Effective analysis of job satisfaction among medical staff in Chinese public hospitals: a random forest model.

Objective: This study explored the factors and influence degree of job satisfaction among medical staff in Chinese public hospitals by constructing the optimal discriminant model. Methods: The participant sample is based on the service volume of 12,405 officially appointed medical staff from different departments of 16 public hospitals for three consecutive years from 2017 to 2019. All medical staff (doctors, nurses, administrative personnel) invited to participate in the survey for the current year will no longer repeat their participation. The importance of all associated factors and the optimal evaluation model has been calculated. Results: The overall job satisfaction of medical staff is 25.62%. The most important factors affecting medical staff satisfaction are: Value staff opinions (Q10), Get recognition for your work (Q11), Democracy (Q9), and Performance Evaluation Satisfaction (Q5). The random forest model is the best evaluation model for medical staff satisfaction, and its prediction accuracy is higher than other similar models. Conclusion: The improvement of medical staff job satisfaction is significantly related to the improvement of democracy, recognition of work, and increased employee performance. It has shown that improving these five key variables can maximize the job satisfaction and motivation of medical staff. The random forest model can maximize the accuracy and effectiveness of similar research.

Role of social organization engagement in high-risk groups intervention against HIV/AIDS: a case study from 176 cities of China.

BACKGROUND: A high-risk prevention strategy is an effective way to fight against human immunodeficiency virus (HIV) and acquired immunodeficiency syndrome (AIDS). The China AIDS Fund for Non-Governmental Organizations (CAFNGO) was established in 2015 to help social organizations intervene to protect high-risk populations in 176 cities. This study aimed to evaluate the role of social organizations in high-risk population interventions against HIV/AIDS. METHODS: This study was based on the CAFNGO program from 2016 to 2020. The collected data included the number and types of social organizations participating in high-risk group interventions and the amount of funds obtained by these organizations each year. We explored the factors influencing the number of newly diagnosed AIDS cases using a spatial econometric model. Furthermore, we evaluated the effectiveness of intervention activities by comparing the percentages of the individuals who initially tested positive, and the individuals who took the confirmatory test, as well as those who retested positive and underwent the treatment. RESULTS: Overall, from 2016 to 2020, the number of social organizations involved in interventions to protect HIV/AIDS high-risk populations increased from 441 to 532, and the invested fund increased from $3.98 to $10.58 million. The number of newly diagnosed cases decreased from 9128 to 8546 during the same period. Although the number of cities with overall spatial correlations decreased, the spatial agglomeration effect persisted in the large cities. City-wise, the number of social organizations (direct effect 19.13), the permanent resident population (direct effect 0.12), GDP per capita (direct effect 17.58; indirect effect - 15.38), and passenger turnover volume (direct effect 5.50; indirect effect - 8.64) were the major factors influencing new positive cases confirmed through the testing interventions performed by the social organizations. The initial positive test rates among high-risk populations were below 5.5%, the retesting rates among those who initially tested positive were above 60%, and the treatment rates among diagnosed cases were above 70%. CONCLUSIONS: The spatial effect of social organizations participating in interventions targeting high-risk populations funded by CAFNGO is statistically significant. Nevertheless, despite the achievements of these social organizations in tracking new cases and encouraging treatment, a series of measures should be taken to further optimize the use of CAFNGO. Working data should be updated from social organizations to CAFNGO more frequently by establishing a data monitoring system to help better track newly diagnosed AIDS cases. Multichannel financing should be expanded as well.

Influencing Factors of Outpatients' Satisfaction in China a Cross-Sectional Study of 16 Public Tertiary Hospitals.

PURPOSE: This study aimed to analyze the status of patient satisfaction in outpatients of tertiary hospitals and the factors affecting patient satisfaction, in order to provide a scientific basis for improving patient satisfaction. METHODS: A total of 6480 surveys of outpatients were conducted by a cross-sectional study in 16 tertiary hospitals in the Zhejiang province of China. The main contents of the survey were the basic characteristics of patients. Statistical description, single-factor analysis and binary logistic regression analysis were used to screen influencing factors. RESULTS: Results of this study showed that the total satisfaction score of outpatients was 87.13±13.47, and higher scored factors in the survey factors were nursing level, the convenience of registration and convenience of appointment diagnosis and treatment. The factors with lower scores were treatment effect, environmental sanitation and comfort and other staffs' attitudes. Hospital managers should pay attention to the improvement of treatment level, environmental sanitation and comfort and other staffs' attitudes. CONCLUSION: In the process of serving outpatients, doctors should pay more attention to patients who are male, 31-45 years old or over 60 years old, permanent residents, from public institutions, possessed postgraduate education, without medical insurance, and who visiting paediatrics and Chinese medicine hospitals.

Effective Analysis of Inpatient Satisfaction: The Random Forest Algorithm.

PURPOSE: To identify the factors influencing inpatient satisfaction by fitting the optimal discriminant model. PATIENTS AND METHODS: A cross-sectional survey of inpatient satisfaction was conducted with 3888 patients in 16 large public hospitals in Zhejiang Province. Independent variables were screened by single-factor analysis, and the importance of all variables was comprehensively evaluated. The relationship between patients' overall satisfaction and influencing factors was established, the relative risk was evaluated by marginal benefit, and the optimal model was fitted using the receiver operating characteristic curve. RESULTS: Patients' overall satisfaction was 79.73%. The five most influential factors on inpatient satisfaction, in this order, were: patients' right to know, timely nursing response, satisfaction with medical staff service, integrity of medical staff, and accuracy of diagnosis. The prediction accuracy of the random forest model was higher than that of the multiple logistic regression and naive Bayesian models. CONCLUSION: Inpatient satisfaction is related to healthcare quality, diagnosis, and treatment process. Rapid identification and active improvement of the factors affecting patient satisfaction can reduce public hospital operating costs and improve patient experiences and the efficiency of health resource allocation. Public hospitals should strengthen the exchange of medical information between doctors and patients, shorten waiting time, and improve the level of medical technology, service attitude, and transparency of information disclosure.

Association between sociodemographic, psychosocial, lifestyle factors, and self-reported health among migrant laborers in China.

BACKGROUND: There were 245 million migrants in China in 2013, the majority of whom migrated from rural to urban areas. Thus, the purpose of this study was to investigate the association between sociodemographic, psychosocial, and lifestyle factors, and self-reported health (SRH) in Chinese migrant laborers. METHODS: This study was conducted based on data from the China Labor-force Dynamics Survey 2012. SRH was measured in a single item, although there were other risk factors from three different groups: sociodemographic, psychosocial, and lifestyle factors. The associations between these risk factors and SRH were tested using multilevel logistic regression analyses including interaction tests. RESULTS: All three groups of factors were explored simultaneously. These factors included age, working hours, marital status, illness, and hospitalization, which were associated with poor SRH, as well as earnings, number of friends, relations with neighbors, trust level, education, and alcohol consumption, which were associated with good SRH. However, there was minimal association found between the two factors of medical insurance and nationality, and SRH. CONCLUSION: Our investigation indicated that there are many factors associated with SRH. In particular, this study undertook a comprehensive investigation of the associations between sociodemographic, psychosocial, lifestyle factors, and SRH in China, the results of which could better inform medical researchers and governments from a Chinese perspective.

Income-related health inequality of migrant workers in China and its decomposition: An analysis based on the 2012 China Labor-force Dynamics Survey data.

BACKGROUND: Although migrant workers are a vulnerable group in China, they demonstrably contribute to the country's economic growth and prosperity. This study aimed to describe and assess the inequality of migrant worker health in China and its association with socioeconomic determinants. METHODS: The data utilized in this study were obtained from the 2012 China Labor-force Dynamics Survey conducted in 29 Chinese provinces. This study converted the self-rated health of these migrant workers into a general cardinal ill-health score. Determinants associated with migrant worker health included but were not limited to age, marital status, income, and education, among other factors. Concentration index, concentration curve, and decomposition of the concentration index were employed to measure socioeconomic inequality in migrant workers' health. RESULTS: Prorich inequality was found in the health of migrant workers. The concentration index was -0.0866, as a score indicator of ill health. Decomposition of the concentration index revealed that the factors most contributing to the observed inequality were income, followed by gender, age, marital status, and smoking history. CONCLUSION: It is generally known that there is an unequal socioeconomic distribution of migrant worker health in China. In order to reduce the health inequality, the government should make a substantial effort to strengthen policy implementation in improving the income distribution for vulnerable groups. After this investigation, it is apparent that the findings we have made warrant further investigation.

[Study on optimizing the reimbursement scheme under the New Rural Cooperative Medical System, based on Monte Carlo simulation].

OBJECTIVE: To explore the application of Monte Carlo simulation in optimizing and adjusting the reimbursement scheme with regard to the New Rural Cooperative Medical System (NCMS) to scientific steering practice. Optimization of the reimbursement scheme in rural areas of China was also studied. METHODS: A multi-stage sampling household survey was conducted in Sihui county, with 4 433 rural residents from 1 179 households from 13 towns in Guangdong province surveyed by self-designed questionnaire. Probit Regression Model was applied in fitting data and then estimating the own-price elasticity and cross elasticity of healthcare demand for both outpatients and inpatients. Monte Carlo simulation model was constructed to estimate the reimbursement effects of various alternative reimbursement schemes, by replicated simulation for one thousand times and each sampling on five hundred households. In this way, optimization of the implemented reimbursement scheme in Sihui county was conducted. RESULTS: Own-priced elasticity of demands for outpatient visit, inpatient visit in the township hospital center, secondary hospital and tertiary hospital were -0.174, -0.264, -0.675 and -0.429, respectively. Outpatient demand was affected by the per-visit price of township hospital center and secondary hospital. The cross-priced elasticity of demands for outpatient visit appeared to be 0.125 and 0.150. The reimbursement effects of Scheme B7 showed that the efficiency of NCMS fund was 17.85% , the reimbursement ratio for healthcare was 25.63%, and the decreased percentages of poverty caused by illness was 18.25%, more than 9.37%, from the implemented scheme A. So the implemented scheme was in need for optimization. CONCLUSION: Monte Carlo simulation technique was applicable to simulate the effects of the optimized alternative reimbursement scheme of NCMS and it provided a new idea and method to optimize and adjust the reimbursement scheme.

Comparison of three data mining models for predicting diabetes or prediabetes by risk factors.

The purpose of this study was to compare the performance of logistic regression, artificial neural networks (ANNs) and decision tree models for predicting diabetes or prediabetes using common risk factors. Participants came from two communities in Guangzhou, China; 735 patients confirmed to have diabetes or prediabetes and 752 normal controls were recruited. A standard questionnaire was administered to obtain information on demographic characteristics, family diabetes history, anthropometric measurements and lifestyle risk factors. Then we developed three predictive models using 12 input variables and one output variable from the questionnaire information; we evaluated the three models in terms of their accuracy, sensitivity and specificity. The logistic regression model achieved a classification accuracy of 76.13% with a sensitivity of 79.59% and a specificity of 72.74%. The ANN model reached a classification accuracy of 73.23% with a sensitivity of 82.18% and a specificity of 64.49%; and the decision tree (C5.0) achieved a classification accuracy of 77.87% with a sensitivity of 80.68% and specificity of 75.13%. The decision tree model (C5.0) had the best classification accuracy, followed by the logistic regression model, and the ANN gave the lowest accuracy.