Pressure injury risk factors in adult orthopaedic surgical patients: a cross-sectional study and random forest.

OBJECTIVE: To identify the most important risk factors for predicting pressure injury (PI) occurrence in adult orthopaedic surgical patients based on investigation data, thereby identifying at-risk patients and facilitating formulation of an effective patient care strategy. METHOD: Patients were assessed with an instrument designed by the authors specifically for this study in a cross-sectional investigation following the STROBE checklist. The random forest method was adopted to select the most important risk factors and predict occurrence of PIs. RESULTS: A dataset of 27 risk factors from 1701 patients was obtained. A subset of the 15 most important risk factors was identified. The random forest method had a high prediction accuracy of 0.9733 compared with 0.9281 calculated with a logistic model. CONCLUSION: Results indicated that the selected 15 risk factors, such as activity ability, friction/shear force, skin type and anaesthesia score, performed very well in predicting the occurrence of PIs in adult orthopaedic surgical patients.

Exploring Mechanisms of Houshiheisan in Treating Ischemic Stroke with Network Pharmacology and Independent Cascade Model.

BACKGROUND: Houshiheisan (HSHS) has been effective in the treatment of ischemic stroke (IS) for centuries. However, its mechanisms are still underexplored. OBJECTIVE: The objective of this study is to identify the active ingredients and mechanisms of HSHS in treating IS. METHODS: We searched the main active compounds in HSHS and their potential targets, and key targets related to IS. Based on the common targets of HSHS and IS, we further expanded genes by KEGG database to obtain target genes and related genes, as well as gene interactions in the form of A→B, and then constructed a directed network including traditional Chinese medicines (TCMs), active compounds and genes. Finally, based on enrichment analysis, independent cascade (IC) model, and molecular docking, we explored the mechanisms of HSHS in treating IS. RESULTS: A directed network with 6,348 nodes and 64,996 edges was constructed. The enrichment analysis suggested that the AGE pathway, glucose metabolic pathway, lipid metabolic pathway, and inflammation pathway played critical roles in the treatment of IS by HSHS. Furthermore, the gene ontologies (GOs) of three monarch drugs in HSHS mainly involved cellular response to chemical stress, blood coagulation, hemostasis, positive regulation of MAPK cascade, and regulation of inflammatory response. Several candidate drug molecules were identified by molecular docking. CONCLUSION: This study advocated potential drug development with targets in the AGE signaling pathway, with emphasis on neuroprotective, anti-inflammatory, and anti-apoptotic functions. The molecular docking simulation indicated that the ligand-target combination selection method based on the IC model was effective and reliable.

Prediction of 5-hydroxytryptamine transporter inhibitors based on machine learning.

In patients with depression, the use of 5-HT reuptake inhibitors can improve the condition. Machine learning methods can be used in ligand-based activity prediction processes. In order to predict SERT inhibitors, the SERT inhibitor data from the ChEMBL database was screened and pre-processed. Then 4 machine learning methods (LR, SVM, RF, and KNN) and 4 molecular fingerprints (CDK, Graph, MACCS, and PubChem) were used to build 16 prediction models. The top 5 models of accuracy (Q) in the cross-validation of training set were used to build three different ensemble learning models. In the test1 set, the VOT_CLF3 model had the largest SP (0.871), Q (0.869), AUC (0.919), and MCC (0.728). In the unbalanced test2 set, VOT_CLF3 had the largest SE (0.857), SP (0.867), Q (0.865) and MCC (0.639). VOT_CLF3 was recommended for the virtual screening process of SERT inhibitors. In addition, 12 molecular structural alerts that frequently appear in SERT inhibitors were found (P < 0.05), which provided important reference value for the design work of SERT inhibitors.

Identification of risk factors in epidemiologic study based on ROC curve and network.

This article proposes a new non-parametric approach for identification of risk factors and their correlations in epidemiologic study, in which investigation data may have high variations because of individual differences or correlated risk factors. First, based on classification information of high or low disease incidence, we estimate Receptor Operating Characteristic (ROC) curve of each risk factor. Then, through the difference between ROC curve of each factor and diagonal, we evaluate and screen for the important risk factors. In addition, based on the difference of ROC curves corresponding to any pair of factors, we define a new type of correlation matrix to measure their correlations with disease, and then use this matrix as adjacency matrix to construct a network as a visualization tool for exploring the structure among factors, which can be used to direct further studies. Finally, these methods are applied to analysis on water pollutants and gastrointestinal tumor, and analysis on gene expression data in tumor and normal colon tissue samples.

Comparison of the effectiveness of whole-brain radiotherapy plus temozolomide versus whole-brain radiotherapy in treating brain metastases based on a systematic review of randomized controlled trials.

Temozolomide (TMZ) combination with whole-brain radiotherapy (WBRT) has been tested by many randomized controlled trials in the treatment of brain metastases (BMs) in China and other countries. We performed an up-to-date meta-analysis to determine (i) the log odds ratios (LORs) of objective response (ORR) and adverse effects (AEs) for all-grade, and (ii) the T value of mean overall survival in patients with BMs treated with WBRT combined with TMZ versus WBRT alone. PubMed, Chinese National Knowledge Infrastructure, and WanFang Data were searched for articles published up to 28 January 2015. Eligible studies were selected according to the PRISMA statement. ORR, AEs, and 95% confidence intervals were calculated using random-effects models. Eighteen studies were included in our analysis. A total of 1028 participants were enrolled. Summary LORs of ORR were 1.0239 (P<0.0001) on comparing WBRT plus TMZ with WBRT ORR (n=17). The overall mean difference of mean overall survival (n=17) between TMZ plus WBRT and WBRT was 2.2505 weeks (P=0.02185). There was a significant difference between WBRT plus TMZ and WBRT alone with a LOR of AEs for all-grade of (i) 0.923 for gastrointestinal toxicity and (ii) 0.7978 for myelosuppression. Sensitivity analysis and subgroup analysis were also performed. The 18 eligible randomized controlled trials demonstrated that the combination of WBRT and TMZ significantly improves the ORR and is statistically insignificant in prolonging the survival of patients with BMs. In addition, an increase in the incidence of gastrointestinal toxicity and myelosuppression was significant for all-grade.

Robust discriminant analysis and its application to identify protein coding regions of rice genes.

Identification of protein coding regions is fundamentally a statistical pattern recognition problem. Discriminant analysis is a statistical technique for classifying a set of observations into predefined classes and it is useful to solve such problems. It is well known that outliers are present in virtually every data set in any application domain, and classical discriminant analysis methods (including linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA)) do not work well if the data set has outliers. In order to overcome the difficulty, the robust statistical method is used in this paper. We choose four different coding characters as discriminant variables and an approving result is presented by the method of robust discriminant analysis.