In a groundbreaking medical advancement, scientists have developed an artificial intelligence (AI) test capable of identifying which men with high-risk prostate cancer will benefit most from the life-extending drug abiraterone—a treatment shown to reduce the risk of death by nearly half.
Although abiraterone has been hailed as a “gamechanger” in prostate cancer care, some countries have limited its use to patients with advanced, spread-stage disease. The newly developed AI tool—created by researchers from the US, UK, and Switzerland—may help expand access by precisely identifying patients likely to respond to the drug before their cancer spreads.
The AI algorithm analyzes routine pathology slides, extracting subtle features from tumor images that are undetectable to the human eye. When tested on biopsy samples from over 1,000 men with high-risk localized prostate cancer, the tool revealed that approximately 25% of patients could benefit significantly when abiraterone is added to standard hormone therapy—almost halving their risk of death.
“This study demonstrates how cutting-edge AI can tailor treatment by uncovering hidden insights in tumor slides,” said Professor Gert Attard, co-lead of the study. “We can now reduce overtreatment and offer personalized therapies that increase the chances of survival.”
Abiraterone works by stopping testosterone production throughout the body, including inside the tumor, helping prevent cancer growth.
Professor Nick James, also a co-lead on the trial, emphasized the potential policy impact: “This research allows us to pinpoint exactly who needs abiraterone to live longer, healthier lives. I hope NHS England and other health systems will reconsider funding it for men with high-risk non-metastatic prostate cancer.”
The results of the trial were presented at the American Society of Clinical Oncology (ASCO) Annual Meeting 2025.