Building the tool meant drawing on the skills of a diverse range of experts, starting with doctors.
“We first sat down with the clinicians who helped us understand the clinical data, the medical terminology, and the problem they needed to solve,” Verspoor said.
Clinical collaborators include Professor Karin Thursky, an infectious diseases physician and health services researcher at Peter MacCallum, and her colleague Dr Anna Khanina, a clinical pharmacist who focusses on using data to enhance infection surveillance in cancer patients.
“After engaging the clinical experts we worked to build the AI solutions that allow us to transform data into information,” Verspoor said.
“Interface designers worked with clinicians to co-design a user interface that provides information visually and aligns to their workflows. We also needed software developers to integrate the technology into the hospital environment.”
A fundamental challenge was deployment of effective AI models into the clinical environment.
“Working at the intersection of AI and medicine is challenging but rewarding,” Verspoor said.
“Complex clinical criteria coupled with small data sets required us to be innovative in our approach.”
The system only went live at Peter MacCallum and the Royal Melbourne Hospital in early May so it’s too early to obtain feedback from the doctors who are using it.
Initial signs are promising: “It’s early days, but so far we know it’s working, it’s stable and it’s providing data.”
Verspoor stresses that the tool will in no way override the professional judgement of medical experts.
“Its utility depends on trust,” she said. “It’s there to add value to the work of the clinicians, helping them do their jobs. It’s not replacing anyone.”
Organisations interested in partnering with RMIT University can contact research.partnerships@rmit.edu.au.
This article originally appeared in the Australian Financial Review on 2 June 2026, republished here with permission.
