e-ISSN 2231-8542
ISSN 1511-3701

Home / Regular Issue / JTAS Vol. 25 (3) Jul. 2017 / JST-S0071-2016


Evaluation of Risk Factors for Prolonged Invasive Mechanical Ventilation in Paediatric Intensive Care Unit (PICU)

Ismail, I., Yap, B. W. and Abidin, A. S. Z.

Pertanika Journal of Tropical Agricultural Science, Volume 25, Issue 3, July 2017

Keywords: Mechanical ventilation, prolonged mechanical ventilation, paediatric, logistic regression, decision tree

Published on: 20 Jun 2017

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 and124 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.

ISSN 1511-3701

e-ISSN 2231-8542

Article ID


Download Full Article PDF

Share this article

Recent Articles