scholarly journals Developing and evaluating a machine learning based algorithm to predict the need of pediatric intensive care unit transfer for newly hospitalized children

Resuscitation ◽  
2014 ◽  
Vol 85 (8) ◽  
pp. 1065-1071 ◽  
Author(s):  
Haijun Zhai ◽  
Patrick Brady ◽  
Qi Li ◽  
Todd Lingren ◽  
Yizhao Ni ◽  
...  
2017 ◽  
Vol 2017 ◽  
pp. 1-7
Author(s):  
Brian LeCleir ◽  
Leslie Jurecko ◽  
Alan T. Davis ◽  
Nicholas J. Andersen ◽  
Dominic Sanfilippo ◽  
...  

Aim. Our goal in this study is to evaluate the effectiveness of our oxygen (O2) protocol to reduce length of stay (LOS) for children hospitalized with bronchiolitis. Methods. In this retrospective cohort study, the outcomes of children ≤ 24 months old that were admitted with bronchiolitis and placed on the O2 protocol were compared to historical controls. The primary outcome was hospital length of stay. Secondary outcomes were duration of O2 supplementation, rates of pediatric intensive care unit transfer, and readmission. Results. Groups were not significantly different in age, gender, and rates of respiratory distress score assessment. Significantly more severely ill patients were in the O2 protocol group. There were no significant differences between control and O2 protocol groups with regard to mean LOS, rates of pediatric intensive care unit transfer, or seven-day readmission rates. By multiple regression analysis, the use of the O2 protocol was associated with a nearly 20% significant decrease in the length of hospitalization (p=0.030). Conclusion. Use of O2 supplementation protocol increased LOS in the more ill patients with bronchiolitis but decreased overall LOS by having a profound effect on patients with mild bronchiolitis.


Sign in / Sign up

Export Citation Format

Share Document