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 understand the ability and level of emergency rescue at general hospitals in Tianjin city. Methods Such actions as formulating plans and examination forms, establishing assessment indicators and evaluation criteria, and simulation exercises were performed to evaluate the capacity of 28 general hospitals in terms of their organizational structure, emergency response, event reporting, and summary assessment. Results The emergency response assessment system consisted of 4 level-1 indicators, 19 level-2 indicators and 58 level-3 indicators. 28 hospitals were found high in their overall emergency response capacity, but some were found with setbacks. For example, the " organizational structure" scored the highest in 4 first-level indicators, up to 88. 91％ , while " incident report" scored the lowest, down to 67. 99％ . Among level-2 indicators, professional emergency professional procedures and initial reporting scored the lowest. Conclusions In order to further improve the ability of medical institutions to respond to emergency events, the hospitals are recommended to enhance their backup resources for emergency response, their staff′s awareness of first aid knowledge and first aid skills, as well as their timeliness of initial reports and the completeness of progress reports.

Objective To learn the current capacity building of emergency response teams in Tianjin for the purpose of goals setting.Methods Health Emergency Capacity Questionnaire was issued to 89 secondary and above medical institutions and 19 CDCs in Tianjin.The form covered such items as basic institutional information, workforce makeup, emergency preparations, detection and early warning, emergency response, and summary/assessment.Data collected in the questionnaire were subject to descriptive and correlation analysis.Results Tianjin has scored an initial success in emergency medicine as evidenced in its emergency response mechanisms in place, elevated capacity in emergency medical rescue and disposal, and enhanced competence of emergency teams.Rooms of improvement however include insufficient professionalism and independence of health emergency, inadequate emergency commanding and decision making system functions, insufficient laboratory test capacity at district/county levels, and insufficient social involvement in health emergency.Conclusions Top-down design should be emphasized, health emergency response should be enhanced in terms of management and response planning system, while capacity building of the teams and long-term primary care emergency mechanism deserve higher attention.

Objective To observe the clinical efficacy of Zhishanghan Zhufeng Formula in treating knee osteoarthritis.Methods Totally 90 patients were randomly divided into treatment group and control group, 45 cases in each group. The treatment group was treated with Zhishanghan Zhufeng Formula for 30 days. The control group was treated with routine medicine (diclofenac sodium sustained release tablets and glucosamine sulfate tablets) for 30 days. The clinical efficacy and the changes of VAS, WOMAC score and knee temperature before and after treatment of two groups were observed.Results TCM clinical symptoms were significantly improved, and the effects in the treatment group were more evident compared with the control group (P<0.05). After treatment, VAS and WOMAC score of the two groups decreased obviously, while the knee temperature increased, and the treatment group was superior to the control group, with significant significance (P<0.05).Conclusion Zhishanghan Zhufeng Formula has effective clinical efficacy for knee osteoarthritis.

Objective To explore the effect of pulmonary rehabilitation under health guidance from clinic nurses on endurance capacity,quality of life, and lung function of the old patients with chronic obstructive pulmonary disease (COPD). Methods 54 old patients with stableCOPD were provided with health advice and rehabilitation training for 3 months. Their dyspnea and fatigue were evaluated with Borgrating scales, lung function were tested, 6-minute walking performance and quality of life were rated before and after the rehabilitation. ResultsThe dyspnea and fatigue decreased, 6-minute walking distance increased, and scores of quality of life improved (P<0.01) after rehabilitation,but lung function was not improved significantly (p0.05). Conclusion Health guidance from clinic nurses is able to improve the endurancecapacity and quality of life in old patients with chronic obstructive pulmonary disease.

Objective To observe the effect of psychological intervention on the anxiety of middle-aged and elderly patients with hypertension. Methods 378 middle-aged and elderly patients with hypertension accepted the intervention (health education and psychological intervention). They were assessed with the Zung Self-rating Anxiety of Scale (SAS) before and after the inertvention. Results The scores of the SAS in patients were higher than the Chinese normal. Female, younger, and higher eduction background were related to the anxiety symptom. The anxiety of the pateints were released after the intervention. Conclusion Health education and psychological intervention is effective on the anxiety of the middle-aged and elderly patients with hypertension at outpatient.

Objective To evaluate the effect of health education on the old male patients with primary hypertension.Methods 120 old male patients with primary hypertension were randomly selected from the whole group and educated with health knowledge related to blood hypertension, and the changes of life style and blood pressure after health education were recorded.Results Most of the patients changed their unhealthy life style. Among these patients, more than 80% were able to have a stable emotion, regular daily life, stop smoking and less drinking, there were 66% cases with a healthy diet. The systolic pressure of the patients declined significantly after health education (P<0.01).Conclusion The health education is an efficient way to control hypertension in the official-service outpatient department.

Objective To investigate the factors related to the depression in the retired old army officers in Beijing, to establish effective nursing intervention on these factors. Methods Various factors related to depression were investigate using questionnaire in 500 retired army officers. Results Among 500 subjects, 23.0% (115/500) were with minor depression, 6.4% (32/500) with moderate depression, while 1.6% with severe depression. Subjects whose wife were still alive had much less incurrence rate of depression than ones remarried or widowed. The less time after retirement and less satisfaction in life were other important factors related to depression. Conclusion Psychological care should be emphasized on widowed, freshly retired, or people feeling less satisfactory in life. Active nursing intervention should be applied to lower the harmful effect of depression on health.

ObjectiveTo investigate correlative factors of non-operative treatment in the senile cataract, and provide gist for the health education measures.Methods1513 retiring old people had a whole medical examination, and the data was analyzed.ResultsThe proportion of binoculus cataract was 45.9%. Predilection age was 70～79 years old. Cognition information and iatrogenic effects were major risk factors in the non-operative therapeutic agents. Cataract was the third in the elder chronic disease.ConclusionMany senile patients with cataract have not enough knowledge about cataract operation although having better medical treatment and economy conditions. So the closed attention to the health education must be paid in the future.