AusCAT - Australian Computer-Assisted Theragnostics

Distributed machine learning for improving cancer treatment.

Kirrily Cloak (UNSW Medicine & Health)

The proposal establishes a nationally agreed capability to link regular treatment (clinical practice) and clinical trial data, for machine learning analysis with international links. This will improve accessibility and governance structures to support data users including clinicians, data scientists, governments and policy makers. It leverages the AusCAT approach’s defining feature, i.e. its decentralised nature.This takes analysis to the data and streamlines the administrative, ethical, political aspects of research, enabling learning across datasets that are otherwise difficult to merge due to size or ethical and governance challenges. It will use tools, knowledge and expertise from ARDC 2019 platform projects. We will ensure cohesion with the Australian clinical trials data platform and the ARDC health studies data program (HeSANDA).