SSA QLD Branch Meeting: Considering patient outcomes and healthcare costs when obtaining prediction model cutpoints may improve value-based care

Please join us online for the August Queensland Branch Meeting, on the 3rd of August. The seminar will start at 4:00pm, with a branch meeting starting at 5:00pm. Please find details for the seminar below.

When: 4:00 PM - 6:00 PM (AEST), Wednesday 3rd August 2022

Location: Q430, Kelvin Grove Campus, Queensland University of Technology, or Online (Zoom link will be sent with registration)

Please note that the seminar will be recorded and might be put on YouTube or similar platform.

Title: Considering patient outcomes and healthcare costs when obtaining prediction model cutpoints may improve value-based care.

Abstract: 

Clinical prediction models estimate the risk that a given patient will experience some healthcare event and can be integrated into computerised clinical decision support systems. Often, these systems guide the use of a clinical intervention and require a cutpoint to categorise the model prediction into intervention assignment or not. Almost all existing cutpoint selection methods are based on classification metrics, including sensitivity and specificity, but do not consider the downstream consequences of the clinical decision: patient outcomes, healthcare costs and the effectiveness of the assignment. In this presentation, I will outline how we can integrate these downstream events into the cutpoint selection process and move towards value-based care. 

Presenter: Rex Parsons

Rex is a PhD candidate and Senior Research Assistant at the Australian Centre Health Services Innovation. His PhD is on prognostic models for inpatient falls and he has been working in biomedical research since 2016. Rex has Bachelor of Science (Honours - Neuroscience) from the University of Queensland and a Master of Medical Statistics from the University of Newcastle.