Machine learning is an ever-improving technology that has the potential to use the vast amounts of data contained in the modern electronic medical record to improve patient care. Through the application of machine learning techniques, trends in patient data can be analysed and predictions made about patients’ risk, giving clinicians an opportunity to mitigate those risks earlier.
Postoperative hypotension is a complex clinical problem that is associated with significant harm during the postoperative period. Data analysis and machine learning techniques represent an opportunity to better understand the magnitude of this problem and predict which patients might be at risk of postoperative hypotension.
The aim of this research is to develop and validate a machine learning model to predict hypotension in postoperative patients. This research is part of a wider program of work to implement an alternative model of postoperative care in our institution. A machine learning model may be helpful as a decision support tool to assist clinicians to identify which patients would most benefit from this alternative model of postoperative care.
Gold Coast University Hospital anaesthesia clinicians Dr Rachel Bourke and Dr Halia O’Shea have partnered with data analysts, Associate Professor Paulina Stehlik (Griffith University) and Principal Research Scientist Dr Sankalp Khanna at the CSIRO Australian e-health research centre.
Dr Rachel Bourke, Dr Halia O'Shea, Dr David Evans, Gold Coast University Hospital, Queensland,
Professor Steven Stern, Bond University, Queensland,
Associate Professor Paulina Stehlik, Griffith University, Queensland,
Dr Sankalp Khanna, Dr Aida Brankovic, CSIRO Australian e-Health Research Centre, Queensland.
The project was awarded A$70,000 funding through the ANZCA research grants program for 2024.