Researchers at Western Sydney University in Australia have led a global project to develop an AI-driven tool which they claim could change the diagnosis and management of type 1 diabetes (T1D).
This tool uses microRNAs, obtained from blood samples, to calculate the risk of developing T1D and predict treatment responses. The microRNA markers in the study were able to forecast early responses to treatments, including cell therapy like islet transplantation and drug therapy such as imatinib for T1D.
The study, published in Nature Medicine, analysed molecular data from 5,983 participants across countries like Australia, Canada, Denmark, Hong Kong SAR China, India, New Zealand, and the US.
The research introduced a Dynamic Risk Score (DRS4C) that identifies individuals with or without T1D. Validated with another 662 participants, the AI-enhanced risk score predicted which patients would remain insulin-free shortly after receiving therapy. Additionally, the same microRNAs identified potential responders to drug therapy before treatment began.
Beyond predicting T1D risk and drug efficacy, this risk score may distinguish between type 1 and type 2 diabetes. According to the 2025 IDF Atlas, over 1.7 million Australians live with diabetes, including more than 135,000 with T1D.
The risk score and modelling approach may have applications in other healthcare areas. A sub-analysis indicated potential for differentiating between Type 2 and Type 1 Diabetes, addressing misdiagnosis issues.
Western Sydney University School of Medicine and Translational Health Research Institute professor Anand Hardikar said: “T1D risk prediction is timely, with therapies that can delay T1D progression becoming recognised and available. Since early-onset T1D before the age of 10 years is particularly aggressive and linked to up to 16 years of reduced life expectancy, accurately predicting progression gives doctors a powerful tool to intervene sooner.”
The study involved 79 researchers across 33 institutions in seven countries on four continents.
Funding was provided by Breakthrough T1D (formerly JDRF Australia), the Australian Research Council, the National Health and Medical Research Council, and The Leona M. and Harry B. Helmsley Charitable Trust, with support from the Danish Diabetes and Endocrine Academy and Western Sydney University.
