Publications by authors named "P Lister"
Introduction: Variable selection is a common technique to identify the most predictive variables from a pool of candidate predictors. Low prevalence predictors (LPPs) are frequently found in clinical data, yet few studies have explored their impact on model performance during variable selection. This study compared the Random Forest (RF) algorithm and stepwise regression (SWR) for variable selection using data from a paediatric sepsis screening tool, where 18 out of 32 predictors had a prevalence < 10%.
View Article and Find Full Text PDFArticle Synopsis
- This study investigates the effects of vitamin C and hydrocortisone on pediatric sepsis, aiming to improve survival rates without the need for inotropes/vasopressors.
- The RESPOND trial is a randomized, open-label study involving nine PICUs in Australia and New Zealand, focusing on children under 18 with suspected or confirmed sepsis.
- It will assess outcomes such as time alive without inotropic support, mortality rates, and quality of life, involving 384 patients to generate robust data for better treatment strategies.