Advances in machine learning (ML) provide great opportunities in the prediction of hospital readmission. This review synthesizes the literature on ML methods and their performance for predicting hospital readmission in the US.
 
  This review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) Statement. The extraction of items was also guided by the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS). Electronic databases PUBMED, MEDLINE, and EMBASE were systematically searched from January 1, 2015, through December 10, 2019. The articles were imported into COVIDENCE online software for title/abstract screening and full-text eligibility. Observational studies using ML techniques for hospital readmissions among US patients were eligible for inclusion. Articles without a full text available in the English language were excluded. A qualitative synthesis included study chara regularized logistic regression, and SVM are commonly used to predict hospital readmission in the US. Further research is needed to compare the performance of ML algorithms for hospital readmission prediction.
 The ML algorithms involving tree-based methods, NN, regularized logistic regression, and SVM are commonly used to predict hospital readmission in the US. Further research is needed to compare the performance of ML algorithms for hospital readmission prediction.
  Circular RNA hsa_circ_0008305 (circPTK2), miR-181c-5p and High mobility group box-1 (HMGB1) had a targeted regulatory relationship through bioinformatics analysis. This study explained the effects of these genes in microglia and sepsis mice.
 
  Lipopolysaccharide (LPS) or Cecal Ligation and Puncture (CLP) was used to induce inflammation cell model or sepsis mouse model, as needed. Gene levels were measured by enzyme linked immunosorbent assay (ELISA), quantitative real-time PCR or Western blot, as required. Apoptosis was detected by TUNEL assay, and RNase R was used to test the stability of circPTK2. Targeting relationships between genes were analyzed using bioinformatics analysis and dual luciferase assay. Morris water maze test and mitochondrial membrane potential (MMP) detection were conducted to analyze the effects of genes on cognitive dysfunction of mice.
 
  Lipopolysaccharide induction triggered the release of pro-inflammatory cytokines, the upregulation of HMGB1 and circPTK2, and the downregulation of miR-181c-5p in microglia. Overexpression of HMGB1 enhanced the effect of LPS, while silencing HMGB1 partially counteracted the effect of LPS. Moreover, miR-181c-5p was a target of circPTK2 and bound to HMGB1. MiR-181c-5p mimic partially reversed the functions of LPS and HMGB1 overexpression, reduced the levels of TNF-α, IL-1β, and HMGB1, and inhibited apoptosis. CircPTK2 knockdown had the same effect as miR-181c-5p up-regulation. In vivo, sicircPTK2 improved cognitive function, restored MMP level, inhibited apoptosis, reduced the levels of inflammatory factors and apoptotic factors, and increased the survival rate of CLP-induced mice.
 
  Our research reveals that circPTK2 regulates microglia activation and hippocampal neuronal apoptosis induced by sepsis via miR-181c-5p-HMGB1 signaling.
 Our research reveals that circPTK2 regulates microglia activation and hippocampal neuronal apoptosis induced by sepsis via miR-181c-5p-HMGB1 signaling.
  In longitudinal critical care studies, researchers may be interested in summarizing an exposure over time and evaluating its association with a long-term outcome. For example, the number of days a patient has delirium (i.e., brain dysfunction) during their critical care stay is associated with the presence and severity of long-term cognitive problems. In large pragmatic trials and multicenter observational studies, particularly when electronic medical record data is used, the information on daily exposure status may be available at some time points and not at others. Model-based multiple imputation is a well-established, widely adopted method to deal with missing data. But the uncertainty around multiple imputation for summary exposure variables is whether the imputation is to be performed at the summary level or at the daily assessment level.
 
  We compare the following approaches to imputing and summarizing partially missing longitudinal data 1) active imputation, where we impute the summary; 2) passive impproach provides efficient and less biased estimates under the missingness at random and missingness completely at random mechanism.
 
  For longitudinal data where a summary exposure is of interest, we recommend practitioners adopting the passive imputation strategy.
 For longitudinal data where a summary exposure is of interest, we recommend practitioners adopting the passive imputation strategy.
  There are no accurate estimates of the prevalence of non-severe maternal morbidities. Given the lack of instruments to fully assess these morbidities, the World Health Organization (WHO) developed an instrument called WOICE. We aimed to evaluate the prevalence of non-severe maternal morbidities in puerperal women and factors associated to impaired clinical, social and mental health conditions.
 
  A cross-sectional study with postpartum women at a high-risk outpatient clinic in southeast Brazil, from November 2017 to December 2018.  https://www.selleckchem.com/peptide/avexitide.html  The WOICE questionnaire included three sections the first with maternal and obstetric history, sociodemographic data, risk and environment factors, violence and sexual health; the second considers functionality and disability, general symptoms and mental health; and the third includes data on physical and laboratory tests. Data collection was supported by Tablets with REDCAP software. Initially, a descriptive analysis was performed, with general prevalence of all variables containepartner reduced perception of women on the presence of clinical morbidities.
 
  During postpartum care of a high-risk population, over one third of the considered women presented anxiety and depression; 10% reported substance use and around 6% exposure to violence. These aspects of women's health need further evaluation and specific interventions to improve quality of care.
 During postpartum care of a high-risk population, over one third of the considered women presented anxiety and depression; 10% reported substance use and around 6% exposure to violence. These aspects of women's health need further evaluation and specific interventions to improve quality of care.