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 identify the structure of the complementarity determining region (CDRs), the V(D)J rearrangement and somatic hypermutational characteristics of the heavy and light chains of a red blood cell blood group-specific monoclonal antibody. Methods: The hybridoma cell line secreting human IgM κ monoclonal anti-P antibody was used as the research object. Total RNA was extracted from cultured monoclonal cell line, and cDNA was obtained by reverse transcription PCR (RT-PCR) using random hexamers primers. It was then amplified and sequenced using primers specific for variable regions of the immunoglobulin heavy and light chains encoding the anti-P antibody. The sequences were aligned against the NCBI database using online Immunoglobulin BLAST (Ig-BLAST) tool. Results: The study determined the structure of the CDRs and framework regions (FRs) of the variable regions of human monoclonal anti-P immunoglobulin, as well as the characteristics of V(D)J rearrangement. Moreover, the closest VH, VD, and VJ germline alleles for the heavy chain and VL and VJ germline alleles for the light chain were also identified. The IgH gene rearrangment pattern of the monoclonal anti-P was IGHV6-1 * 01—IGHD5-18 02—IGHJ4 02 and IgL gene was IGκV1-12 01—IGκJ3 01. Nine base mutations occurred within the germline gene IGHV6-1 01 in variable region of heavy chain, whereas 5 base mutations were found in the germline gene IGκV1-12 01 in variable region of light chain, respectively. Conclusion: This study characterized the CDR structure in monoclonal antibody cell line targeting the high-frequency red blood cell P antigen, and provided a foundation for the construction of recombinant antibody expressing plasmids and transfomation of the immunoglobulin type.

Objective To identify factors affecting and key environmental factors of the Oncomelania hupensis snail density in the Yangtze River Delta region using machine learning methods. Methods Administrative village-level O. hupensis snail survey data in the Yangtze River Delta (including Shanghai Municipality, Jiangsu Province, Zhejiang Province and Anhui Province) from 2011 to 2021 were retrieved from the Information Management System for Parasitic Disease Control of Chinese Center for Disease Control and Prevention. Environmental factor data were captured from the Google Earth Engine platform, including elevation, slope, terrain, normalized difference vegetation index (NDVI), vegetation type, soil type, total petroleum hydrocarbon (TPH), ammonium nitrogen, inorganic nitrogen, dissolved oxygen, pH of water, chemical oxygen demand (COD) and inorganic phosphorus, and climatic factor data in the study region were retrieved from the Copernicus Climate Data Store, including annual precipitation, aridity index and annual mean temperature (AMT). O. hupensis snail survey data in the Yangtze River Delta region from 2011 to 2021 were randomly divided into a training set (70%) and a test set (30%), and five machine learning models were selected for machine learning model construction and comparative analysis of the O. hupensis snail density using the software R 4.3.0, including random forest (RF), eXtreme gradient boosting (XGBoost), support vector machine (SVM), gradient boosting machine (GBM) and neural network (NN). The XGBoost model was employed to construct a predictive model for the O. hupensis snail density, and the impact of each environmental factor on O. hupensis snail distribution was quantified. The SHapley Additive exPlanations (SHAPs) values were calculated to estimate the average contribution of each variable to the model prediction, and the core environmental factors affecting the O. hupensis snail population density were screened. Results Among the five machine learning models, the XGBoost model exhibited the optimal comprehensive performance, with the coefficient of determination (R²) of 0.855, mean squared error (MSE) of 0.188, root mean squared error (RMSE) of 0.434 and mean absolute error (MAE) of 0.155, respectively. Analysis of factors affecting the O. hupensis snail density with the XGBoost model showed that among the 16 environmental factors, the top four high-impact factors ranked by SHAPs values included annual precipitation, elevation, aridity index and NDVI, with cumulative SHAPs contributions of 75%, which was higher than that of other environmental factors. If NDVI was higher than 0.6, the O. hupensis snail density increased with NDVI and peaked if NDVI was 0.8 (1.60 snails/0.1 m²). The O. hupensis snail density increased with elevation if the elevation ranged from 14 to 40 m, and slowly rose if the annual precipitation ranged from 900 to 1 300 mm, and then increased rapidly to the peak (1.52 snails/0.1 m²) if the annual precipitation ranged from 1 300 to 1 500 mm. In addition, the O. hupensis snail density increased rapidly to the maximum (1.60 snails/0.1 m²) if the aridity index ranged from 0.8 to 1.1, and decreased gradually if the aridity index exceeded 1.1. Conclusions The XGBoost model shows excellent performance in prediction of the O. hupensis snail density and identification of key environmental factors in the Yangtze River Delta region. Annual precipitation, elevation, aridity index and NDVI are key environmental factors affecting the distribution and density of O. hupensis snails in the Yangtze River Delta region.

In the strategic context of "healthy China"， the concept of "medicine and food homology"， rooted in the culture of traditional Chinese medicine （TCM）， has received unprecedented attention. In response to population aging in China， the health of the elderly has become the focus of public health attention， and proactive health is the key to healthy aging. From the perspective of the application of medicinal and edible materials in proactive health and technological responses to population aging for the first time， this paper firstly provided a systematic overview of medicinal and edible materials and the policies related to proactive health. Second， it summarized the situation of modern technology that accelerates the research and development of medicinal and edible products， as well as the current situation of various modern biotechnologies that reveal the mechanism of action of medicinal and edible materials. Third， it discussed the application scenarios of medicinal and edible materials in proactive health and technological responses to population aging， as well as the future research and development of medicinal and edible materials. By exploring in depth the unique value and importance of medicinal and edible materials， the paper lays a theoretical foundation for improving the health care capabilities of TCM and contributes new strategies derived from TCM to healthy aging.

Objective: To investigate the association between medium to long term PM 2.5 exposure around school areas and overweight/obesity among primary and secondary school students in Guangxi, providing data support and theoretical foundations for scientifically addressing overweight and obesity in primary and secondary school students. Methods: From September to November 2023, a stratified cluster random sampling method was employed to select 251 183 students aged 7-18 years (grade 1 to grade 12) from 14 prefecture level cities (111 districts and counties) in Guangxi. PM 2.5 mass concentration data were obtained from the Tracking Air Pollution in China (TAP) dataset. Preliminary comparative analysis was conducted using the Mann-Whitney U test, while binary Logistic regression models were applied to quantify the relationship between PM 2.5 exposure and overweight/obesity. Restricted cubic spline analysis was further utilized to examine the nonlinear association between PM 2.5 concentration and overweight/obesity risk. Results: The detection rate of overweight/obesity among Guangxi students in 2023 was 19.5%. The median PM 2.5 concentration in the year prior to the study was higher in the overweight/obesity group (23.22 μg/m 3) compared to the non overweight/obesity group (22.63 μg/m 3) ( Z=-15.66, P <0.01), and consistent trends were observed across gender (male/female) and educational stage (primary/junior/senior high school) subgroups (all P <0.01). Binary Logistic regression revealed that for every 10 μg/m 3 increase in the annual average PM 2.5 concentration, the risk of overweight/obesity increased by 12% ( OR=1.12, 95%CI=1.09- 1.15 , P <0.01). Restricted cubic spline analysis indicated a nonlinear relationship between monthly PM 2.5 levels and overweight/obesity risk ( P trend <0.01). Below 22.68 μg/m 3, PM 2.5 exposure showed no significant association with obesity risk; above the threshold, the risk increased with rising PM 2.5 levels. Conclusion Medium to long term PM 2.5 exposure around school environments is significantly associated with overweight/obesity among primary and secondary school students.

Objective To investigatethe relationship between gastroesophageal reflux disease (GERD) symptoms and clinicopathological characteristics, p53 expression, and survival of Chinese patients with esophageal adenocarcinoma. Methods A total of 3882 patients with esophageal adenocarcinoma, 970 matched patients with esophageal squamous cell carcinoma, and 970 matched patients with gastric cardia adenocarcinoma were included to compare the incidence of GERD symptoms. Patients with esophageal adenocarcinoma were divided into two groups according to the presence and absence of GERD symptoms. The differences in clinicopathological characteristics and p53 expression between the two groups were compared by chi-square test, and the differences in survival between the two groups were compared by landmark analysis. Results The incidence of GERD symptoms increased successively in esophageal squamous cell carcinoma, esophageal adenocarcinoma, and gastric cardia adenocarcinoma. In patients with esophageal adenocarcinoma, the proportions of male, less than 65 years old, lower thoracic tumors, tumors without squamous cell carcinoma, poorly differentiation, early tumors (stage 0-I), and p53-positive tumors in the group with GERD symptoms were higher than those in the group without GERD symptoms; moreover, the long-term survival (≥15 years) was better. Conclusion GERD symptom is an important clinical sign of esophageal adenocarcinoma. It is closely related to specific clinicopathological characteristics, p53 overexpression, and good long-term prognosis.

Objective:To explore the coordinated development status of the medical service supply-economy-society trinity systems in Zhejiang Common Prosperity Demonstration Zone,and to offer references for formulating policies conducive to the efficient and coordinated development of these three systems.Methods:Based on the panel data from 2013 to 2022,this research was conducted on the 11 prefectural-level cities in Zhejiang Province.Firstly,an evaluation index system for the three systems was established,and the entropy method was employed to determine the weights of each index and calculate the comprehensive evaluation index.Secondly,a triangular model was introduced to delineate the relative relationships among the three systems,and the coupling coordination degree model was utilized to disclose the coordination degree of the three systems.Finally,the spatial autocorrelation analysis method was applied to investigate the spatial autocorrelation of the coupling coordination degree of the three systems.Results:(1)On the whole,the development status of the three systems has improved over time,yet the comprehensive development level remains to be improved.(2)Overall,each prefectural-level city has transited from a medical service supply-society-dominated development to a balanced and coordinated development of the medical service supply-economy-society trinity systems.The coupling coordination degree of the three systems has risen from 0.468(on the verge of imbalance)in 2013 to 0.609(primary coordination)in 2022,presenting an upward trend in general.However,the coordination level remains to be improved and there exist imbalances among regions.(3)The coupling coordination degree of the three systems in Zhejiang Province exhibits a significant positive spatial correlation,and the spatial distribution characteristics are relatively stable. Conclusion:The coupling coordination degree of the medical service supply-economy-society trinity systems in Zhejiang Province awaits further enhancement. At the level of Zhejiang Province,favorable policy support should be provided,the layout of medical resources should be rationally planned,and high-quality economic and social development should be promoted. Each prefectural-level city should formulate strategies for medical service supply,economic,and social development in accordance with its own development level and local conditions,strengthen inter-city linkage and cooperation,and thereby elevate the coordinated development level of the three systems.

Objective:To explore the clinical features of death in children with acute encephalopathy associated with influenza and corona virus disease 2019（COVID-19）and to enhance pediatrician's understanding of this disease.Methods:Clinical data of children with influenza and COVID-19-related acute encephalopathy hospitalized in Pediatric Intensive Care Unit of Children's Hospital Affiliated to Soochow University from September 2021 to July 2023 were retrospectively analyzed.The cases were divided into survival group and death group according to outcome.The general condition，clinical manifestations，auxiliary examination and treatment between the two groups were compared and analyzed.Results:A total of 41 pediatric patients were enrolled.In the death group,there were 17 cases,including 15 cases of acute necrotizing encephalopathy (ANE); among them,there were 7 male patients and 10 female patients,with a median age of 3.50 years.Eight patients were infected with influenza A virus,3 with influenza B virus,and 6 with SARS-CoV-2.The survival group comprised 24 cases,including 10 cases of ANE; among them,there were 16 male patients and 8 female patients,with a median age of 4.33 years.Fourteen patients were infected with influenza A virus,4 with influenza B virus,and 6 with SARS-CoV-2.None of the patients in the death group has received influenza and COVID-19 vaccines within 1 year before infection.Common symptoms were fever and disturbance of consciousness in the death group，eight cases had mild cough，seven cases had convulsions ≥three times，one case had two convulsions，nine cases had only one seizure，of which five cases were epileptic status.One case had delirium before convulsions.Seventeen cases began to fall into a coma (6.50±1.50) hours after their first onset of convulsion.Two patients had secondary pulmonary infection.Nine cases showed significantly elevated interleukin-6,while 17 cases had normal cerebrospinal fluid cell counts and 14 cases had elevated protein levels.All 17 cases underwent cranial CT scans,among which 13 showed symmetric necrosis of the bilateral thalami.All patients in the death group underwent glucocorticoid and intravenous immunoglobulin pulse therapy.Eleven patients received continuous renal replacement therapy,ten patients received intrathecal dexamethasone injection,and two patients were treated with tocilizumab.One patient underwent extracorporeal membrane oxygenation.Among the eight influenza patients,neuraminidase inhibitors were first administered 48 hours after the onset of fever.None of the six patients infected with SARS-CoV-2 received nirmatrelvir/ritonavir antiviral treatment.The causes of death in 17 patients included ANE(15 cases) and secondary infections(2 cases).Compared with the survival group,the incidence of brainstem involvement,shock,and low Glasgow coma scores (GCS ≤ 4) were significantly higher in the death group(15/17 vs.2/24， χ 2=26.18， P<0.001；16/17 vs.5/24， χ 2=21.39， P<0.001；14/17 vs.5/24， χ 2=15.15， P<0.001). Conclusion:Acute encephalopathy is primarily characterized by recurrent convulsions and disturbances of consciousness.Influenza and COVID-19 are the main causes.Cranial imaging is helpful for clinical diagnosis.Involvement of the brainstem,occurrence of shock,and GCS≤4 are associated with a higher fatality rate of ANE.

The application of sensors to the monitoring of spinal morphology and motion was reviewed in terms of the research object and monitoring index.The present situation of the application of sensors was introduced,such as inertial sensor,stretchable strain sensor and electromagnetic sensor.The deficiencies of sensors applied to the monitoring of spinal morphology and motion were analyzed,and the future directions of the application were pointed out.[Chinese Medical Equipment Journal,2025,46(6):105-110]