Body mass index (BMI) and dyslipidemia are indicators of human health and are often associated with high blood pressure. In this study,we explored the relationship between BMI or dyslipidemia and the risk of hypertension and further verified the possible interacting influences of BMI with dyslipidemia on the risk of hypertension. The aim is to explore the possible risk factors of hypertension and to provide scientific basis for the prevention and treatment of hypertension. Eligible subjects were selected from a cross-sectional survey in Changsha City, and we collected relevant data and clinical indicators for each participant. Body mass index (BMI) was calculated as weight (kg)/height² (m²), and divided into four categories according to the Chinese standard. Dyslipidemia is defined according to Chinese guideline. Unconditional logistic regression models were used for dichotomous variables to determine the risk or protective factors of dependent variables. Multivariate Logistic model was used to study the influence of BMI and dyslipidemia on hypertension. The following indicators were used to assess the interaction effects: (1) Relative excess risk due to interaction (RERI); (2) Attributable proportion due to interaction(AP); (3) Synergy index (SI). SPSS software was used for statistical analysis. A total of 2740 eligible participants were enrolled in the cross-sectional study, of which 765 subjects (27.9%) were diagnosed with hypertension. Multivariate Logistic model showed that overweight (OR: 1.70, 95%CI: 1.39–2.09) or obese (OR: 2.60, 95%CI: 1.84–3.66) subjects had a significantly higher risk of hypertension than normal weight people, and underweight was a protective factor for hypertension(OR: 0.52, 95%CI: 0.29–0.93). People with dyslipidemia have a higher risk of hypertension than those with normal lipids (OR: 3.05, 95%CI: 2.36–3.90). In addition,there was a significant potentiating interaction effect between overweight or obesity and dyslipidemia(overweight: RERI (1.91, 95%CI: 0.17–3.66), AP (0.40, 95%CI:0.14–0.66), SI (2.03, 95%CI:1.11–3.74) and obesity: RERI (2.20, 95%CI:1.01–3.40), AP (0.38, 95%CI:0.18–0.58), SI (1.84, 95%CI:1.18–2.89), while no interaction was found between underweight and dyslipidemia. Low body weight is an independent protective factor for hypertension, but overweight, obesity and dyslipidemia are risk factors for hypertension, and dyslipidemia significantly shared interactions with overweight and obesity that influenced the risk of hypertension.

We conducted a meta-analysis to systematically assess the prevalence of hyperhomocysteinemia (HHcy) in China, its change over time, and its determinants. Literature searches were conducted using English databases (PubMed, Embase, and Web of Science) and Chinese databases (CNKI, CBM, VIP, and Wanfang). The time ranges were from Jan 2014 to Mar 2021 in China. We adopted the random effects model to estimate the pooled positive rates of HHcy and corresponding 95% confidence intervals (95% CI). To find the sources of heterogeneity, we performed subgroup analysis and meta-regression. A total of 29 related articles were identified involving 338,660 participants with 128,147 HHcy cases. The estimated prevalence of HHcy in China was 37.2% (95% CI: 32.6–41.8%, I² = 99.8%, p for heterogeneity < 0.001). The trend of HHcy prevalence was gradually upward over time, with increases during 2015–2016 (comparison to 2013–2014, p < 0.001), but steady between 2015–2016 and 2017–2018. Subgroup analysis showed that the prevalence was higher in the elderly over 55 years old, males, and residents in the north, inland, and rural China (for each comparison, p < 0.001). Meta-regression analysis revealed that age and area of study contributed to 42.3% of the heterogeneity between studies. The current meta-analysis provides strong evidence that the prevalence of HHcy is increasing in China, and varies substantially across different ages, genders, and geographic distribution. Accordingly, high-risk population groups should be focused on, and public health policies and strategies should be carried out to prevent and control HHcy in China.

Background: Tuberculosis (TB) is a public health problem worldwide, and the influence of meteorological and air pollutants on the incidence of tuberculosis have been attracting interest from researchers. It is of great importance to use machine learning to build a prediction model of tuberculosis incidence influenced by meteorological and air pollutants for timely and applicable measures of both prevention and control. Methods: The data of daily TB notifications, meteorological factors and air pollutants in Changde City, Hunan Province ranging from 2010 to 2021 were collected. Spearman rank correlation analysis was conducted to analyze the correlation between the daily TB notifications and the meteorological factors or air pollutants. Based on the correlation analysis results, machine learning methods, including support vector regression, random forest regression and a BP neural network model, were utilized to construct the incidence prediction model of tuberculosis. RMSE, MAE and MAPE were performed to evaluate the constructed model for selecting the best prediction model. Results: (1) From the year 2010 to 2021, the overall incidence of tuberculosis in Changde City showed a downward trend. (2) The daily TB notifications was positively correlated with average temperature (r = 0.231), maximum temperature (r = 0.194), minimum temperature (r = 0.165), sunshine duration (r = 0.329), PM_2.5 (r = 0.097), PM₁₀ (r = 0.215) and O₃ (r = 0.084) (p < 0.05). However, there was a significant negative correlation between the daily TB notifications and mean air pressure (r = −0.119), precipitation (r = −0.063), relative humidity (r = −0.084), CO (r = −0.038) and SO₂ (r = −0.034) (p < 0.05). (3) The random forest regression model had the best fitting effect, while the BP neural network model exhibited the best prediction. (4) The validation set of the BP neural network model, including average daily temperature, sunshine hours and PM₁₀, showed the lowest root mean square error, mean absolute error and mean absolute percentage error, followed by support vector regression. Conclusions: The prediction trend of the BP neural network model, including average daily temperature, sunshine hours and PM₁₀, successfully mimics the actual incidence, and the peak incidence highly coincides with the actual aggregation time, with a high accuracy and a minimum error. Taken together, these data suggest that the BP neural network model can predict the incidence trend of tuberculosis in Changde City.

With the increase of Internet visits and connections, it is becoming essential and arduous to protect the networks and different devices of the Internet of Things (IoT) from malicious attacks. The intrusion detection systems (IDSs) based on supervised machine learning (ML) methods require a large number of labeled samples. However, the number of abnormal behaviors is far less than that of normal behaviors, let alone that the shots of malicious behavior samples which can be intercepted as training dataset are actually limited. Consequently, it is a key research topic to conduct the anomaly detection for the small number of abnormal behavior samples. This paper proposes an anomaly detection model with a few abnormal samples to solve the problem in few-shot detection based on convolutional neural networks (CNN) and autoencoder (AE). This model mainly consists of the CNN-based supervised pretraining module and the AE-based data reconstruction module. Only a few abnormal samples are utilized to the pretrain module to build the structure of extracting deep features. The data reconstruction module simply chooses the deep features of normal samples as training data. There also exist some effective attention mechanisms in the pretraining module. Through the pretraining of small samples, the accuracy of abnormal detection is improved compared with merely training normal samples with AE. The simulation results prove that this solution can solve the above problems occurring in network behavior anomaly detection. In comparison to the original AE model and other clustering methods, the proposed model advances the detection results in a visible way.

Cervical cancer (CC) is the fourth most common malignant tumor among women worldwide. Constructing a high-accuracy deep convolutional neural network (DCNN) for cervical cancer screening and diagnosis is important for the successful prevention of cervical cancer. In this work, we proposed a robust DCNN for cervical cancer screening using whole-slide images (WSI) of ThinPrep cytologic test (TCT) slides from 211 cervical cancer and 189 normal patients. We used an active learning strategy to improve the efficiency and accuracy of image labeling. The sensitivity, specificity, and accuracy of the best model were 96.21%, 98.95%, and 97.5% for CC patient identification respectively. Our results also demonstrated that the active learning strategy was superior to the traditional supervised learning strategy in cost reduction and improvement of image labeling quality. The related data and source code are freely available at https://github.com/hqyone/cancer_rcnn.

Background: Influenza is the first infectious disease that implements global monitoring and is one of the major public health issues in the world. Air pollutants have become an important global public health issue, in recent years, and much epidemiological and clinical evidence has shown that air pollutants are associated with respiratory diseases. Methods: We comprehensively searched articles published up to 15 November 2022 in PubMed, Web of Science, China National Knowledge Infrastructure (CNKI), Database of Chinese sci-tech periodicals, and Wanfang Database. The search strategies were based on keyword combinations related to influenza and air pollutants. The air pollutants included particulate matter (PM2.5, PM10), nitrogen dioxide (NO2), sulfur dioxide (SO2), carbon monoxide (CO), and ozone (O3). Meta-analysis was performed using the R programming language (R4.2.1). Results: A total of 2926 records were identified and 1220 duplicates were excluded. Finally, 19 studies were included in the meta-analysis according to inclusion and exclusion criteria. We observed a significant association between partial air pollutants (PM2.5, NO2, PM10 and SO2) and the incidence risk of influenza. The RRs were 1.0221 (95% CI: 1.0093~1.0352), 1.0395 (95% CI: 1.0131~1.0666), 1.007 (95% CI: 1.0009~1.0132), and 1.0352 (95% CI. 1.0076~1.0635), respectively. However, there was no significant relationship between CO and O3 exposure and influenza, and the RRs were 1.2272 (95% CI: 0.9253~1.6275) and 1.0045 (95% CI: 0.9930~1.0160), respectively. Conclusion: Exposure to PM2.5, NO2, PM10, and SO2 was significantly associated with influenza, which may be risk factors for influenza. The association of CO and O3 with influenza needs further investigation.