AI Test Identifies Prostate Cancer Patients Who Benefit Most from Abiraterone Treatment

New AI test identifies prostate cancer patients who benefit from abiraterone

University College LondonMay 30 2025 A new artificial intelligence (AI) test can identify which men with prostate cancer will benefit most from the life-extending drug abiraterone, in clinical trial results presented by scientists from UCL and the Institute of Cancer Research. The researchers analyzed prostate cancer tumour samples from men with high-risk prostate cancer that had not spread, who took part in the STAMPEDE trial. Using the new AI test, they found that abiraterone given alongside standard hormone therapy almost halves the risk of death for approximately 25% of men with this type of cancer. However, since many men do well with standard therapy, there is a need to better select those who would gain the most benefit. Experts say that because fewer men than previously thought will need the drug, NHS England should review the decision not to fund the treatment for this group of men. The natural history of advanced and aggressive prostate cancer is highly variable and now with better treatments, the risk of cancer relapse can be significantly reduced. This study shows, in a very large cohort of patients, that novel AI algorithms can be used to extract information from routinely available pathology slides to tailor these treatments to specific patients and minimize overtreatment whilst maximizing the chance of cure." Professor Gert Attard, co-lead of the trial from UCL Cancer Institute Abiraterone, discovered in the UK at The Institute of Cancer Research (ICR), works by inhibiting the production of the hormone testosterone in all tissues throughout the body, including in the tumour. It is approved for use on the NHS in England for patients with advanced prostate cancer that has come back and spread to other parts of the body, but not for the 8,400 men per year with newly diagnosed, high-risk prostate cancer that has not yet spread. However, it has been available for men with this indication in Scotland and Wales for two years. The new test, developed by Artera Inc., uses AI to study images of tumour samples and spot features that are invisible to the human eye. The researchers used the test on biopsy images from more than 1,000 men who took part in the STAMPEDE trial. Patients were given a score - either biomarker-positive or biomarker-negative - that was compared to the outcomes of their illness. For patients with biomarker-positive tumours, abiraterone cut the risk of death after five years from 17% to 9%. For those with biomarker-negative tumours, risk of death without abiraterone was 7%, which was cut to 4% with abiraterone - a difference that was not statistically or clinically significant. These men would therefore benefit from standard therapy alone and could avoid unnecessary treatment and the additional side effects that come with it. Professor Nick James, co-lead of the trial from the Institute of Cancer Research and the Royal Marsden NHS Foundation Trust, said: "Abiraterone has already hugely improved the outlook for hundreds of thousands of men with advanced prostate cancer. We know that for many men with cancer that has not yet spread, it can also have spectacular results. But it does come with side effects and requires additional monitoring for potential issues with high blood pressure or liver abnormalities. It can also slightly increase the risk of diabetes and heart attacks, so knowing who is most likely to benefit is very valuable. "This research shows that we can pick out the people who will respond best to abiraterone, and those who will do well from standard treatment alone - hormone therapy and radiotherapy. "Access to this life-extending drug is currently a postcode lottery - with those living in Scotland and Wales able to receive the treatment for free. The NHS in England has previously decided that it would be too expensive to offer the drug. Since the patent expired in 2022, abiraterone costs just £77 per pack - compared with the thousands of pounds that new drugs cost. Previous research by my team has shown that preventing cancer relapses for these men would save more money than the drug costs to purchase. I truly hope that this new research - showing precisely who needs the drug to live well for longer - will lead to NHS England reviewing their decision to fund abiraterone for high-risk prostate cancer that has not spread." Dr Matthew Hobbs, Director of Research at Prostate Cancer UK, said: "STAMPEDE has driven huge improvements in prostate cancer treatment over the past decade. But we recognised that the samples and data from men in the trial represented an untapped resource and a way to deliver the sort of precision treatment we have seen benefiting patients with other cancers for years. "To unlock that potential, Prostate Cancer UK, in partnership with Movember, awarded £1.4m to lead the way in getting a more precise understanding of prostate cancer, including by using AI tools. Today's results show that our strategic investment is now delivering exactly what we were aiming for: tools that identify men most likely to benefit from a treatment. "Prostate Cancer UK has been calling on the UK Government to approve this life-saving, cost-effective drug for over two years. These exciting results suggest a way to make this an even more cost-effective approach. We therefore echo the researchers' urgent call for abiraterone to be made available to those men whose lives it can save - men who, thanks to this research, we can now identify more precisely than ever before." Giles Turner, 64, who lives in Brighton, was diagnosed with prostate cancer in March 2023. He has been taking abiraterone for almost two years and has spent £20,000 on his treatment so far. He said: "This is great research and adds even more reason for NHS England to start funding this treatment now. I find it very difficult to come to terms with having to pay for this treatment, whereas if I was with the NHS in Scotland or Wales I would not. Even more important are the thousands of men in England who are missing out on this cheap, life-saving and cost-saving drug. Action must be taken by NHS England and the government right now." The trial results were presented at the American Society of Clinical Oncology (ASCO) Annual Meeting 2025. This current research received funding from Artera Inc., UK Medical Research Council and Prostate Cancer UK. The STAMPEDE trial is coordinated by the Medical Research Council (MRC) Clinical Trials Unit at UCL and is funded by Cancer Research UK. University College London

AI test to determine best prostate cancer treatment could save lives and money

A new artificial intelligence (AI) test can identify which men with prostate cancer will benefit most from the life-extending drug abiraterone, in clinical trial results presented by scientists from UCL and the Institute of Cancer Research at the American Society of Clinical Oncology (ASCO 2025) Annual Meeting. The researchers analyzed prostate cancer tumor samples from men with high-risk prostate cancer that had not spread, who took part in the STAMPEDE trial. Using the new AI test, they found that abiraterone given alongside standard hormone therapy almost halves the risk of death for approximately 25% of men with this type of cancer. However, since many men do well with standard therapy, there is a need to better select those who would gain the most benefit. Experts say that because fewer men than previously thought will need the drug, NHS England should review the decision not to fund the treatment for this group of men. Professor Gert Attard, co-lead of the trial from UCL Cancer Institute, said, "The natural history of advanced and aggressive prostate cancer is highly variable and now with better treatments, the risk of cancer relapse can be significantly reduced. This study shows, in a very large cohort of patients, that novel AI algorithms can be used to extract information from routinely available pathology slides to tailor these treatments to specific patients and minimize overtreatment while maximizing the chance of cure." Abiraterone, discovered in the UK at The Institute of Cancer Research (ICR), works by inhibiting the production of the hormone testosterone in all tissues throughout the body, including in the tumor. It is approved for use on the NHS in England for patients with advanced prostate cancer that has come back and spread to other parts of the body, but not for the 8,400 men per year with newly diagnosed, high-risk prostate cancer that has not yet spread. However, it has been available for men with this indication in Scotland and Wales for two years. The new test, developed by Artera Inc., uses AI to study images of tumor samples and spot features that are invisible to the human eye. The researchers used the test on biopsy images from more than 1,000 men who took part in the STAMPEDE trial. Patients were given a score -- either biomarker-positive or biomarker-negative -- that was compared to the outcomes of their illness. For patients with biomarker-positive tumors, abiraterone cut the risk of death after five years from 17% to 9%. For those with biomarker-negative tumors, risk of death without abiraterone was 7%, which was cut to 4% with abiraterone -- a difference that was not statistically or clinically significant. These men would therefore benefit from standard therapy alone and could avoid unnecessary treatment and the additional side effects that come with it. Professor Nick James, co-lead of the trial from the Institute of Cancer Research and the Royal Marsden NHS Foundation Trust, said, "Abiraterone has already hugely improved the outlook for hundreds of thousands of men with advanced prostate cancer. We know that for many men with cancer that has not yet spread, it can also have spectacular results. "But it does come with side effects and requires additional monitoring for potential issues with high blood pressure or liver abnormalities. It can also slightly increase the risk of diabetes and heart attacks, so knowing who is most likely to benefit is very valuable. "This research shows that we can pick out the people who will respond best to abiraterone, and those who will do well from standard treatment alone -- hormone therapy and radiotherapy. "Access to this life-extending drug is currently a postcode lottery -- with those living in Scotland and Wales able to receive the treatment for free. The NHS in England has previously decided that it would be too expensive to offer the drug. Since the patent expired in 2022, abiraterone costs just £77 per pack -- compared with the thousands of pounds that new drugs cost. "Previous research by my team has shown that preventing cancer relapses for these men would save more money than the drug costs to purchase. I truly hope that this new research -- showing precisely who needs the drug to live well for longer -- will lead to NHS England reviewing their decision to fund abiraterone for high-risk prostate cancer that has not spread." Dr. Matthew Hobbs, Director of Research at Prostate Cancer UK, said, "STAMPEDE has driven huge improvements in prostate cancer treatment over the past decade. But we recognized that the samples and data from men in the trial represented an untapped resource and a way to deliver the sort of precision treatment we have seen benefiting patients with other cancers for years. "To unlock that potential, Prostate Cancer UK, in partnership with Movember, awarded £1.4m to lead the way in getting a more precise understanding of prostate cancer, including by using AI tools. Today's results show that our strategic investment is now delivering exactly what we were aiming for: tools that identify men most likely to benefit from a treatment. "Prostate Cancer UK has been calling on the UK Government to approve this life-saving, cost-effective drug for over two years. These exciting results suggest a way to make this an even more cost-effective approach. We therefore echo the researchers' urgent call for abiraterone to be made available to those men whose lives it can save -- men who, thanks to this research, we can now identify more precisely than ever before." Giles Turner, 64, who lives in Brighton, was diagnosed with prostate cancer in March 2023. He has been taking abiraterone for almost two years and has spent £20,000 on his treatment so far. He said, "This is great research and adds even more reason for NHS England to start funding this treatment now. I find it very difficult to come to terms with having to pay for this treatment, whereas if I was with the NHS in Scotland or Wales I would not. Even more important are the thousands of men in England who are missing out on this cheap, life-saving and cost-saving drug. Action must be taken by NHS England and the government right now."

New AI test can predict which men will benefit from prostate cancer drug

Artificial intelligence tool determines best candidates to take abiraterone, which can halve risk of death from disease Doctors have developed an artificial intelligence tool that can predict which men with prostate cancer will benefit from a drug that halves the risk of dying. Abiraterone has been described as a "gamechanger" treatment for the disease, which is the most common form of cancer in men in more than 100 countries. It has already helped hundreds of thousands with advanced prostate cancer to live longer. But some countries, including England, have stopped short of offering the "spectacular" drug more widely to men whose disease has not spread. Now a team from the US, UK and Switzerland have built an AI test that shows which men would most likely benefit from abiraterone. The "exciting" breakthrough will enable healthcare systems to roll out the drug to more men, and spare others unnecessary treatment. The AI test is being unveiled in Chicago at the annual meeting of the American Society of Clinical Oncology, the world's largest cancer conference. Nick James, professor of prostate and bladder cancer research at the Institute of Cancer Research in London and a consultant clinical oncologist at the Royal Marsden NHS foundation trust, co-led the team that built it. "Abiraterone has already hugely improved the outlook for hundreds of thousands of men with advanced prostate cancer," said James. "We know that for many men with cancer that has not yet spread, it can also have spectacular results. "But it does come with side-effects and requires additional monitoring for potential issues with high blood pressure or liver abnormalities. It can also slightly increase the risk of diabetes and heart attacks, so knowing who is most likely to benefit is very valuable. "This research shows that we can pick out the people who will respond best to abiraterone, and those who will do well from standard treatment alone - hormone therapy and radiotherapy." The test uses AI to study images of tumours and pick out features invisible to the human eye. The team, funded by Prostate Cancer UK, the Medical Research Council and Artera, trialled the test on biopsy images from more than 1,000 men with high-risk prostate cancer that had not spread. The AI test identified the 25% of men in the group most likely to benefit from the abiraterone - for these men, the drug halves the risk of death. In the trial, patients received a score - biomarker-positive or -negative - which was compared with their outcomes. For those with biomarker-positive tumours, one in four of the men, abiraterone cut their risk of death after five years from 17% to 9%. For those with biomarker-negative tumours, abiraterone cut the risk of death from 7% to 4% - a difference that was not statistically or clinically significant, the team said. These men would benefit from standard therapy alone and be spared unnecessary treatment. The study co-leader Prof Gert Attard, of the UCL Cancer Institute, said: "This study shows, in a very large cohort of patients, that novel algorithms can be used to extract information from routinely available pathology slides to tailor these treatments to specific patients and minimise over treatment whilst maximising the chance of cure." James said that because fewer men than previously thought would need the drug, healthcare systems should consider giving it to men whose cancer had not spread. It is approved for NHS use in England for advanced prostate cancer, but not for newly diagnosed high-risk disease that has not spread. However, it has been available for men with this indication in Scotland and Wales for two years. "Abiraterone costs just £77 per pack, compared with the thousands of pounds that new drugs cost," said James. "I truly hope that this new research - showing precisely who needs the drug to live well for longer - will lead to NHS England reviewing their decision not to fund abiraterone for high-risk prostate cancer that has not spread." Dr Matthew Hobbs, director of research at Prostate Cancer UK, described the AI test as "exciting". He added: "We therefore echo the researchers' urgent call for abiraterone to be made available to those men whose lives it can save - men who, thanks to this research, we can now identify more precisely than ever before."

Give prostate cancer patients drug that halves risk of death, NHS told

In cases which were fuelled by the hormones - which makes the disease more aggressive - giving men abiraterone cut the risk of death after five years from 17 per cent to 9 per cent. In cases which were not, the risk went from 7 to 4 per cent among those given the drug, which experts said was not statistically or clinically significant. Such men would benefit from standard treatment, which would spare them the side effects which come with abiraterone, experts said. The current research received funding from Artera Inc., UK MRC and Prostate Cancer UK. Professor Nick James, Professor of Prostate and Bladder Cancer Research at The Institute of Cancer Research, London, who co-led the study said that the drug had already been found to have "spectacular results" for many men. He said the new findings allowed the treatment to be far more narrowly targeted, to pick out those who would respond best, and spare others from side effects. The Consultant Clinical Oncologist at The Royal Marsden NHS Foundation Trust said access to the life extending drug was currently "a postcode lottery" despite the fact the drug costs just £2.75 a day. He urged NHS England to fund the drugs. Professor Kristian Helin, Chief Executive of The Institute of Cancer Research, said: "Abiraterone has been a game changer for treatment of prostate cancer, and I'm proud of the ICR's role in discovering and testing this drug which has extended the lives of so many men. "Alongside our mission to find smarter, kinder treatments, we must ensure we are matching the right drugs to the right patients. This research, using artificial intelligence, provides an innovative route to testing prostate cancer patients to determine their treatment. I hope that this can be implemented so that all men with prostate cancer who will benefit from abiraterone can do so."

New AI tool could identify which patients may benefit from cancer drug

The test could help direct prostate cancer patients to the best treatment option for them, researchers behind the findings said. A new artificial intelligence (AI) tool could boost health outcomes for some men with prostate cancer by identifying whether they would benefit from a promising treatment. The drug abiraterone works by blocking testosterone production throughout the body, including in the tumour. It's been shown to slash the risk of death by nearly half for about one in four men with prostate cancer - but it can be costly and have side effects, making health authorities wary of prescribing it too readily. That means getting abiraterone to the right patients at the right time could help improve their prognosis, while also avoiding over-treating patients who might not benefit from the drug, according to the study led by UK institutions. "This research shows that we can pick out the people who will respond best to abiraterone, and those who will do well from standard treatment alone - hormone therapy and radiotherapy," Nick James, the study's co-lead and a professor of prostate and bladder cancer research at the UK's Institute of Cancer Research, said in a statement. The findings were presented this week at the American Society of Clinical Oncology's annual meeting in Chicago. Scientists used AI to study images of tumour samples and identify biomarkers that could have otherwise gone undetected, and then applied the test to biopsy images from more than 1,000 men who had participated in another clinical trial on prostate cancer treatments. Among patients with biomarker-positive tumours, abiraterone slashed the risk of death from 17 per cent to 9 per cent within five years. For those with biomarker-negative tumours, abiraterone did not significantly reduce their mortality risks - meaning these patients should receive standard treatment, the study concluded. Researchers noted that abiraterone can cause side effects such as high blood pressure, liver problems, and diabetes, meaning the AI tool could help direct prostate cancer patients to the best treatment for them. "This study shows, in a very large cohort of patients, that novel algorithms can be used to extract information from routinely available pathology slides to tailor these treatments to specific patients and minimise over treatment whilst maximising the chance of cure," Gert Attard, the study's co-lead and a professor of medical oncology at the University College London Cancer Institute, said in a statement. In the United Kingdom, abiraterone has been approved in Scotland and Wales to treat newly-diagnosed, high-risk prostate cancer that has not yet spread, but in England, it is only available through the National Health Service (NHS) for men whose cancer has metastasised. The researchers called on the NHS to reassess this decision, saying 8,400 men per year could potentially benefit from the drug. "Access to this life-extending drug is currently a postcode lottery - with those living in Scotland and Wales able to receive the treatment for free," James said. Prostate cancer is one of the most common forms of cancer for men, with nearly 336,000 new cases diagnosed every year in the European Union.