AI rewrites the script on hormone therapy use in prostate cancer

Artificial intelligence (AI) is reshaping prostate cancer treatment decisions, with an Australian trial revealing substantial reduction in hormone therapy use.

The GenesisCare-led ASTuTE Trial recorded a 20.7% net reduction in androgen deprivation therapy (ADT) use (p<0.001) among Australian men participating in the study. The findings were presented days ago at the American Society for Radiation Oncology (ASTRO) Annual Meeting.

The results have particular significance in the treatment of men with intermediate-risk prostate cancer, for whom the decision to combine radiotherapy with hormone therapy can involve a complex balance between incremental survival benefit and the substantial burden of treatment-related adverse effects.

Hormone therapies such as Lucrin, Zoladex, Eligard and Firmagon, when administered alongside radiotherapy, confer an average survival benefit of approximately 5% across the overall treated population. The therapeutic trade-off has become increasingly consequential as understanding of ADT’s effects on quality of life has evolved. Potential adverse effects include sexual dysfunction, persistent fatigue, hot flushes, osteoporosis, insomnia, diabetes and cardiovascular complications, alongside psychological effects such as depression and mood disturbances.

Principal Investigator and GenesisCare Radiation Oncologist Dr Eric Wegener said, “The ASTuTE Trial findings show that when we use AI to help guide treatment decision-making, a lot of men and their doctors choose differently. Hormone therapy or ADT saves lives, and for some men it is the right treatment choice when faced with prostate cancer. Every man with intermediate-risk prostate cancer has asked me some version of ‘do I really need this?’ Of the men who were recommended for hormone therapy in the trial, three in four went a different way once they had their AI biomarker result.”

The multicentre ASTuTE Trial enrolled 786 participants and examined, in a real-world clinical setting, how a multimodal artificial intelligence (MMAI) biomarker test influenced treatment decisions among men with intermediate-risk prostate cancer undergoing radiotherapy.

Of the 230 men initially recommended short-term ADT before MMAI testing, approximately three in four subsequently elected not to proceed with the treatment. The biomarker also identified a cohort in the opposite direction; 21 men who had not initially been recommended ADT were identified as likely to derive benefit from the therapy.

The net effect was a 20.7% reduction in ADT utilisation, equating to approximately one in five men avoiding hormone therapy.

The AI platform underpinning the study is the Artera AI Prostate Test, which generates a prognostic estimate of a patient’s 10-year risk of metastatic disease while also providing predictive information regarding the likely benefit of adding ADT to radiotherapy in men with intermediate-risk prostate cancer.

Importantly, the influence of the technology appeared to extend beyond the individual test result. Researchers observed that clinicians became progressively less likely to recommend ADT as the trial advanced, including before they had access to a patient’s biomarker result. This raises the possibility that exposure to the tool may have recalibrated clinical decision-making more broadly, rather than simply altering treatment choices in response to individualised test results.

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.