95％confidence interval(CI)were calculated using Joinpoint software to analyze the trends of the incidence and mortality from 2010 to 2020.[Results]In 2020,24 744 new cases and 4 989 deaths of female breast cancer were documented in Henan Province,with a crude incidence rate of 46.96/105,ASIRC of 38.43/105 and ASIRW of 35.71/105;a crude mortality rate of 9.47/105,ASMRC of 6.80/105 and ASMRW of 6.72/105,respectively.The above indicators in urban areas were signifi-cantly higher than those in rural areas.The highest incidence was observed in the age group of 50～54 years old,while the highest mortality reached in the age group of 85 years old and above.From 2010 to 2020,the overall incidence of female breast cancer showed a slow upward trend(AAPC=2.09％,95％CI:0.62％～3.58％,P=0.010),while the mortality rate exhibited a signif-icant downward trend(AAPC=-3.49％,95％CI:-5.62％～-1.30％,P=0.005).[Conclusion]The incidence and mortality rates of female breast cancer in Henan Province are still at a high level,and corresponding preventive measures and control strategies are needed to effectively reduce the health hazards of breast cancer to women.

Objective To investigate the safety and efficacy of combined confluence microdissection or balloon dilatation followed by laparoscopic transcystic common bile duct exploration (LTCBDE) in day surgery laparoscopic cholecystectomy. Methods The clinical data of 203 patients with day surgery laparoscopic cholecystectomy combined with LTCBDE from June 2021 to June 2024 in Beijing Friendship Hospital, Capital Medical University were retrospectively analyzed. They were divided into an observation group (59 cases, including 42 cases of confluent microdissection and 17 cases of balloon dilatation) and a conventional group (144 cases) according to the surgical technique used. Baseline characteristics, intraoperative exploration results, operation time, postoperative recovery and complications were compared between the two groups. Results The history of preoperative cholangitis or pancreatitis (P<0.001) was more common in the observation group. And total bilirubin level was significantly higher in the observation group than in the conventional group (P=0.035). The observation group had a longer operative time (P=0.014) and higher hospitalization costs (P=0.001), but there was no difference in intraoperative bleeding and postoperative discharge time. There were no serious postoperative complications in either group. Conclusions Under the premise of strict patient screening, day surgery LTCBDE combined with confluence microdissection or balloon dilatation can effectively solve the problem of difficult choledochoscopic access, with high safety and thoroughness of exploration. Both techniques provide a feasible minimally observation solution for day surgery biliary exploration.