The Invasive Fungal Infection Surveillance (IFIS) tool
Lead - Prof Karin Thursky
PhD Student - Anna Khanina
Invasive fungal infections (IFIs) are rare but serious infections most commonly affecting immunocompromised and critically ill patients. IFIs are associated with high morbidity, mortality, and costly management. Routine IFI surveillance is needed in healthcare facilities to allow timely detection of infection outbreaks, to identify new and emerging risks for IFI, evaluate infection prevention and prophylaxis interventions, and to allow benchmarking between facilities.
Traditional manual surveillance approaches are subjective, resource-intensive, time-consuming, error prone and subject to under-reporting. Overcoming these barriers may be possible in the era of artificial intelligence (AI).
Our team, in collaboration with the Royal Melbourne Institute of Technology (RMIT), The Guidance Group at Melbourne Health and BioGrid Australia are working together to develop a platform for automated routine surveillance of IFI, employing a combination of AI techniques to identify episodes of IFI. Our goal is to go beyond the development of an AI model by creating a web-based user interface accessible by medical professionals to support surveillance and management of IFI in clinical practice.
EINSTIEN
Lead- A/Prof Leon Worth
The MRFF funded (MRFCR1000188) EINSTEIN (enhancing infection surveillance to transform excellence in national cancer care) platform will utilise a digital learning health framework and novel data science to address the unmet need of detecting serious and emerging infections in the immune-compromised cancer population. We will prospectively develop a national scalable system standardising digital algorithms that will support the continual improvement and validation of existing and new algorithms in a research environment. We will then facilitate the supply of algorithm outputs to clinicians by building a clinical portal to accommodate everyday workflows in an electronic health record environment for regular clinical use.
SIRCA- Surveillance of IR-Colitis using AI
PhD Student - Dr Jasmine Teng
Immune checkpoint inhibitors (ICI) have revolutionised the treatment landscape of solid cancers over the past decade. However, their use is complicated by an array of significant auto-immune adverse events. IR-colitis, an auto-inflammatory condition of the colon, impacts up to 30% of patients. Moderate-to-severe cases of IR-colitis can lead to significant morbidity such as gut perforation, infection and death.
In Australia, monitoring systems for IR-colitis are not routine and data concerning healthcare costs within this cohort are lacking. There is also heterogeneity in treatment approaches for patients with IR-colitis. Challenges in case-finding and standardised classification of cases using existing data frameworks hamper real-world research in this area.
This project aims to: (i) develop a digital tool that enables case-finding, and (ii) map the clinical care pathways of patients with IR-colitis by applying artificial intelligence methods to electronic medical record data captured as part of routine clinical care. A multi-specialty team from Internal Medicine, Oncology, Health Services Research and Biomedical Informatics will be engaged using a Learning Health Systems framework to facilitate this research.
Important outputs of this project include a scalable, inter-operable, case-finding digital tool which supports descriptive epidemiology of IR-colitis; description of key events in workflow and turnaround times within the healthcare delivery process for patients with IR-colitis; and reporting of healthcare costs related to management of IR-colitis.