AI-powered test to reshape use of hormone therapy in prostate cancer

Australian researchers are pioneering the use of artificial intelligence (AI) to enhance decision-making in prostate cancer treatment, specifically focusing on the combination of androgen deprivation therapy (ADT) with radiotherapy. The study, known as ASTuTE, aims to optimise treatment outcomes while minimising potential risks associated with ADT.

Short-term ADT (also known as hormone therapy), administered over 4-6 months alongside radiation therapy, has demonstrated improvements in disease outcomes for patients with intermediate-risk localised prostate cancer. Despite its efficacy, ADT like Lucrin, Firmagon or Eligard is linked to adverse effects such as weight gain, reduced bone density, insulin sensitivity, and altered lipid profiles. These complications not only impact patient quality of life but also pose challenges to healthcare systems.

The key issue addressed by the ASTuTE study lies in identifying patients who stand to benefit most from short-term ADT treatment when combined with radiotherapy.

Dr Eric Wegener, Radiation Oncologist at GenesisCare and principal investigator of the ASTuTE study, said “AI-powered biomarker reshapes prostate cancer treatment decisions, reducing overtreatment and providing prognostic insights crucial for informed ADT decisions.”

Central to the study’s approach is the ArteraAI prostate test, developed using a multi-modal AI (MMAI) deep learning architecture that integrates clinical and imaging data. The test comprises two AI models: a prognostic model estimating risks of distant metastasis and prostate cancer-specific mortality, and a hormone therapy benefit model offering a binary prediction of ADT’s effectiveness in conjunction with radiotherapy.

By December 2024, the ASTuTE study had enrolled 296 participants nationwide, with a review conducted on 208 patients. Notably, 67% of patients initially considering ADT changed their treatment decision based on the ArteraAI test results, highlighting the trial’s role in enabling informed patient choices and potentially reducing unnecessary treatments.

The AI models underpinning ArteraAI were trained and validated using data from five phase III randomised controlled trials involving 5,654 patients and over 16,204 histopathology slides.

In reimagining healthcare across the entire patient journey, Health Industry Hub^TM is the only one-stop-hub uniting the diversity of the Pharma, MedTech, Diagnostics & Biotech sectors to inspire meaningful change.

The Health Industry Hub^TM content is copyright protected. Access is available under individual user licenses. Please click here to subscribe and visit T&Cs here.