Search

The long non‐coding RNAs (lncRNAs) play critical roles in various biological processes and are associated with many diseases. Functional annotation of lncRNAs in diseases attracts great attention in understanding their etiology. However, the traditional co-expression-based analysis usually produces a significant number of false positive function assignments. It is thus crucial to develop a new approach to obtain lower false discovery rate for functional annotation of lncRNAs. Here, a novel strategy termed DAnet which combining disease associations with cis-regulatory network between lncRNAs and neighboring protein-coding genes was developed, and the performance of DAnet was systematically compared with that of the traditional differential expression-based approach. Based on a gold standard analysis of the experimentally validated lncRNAs, the proposed strategy was found to perform better in identifying the experimentally validated lncRNAs compared with the other method. Moreover, the majority of biological pathways (40%∼100%) identified by DAnet were reported to be associated with the studied diseases. In sum, the DAnet is expected to be used to identify the function of specific lncRNAs in a particular disease or multiple diseases.

Abstract Background Osteoporosis is a gradually recognized health problem with risks related to disease history and living habits. This study aims to establish the optimal prediction model by comparing the performance of four prediction models that incorporated disease history and living habits in predicting the risk of Osteoporosis in Chongqing adults. Methods We conduct a cross-sectional survey with convenience sampling in this study. We use a questionnaire From January 2019 to December 2019 to collect data on disease history and adults’ living habits who got dual-energy X-ray absorptiometry. We established the prediction models of osteoporosis in three steps. Firstly, we performed feature selection to identify risk factors related to osteoporosis. Secondly, the qualified participants were randomly divided into a training set and a test set in the ratio of 7:3. Then the prediction models of osteoporosis were established based on Artificial Neural Network (ANN), Deep Belief Network (DBN), Support Vector Machine (SVM) and combinatorial heuristic method (Genetic Algorithm - Decision Tree (GA-DT)). Finally, we compared the prediction models’ performance through accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC) to select the optimal prediction model. Results The univariate logistic model found that taking calcium tablet (odds ratio [OR] = 0.431), SBP (OR = 1.010), fracture (OR = 1.796), coronary heart disease (OR = 4.299), drinking alcohol (OR = 1.835), physical exercise (OR = 0.747) and other factors were related to the risk of osteoporosis. The AUCs of the training set and test set of the prediction models based on ANN, DBN, SVM and GA-DT were 0.901, 0.762; 0.622, 0.618; 0.698, 0.627; 0.744, 0.724, respectively. After evaluating four prediction models’ performance, we selected a three-layer back propagation neural network (BPNN) with 18, 4, and 1 neuron in the input layer, hidden and output layers respectively, as the optimal prediction model. When the probability was greater than 0.330, osteoporosis would occur. Conclusions Compared with DBN, SVM and GA-DT, the established ANN model had the best prediction ability and can be used to predict the risk of osteoporosis in physical examination of the Chongqing population. The model needs to be further improved through large sample research.

PurposeThe purpose is to accurately identify women at high risk of developing cervical cancer so as to optimize cervical screening strategies and make better use of medical resources. However, the predictive models currently in use require clinical physiological and biochemical indicators, resulting in a smaller scope of application. Stacking-integrated machine learning (SIML) is an advanced machine learning technique that combined multiple learning algorithms to improve predictive performance. This study aimed to develop a stacking-integrated model that can be used to identify women at high risk of developing cervical cancer based on their demographic, behavioral, and historical clinical factors.MethodsThe data of 858 women screened for cervical cancer at a Venezuelan Hospital were used to develop the SIML algorithm. The screening data were randomly split into training data (80%) that were used to develop the algorithm and testing data (20%) that were used to validate the accuracy of the algorithms. The random forest (RF) model and univariate logistic regression were used to identify predictive features for developing cervical cancer. Twelve well-known ML algorithms were selected, and their performances in predicting cervical cancer were compared. A correlation coefficient matrix was used to cluster the models based on their performance. The SIML was then developed using the best-performing techniques. The sensitivity, specificity, and area under the curve (AUC) of all models were calculated.ResultsThe RF model identified 18 features predictive of developing cervical cancer. The use of hormonal contraceptives was considered as the most important risk factor, followed by the number of pregnancies, years of smoking, and the number of sexual partners. The SIML algorithm had the best overall performance when compared with other methods and reached an AUC, sensitivity, and specificity of 0.877, 81.8%, and 81.9%, respectively.ConclusionThis study shows that SIML can be used to accurately identify women at high risk of developing cervical cancer. This model could be used to personalize the screening program by optimizing the screening interval and care plan in high- and low-risk patients based on their demographics, behavioral patterns, and clinical data.

The Coronavirus Disease 2019 (COVID-19) may affect mental health. There is little research about the influence of family function on the state anxiety of college students in the context of the global pandemic. The study aimed to clarify that generalized anxiety disorder (GAD) and trait anxiety had mediating effects in family function on the state anxiety of Chinese college students following the “stay-at-home” order during the outbreak of COVID-19. This cross-sectional study was conducted online with 1,039 respondents. We analyzed demographics, The State-Trait Anxiety Inventory (ST-AI) and Chinese Family Function Scale (FAD-18), Generalized Anxiety Disorder-7 (GAD-7), and used path analysis to discuss the influence of family function on state and trait anxiety. The results showed that female students’ state and trait anxiety was higher than that of male students (P < 0.05). Medical students’ state and trait anxiety was lower than that of literature students (P < 0.05). The GAD of the male was lower compared with the female. The score of family function has significant differences in gender, age, education, and region (P < 0.05). Gender, family function, state anxiety, trait anxiety, and GAD relate to others (r = 0.07∼0.85, p < 0.05). The results of fit indices for measurement invariance models showed that the impact of family function among GAD, state and trait anxiety across gender is significantly different (each step p < 0.05). GAD and trait anxiety had a complete meditating effect between family function and state anxiety (the proportion of standard indirect mediating effect was 24.94% in females and 36.79% in males). A healthy family function may alleviate GAD and anxiety of college students during the COVID-19 pandemic.

Consumers play an important role as one of the main actors in food safety social co-governance. To create a pattern of food safety social co-governance, the active and effective participation of consumers is critical. To encourage consumers to participate in food safety social co-governance voluntarily and positively, we attempted to develop and preliminarily validate a multidimensional questionnaire on consumer psychological capital that could be used to measure the degree of consumer participation in food safety social co-governance. The aim of the initial sample (N = 170) and test sample 2 (N = 204) was to investigate the factor structure of a preliminary measure of consumer psychological capital. A 4-factor model with 23 items explained 61.05% of the total variance in item scores. The aim of test sample 3 (N = 30) was to measure the retest reliability. Test sample 4 (N = 1,076) was randomly allocated to the modeling sample (N = 538) and validation sample (N = 538) to verify questionnaire reliability and validity. Convergent validity, discriminant validity, and the internal inconsistency coefficients of the questionnaire were assessed in the modeling sample. While processing CFA, we deleted 9 items with small standardized factor loadings. The remaining 14 items in the final revised 4-factor model included self-efficacy, resilience, hope, and optimism. The fit indices of the revised four-factor model and second-order factor model in the modeling sample revealed an acceptable model fit. The convergent validity and discriminant validity of the revised model were good and acceptable, respectively. A cross-validation procedure confirmed the appropriateness of the revised four-factor model and second-order factor model in the validation sample. The cross-validation results confirmed that the fit indices of the revised four-factor model fitted the data well and the second-order factor model in the validation sample reached acceptable values. We concluded that the questionnaire developed in this study had good reliability and stable and acceptable construct validity. It could provide a theoretical basis for measuring psychological capital in food safety co-governance.