Unplanned extubation (UE) may cause considerable adverse effects in patients receiving mechanical ventilation (MV). Previous literature showed inconsistent prognosis in patients with UE. This study aimed to evaluate the clinical implications and outcomes of UE.The intubated adult patients with MV support in our hospital were enrolled, and they were divided into the UE and non-UE groups. Demographic data, admission unit, MV duration, overall weaning rate, and mortality rates were compared. The outcomes of UE in ordinary ward and intensive care unit (ICU) were also assessed.Totally 9245 intubated adult patients were included. UE occurred in 303 (3.5%) patients, and the UE events were 0.27 times/100 MV days. Old age, nonoperation related MV cause, and admission out of the ICU were significant factors associated with UE events. UE patients showed a trend of better overall weaning rate (71.9% vs 66.7%, P = .054) than non-UE. However, the in-hospital mortality rate (25.7% vs 24.8%, P = .713) were similar between the UE and non-UE patients. The reintubation rate of UE patients was 44.1% (142/322). Successful UEs were associated with patients in weaning process (52.8% vs 38.7%, P = .012), and patients received non-invasive positive pressure ventilation (NIPPV) support after UE (19.4% vs 3.5%, P < .001). Patients with successful UE had significantly shorter MV days, higher overall weaning rate, and lower mortality than those with unsuccessful UE. Outcomes of UE in ordinary ward and in ICU had similar MV duration, reintubation rate, overall weaning rate, and in-hospital mortality rate.The overall weaning rate and in-hospital mortality rates of the UE and non-UE patients were similar. UE occurred in ordinary ward had similar outcomes to those in ICU. Patients receiving MV should be assessed daily for weaning indications to reduce delayed extubation, and therefore, may decrease UE occurrence. Once the UE happened, NIPPV support may reduce the reintubation rate.

No abstract

Pedrycz and Sosnowski proposed C-fuzzy decision trees [5] based on information granulation. The tree grows gradually by using fuzzy C-means clustering algorithm to split the patterns in a selected node with the maximum heterogeneity into C corresponding children nodes. However, the distance function was only defined on the input difference between a pattern and a cluster center, causing difficulties in some cases. Besides, the output model of each leaf node represented by a constant restricts the representation capability about the data distribution in the node. We propose a more reasonable definition of the distance function by considering both the input and output differences with weighting factors. We also extend the output model of each leaf node to a local linear model and estimate the model parameters with a recursive SVD-based least squares estimator. Experimental results have shown that our improved version produces higher recognition rates and smaller mean square errors for classification and regression problems, respectively.

No abstract

No abstract