BACKGROUND: Hypertension is a serious chronic disease that can significantly lead to various cardiovascular diseases, affecting vital organs such as the heart, brain, and kidneys. Our goal is to predict the risk of new onset hypertension using machine learning algorithms and identify the characteristics of patients with new onset hypertension. METHODS: We analyzed data from the 2011 China Health and Nutrition Survey cohort of individuals who were not hypertensive at baseline and had follow-up results available for prediction by 2015. We tested and evaluated the performance of four traditional machine learning algorithms commonly used in epidemiological studies: Logistic Regression, Support Vector Machine, XGBoost, LightGBM, and two deep learning algorithms: TabNet and AMFormer model. We modeled using 16 and 29 features, respectively. SHAP values were applied to select key features associated with new onset hypertension. RESULTS: A total of 4,982 participants were included in the analysis, of whom 1,017 developed hypertension during the 4-year follow-up. Among the 16-feature models, Logistic Regression had the highest AUC of 0.784(0.775∼0.806). In the 29-feature prediction models, AMFormer performed the best with an AUC of 0.802(0.795∼0.820), and also scored the highest in MCC (0.417, 95%CI: 0.400∼0.434) and F1 (0.503, 95%CI: 0.484∼0.505) metrics, demonstrating superior overall performance compared to the other models. Additionally, key features selected based on the AMFormer, such as age, province, waist circumference, urban or rural location, education level, employment status, weight, WHR, and BMI, played significant roles. CONCLUSION We used the AMFormer model for the first time in predicting new onset hypertension and achieved the best results among the six algorithms tested. Key features associated with new onset hypertension can be determined through this algorithm. The practice of machine learning algorithms can further enhance the predictive efficacy of diseases and identify risk factors for diseases.
Humans ; China/epidemiology* ; Hypertension/diagnosis* ; Machine Learning ; Male ; Female ; Middle Aged ; Adult ; Nutrition Surveys ; Algorithms ; Aged ; Risk Factors

Strengthening the supervision over the use of large-scale medical equipment is an effective means to improve the efficiency of equipment use and the quality of medical services, and it is an important part of promoting the construction of the Healthy China and the development of health undertakings. Through four stages of preliminary demand investigation, intelligent collection of data, intelligent analysis and evaluation, and continuous improvement, a large-scale medical equipment intelligent management platform was built in our hospital. Real-time data collection, interconnection, analysis and evaluation were achieved, which could help the use and supervision, improve efficiency and effectiveness, and optimize the evaluation system.

Medical device management has become a key to medical quality management, medical risk prevention and medical cost control. Continuous innovation is needed to realize the refinement of device management, ensure the safety of patients and improve medical quality. The authors take MRI as an example to monitor the medical devices based on the data platform support in combination with hospital specifics, so as to provide references for the rational use of medical devices.

As an important part of public emergency response mechanism, medical supplies and equipment support is an important material support for medical rescue and disposal.For the medical equipment management industry, the epidemic prevention and control practice is a major test, but also a leap forward development opportunity. Based on the working experience, the authors put forward that medical equipment support should be upgraded to the strategic material support for the prevention and control of major infectious diseases. It is suggested to improve the whole process support management system of medical equipment purchase, collection, allocation and donation. The authors discuss how to implement the construction of medical equipment support elements from four aspects of system, technology, supply chain and information system, and also discuss how to promote the development of medical engineering interdisciplinary.

Objective:To assess the relationship between body mass index (BMI) and death risk of cardiovascular disease (CVD) in rural male population.Methods:22 282 men aged 40 years older in Tanghe county and Fenghuang county from the cohort of the "Prospective Study on Adult Behavior and Health Risk Factors in China" were selected as subjects of this study. Cox regression model was used to calculate the hazard ratios ( HRs) of the death of CVD during the follow-up period with different BMI groups at baseline. Results:The average follow-up period in the two counties was (19.1±8.7) years and 10 828 (48.6%) people died during the follow-up period. 4 504 deaths were attributed to CVD. Among the deaths of CVD, 1 279 cases died of ischemic heart disease (IHD), ischemic stroke (IS) died in 1 201, cases died of died of 1 317 hemorrhagic stroke (HS), other 707 cases. Compared to population with BMI<18 kg/m 2, Cox regression model (adjusting factors of region, age, nationality, education level, occupation, smoking, drinking, blood pressure, blood pressure, etc.) showed that people with BMI between 20-22 kg/m 2 had the lowest risk of CVD death ( HR=0.95, 95 %CI: 0.83-1.09). But the difference was not statistically significant among each BMI group ( P>0.05). The risk of IHD death was the lowest in the population with BMI between 20-22 kg/m 2 ( P<0.05) ( HR=0.64, 95 %CI: 0.52-0.80). There was no statistically significant difference between the risk of IHD death in the population with BMI≥24 kg/m 2 and that in the population with BMI<18 kg/m 2 ( P>0.05). There was no statistically significant difference between the risk of IS death and BMI ( P>0.05). The death risk of HS in the population with BMI between 18-24 kg/m 2 was higher than that in the population with BMI<18 kg/m 2 ( P<0.05). The death risk of the population with BMI between 26-28 kg/m 2 was the highest ( HR=1.88, 95 %CI:1.18-2.99). Conclusions:The mortality risk of CVD and IHD was the lowest in lean or normal weight group, and HS was higher in overweight group. Maintaining a reasonable weight can reduce the risk of death in patients with CVD.

Interrupted time series (ITS) is a statistical method for the quasi-experimental design specific to the outcome of time series, in which the effectiveness of an intervening measure is evaluated by examining change in slope and immediate change in level. The key feature of ITS is that the secular trend of time series prior to the intervention can be effectively controlled so as to accurately estimate the intervention effect. The design principle and statistical method for ITS were illustrated by an example of evaluating halving policy for the expert registration fee in the general hospital of a city. The segmented linear regression was used to fit the above time series data and the results were explained in detail. Meanwhile, the study design and model fitting along with explanations of the results with respect to the effects of two types of successive interventions and on different time-points of an intervention were illustrated as well in this paper. The existed upward or downward trend should be taken into account in order to accurately estimate the intervention effect as it exists in most of the public health surveillance data. Two parameters, known as change in slope and immediate change in level, were employed to evaluate the effect of the intervention. The ITS analysis can be widely applied to the program evaluation as it could enrich methods of the evaluation compared to the traditional model of the program evaluation.

Interrupted time series (ITS) is a statistical method for the quasi?experimental design specific to the outcome of time series, in which the effectiveness of an intervening measure is evaluated by examining change in slope and immediate change in level. The key feature of ITS is that the secular trend of time series prior to the intervention can be effectively controlled so as to accurately estimate the intervention effect. The design principle and statistical method for ITS were illustrated by an example of evaluating halving policy for the expert registration fee in the general hospital of a city. The segmented linear regression was used to fit the above time series data and the results were explained in detail. Meanwhile, the study design and model fitting along with explanations of the results with respect to the effects of two types of successive interventions and on different time?points of an intervention were illustrated as well in this paper. The existed upward or downward trend should be taken into account in order to accurately estimate the intervention effect as it exists in most of the public health surveillance data. Two parameters, known as change in slope and immediate change in level, were employed to evaluate the effect of the intervention. The ITS analysis can be widely applied to the program evaluation as it could enrich methods of the evaluation compared to the traditional model of the program evaluation.

Interrupted time series (ITS) is a statistical method for the quasi?experimental design specific to the outcome of time series, in which the effectiveness of an intervening measure is evaluated by examining change in slope and immediate change in level. The key feature of ITS is that the secular trend of time series prior to the intervention can be effectively controlled so as to accurately estimate the intervention effect. The design principle and statistical method for ITS were illustrated by an example of evaluating halving policy for the expert registration fee in the general hospital of a city. The segmented linear regression was used to fit the above time series data and the results were explained in detail. Meanwhile, the study design and model fitting along with explanations of the results with respect to the effects of two types of successive interventions and on different time?points of an intervention were illustrated as well in this paper. The existed upward or downward trend should be taken into account in order to accurately estimate the intervention effect as it exists in most of the public health surveillance data. Two parameters, known as change in slope and immediate change in level, were employed to evaluate the effect of the intervention. The ITS analysis can be widely applied to the program evaluation as it could enrich methods of the evaluation compared to the traditional model of the program evaluation.

Objective: To explore the influence of caregiver burden on quality of life among caregivers for patients with lung cancer in Beijing. Methods: From August to October in 2017, 336 caregivers for patients with primary lung cancer from a large tertiary hospital were recruited to this survey by convenient sampling method. The Caregiver Reaction Assessment (CRA) and the WHO Quality of Life-BREF (WHOQOL-BREF) Instruments were used to evaluate the caregiver burden and quality of life. The demographic characteristics were evaluated using Pearson chi-square or Fisher′s exact tests. In addition, using the 4 dimensions of quality of life scale as the dependent variables while the 5 dimensions of caregiver burden and demographic variables as the explanatory variables, we conducted the multiple linear stepwise regression analysis (the defaults were 0.15 for FORWARD and BACKWARD). Results: The scores of family caregivers′ esteem, impact on schedule, impact on finances, impact on health and lack of family support were 4.30±0.47、3.55±0.74、3.10±0.91、2.60±0.78、2.32±0.73, respectively. Regression results showed that demographic factors, including marriage, occupation and relationship with patients and impact on health, caregivers′ esteem and impact on finances dimensions of caregiver burden were the factors which influenced the quality of life of caregivers. Conclusions The caregiver burden in patients with lung cancer is mainly focused on impact on schedule and finances. Impact on health, finances and caregivers′ esteem (seven items were reverse-scored) are significantly negatively correlated with quality of life of caregivers.