Please use this identifier to cite or link to this item: https://ptsldigital.ukm.my/jspui/handle/123456789/578395
Title: Evaluation of risk factors for prolonged invasive mechanical ventilation in Paediatric Intensive Care Unit (PICU)
Authors: Ismail I (UITM)
Yap B. W (UITM)
Abidin A. S. Z (UITM)
Keywords: Mechanical ventilation
Prolonged mechanical ventilation
Paediatric
Logistic regression
Decision tree
Issue Date: Jul-2017
Description: Prolonged mechanical ventilation (PMV) is associated with increase in mortality and resource utilisation as well as hospitalisation costs. This study evaluates the risk factors of PMV. A retrospective study was conducted involving 890 paediatric patients comprising 237 neonates, 306 infants, 223 of pre-school age and 124 who are of school going age. The data mining decision trees algorithms and logistic regression was employed to develop predictive models for each age category. The independent variables were classified into four categories, that is, demographic data, admission factors, medical factors and score factors. The dependent variable is the duration of ventilation where it is categorized 0 denoting non-PMV and 1 denoting PMV. The performances of three decision tree models (CHAID, CART and C5.0) and logistic regression were compared to determine the best model. The results indicated that the decision tree outperformed the logistic regression model for all age categories, given its good accuracy rate for testing dataset. Decision trees results identified length of stay and inotropes as significant risk factors in all age categories. PRISM 12 hours and principal diagnosis were identified as significant risk factors for infants.
News Source: Pertanika Journals
ISSN: 0128-7680
Volume: 25
Pages: 811-824
Publisher: Universiti Putra Malaysia Press
Appears in Collections:Journal Content Pages/ Kandungan Halaman Jurnal

Files in This Item:
File Description SizeFormat 
ukmvital_115894+Source01+Source010.PDF334.71 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.