AI Tool May Help Some Prostate Cancer Patients Avoid Hormone Therapy
Published
Standard treatment for prostate cancer often includes surgery, radiation and up to two years of hormonal therapy, which can cause fatigue, muscle loss, and raise the risk of heart problems. But what if not every patient needs the full course?
Researchers at Duke Cancer Institute, working with the health technology company ArteraAI, have developed a new artificial intelligence-powered biomarker that could help determine which patients need extended hormone therapy and which could safely avoid it.
Using digitized biopsy samples from a large clinical trial of 1,000 patients, the team trained the AI model to spot patterns linked to long-term outcomes, like the risk of cancer spreading to distant parts of the body, a major factor in prostate cancer survival.
“About two-thirds of the men had a positive biomarker, meaning that they benefited from the two years of hormonal therapy,” said Andrew Armstrong, MD, director of research for the DCI Center for Prostate and Urologic Cancers. “But one third of the men did not—they had no added risk of cancer spreading or coming back. That would save a third of all high-risk men that extra 18 months of hormonal therapy.”
The work published in the Journal of Clinical Oncology not only offers hope for more personalized prostate cancer care but also shows how AI tools could help reduce overtreatment and improve quality of life for cancer patients.
“We sought to develop a biomarker using tissue that could identify patients that really need those two years of hormonal therapy, or patients that could have excellent outcomes and not have to spend two years on hormonal therapy,” Armstrong said.
While the development and validation of the biomarker is complete, the team is now moving toward commercialization and creating a product that can be approved and used by doctors.
Armstrong acknowledged the importance of transparency in introducing AI tools into clinical care. He also noted that this may be just the beginning with more AI-driven innovations likely on the way.
“Digital pathology could be applied to many other contexts – kidney cancer, bladder, breast, colon, or lung,” Armstrong said. “There’s a lot of promise; as long as you have big data, long-term outcomes, and tissue samples, AI can uncover patterns that even expert pathologists might miss.”
New research from Duke Cancer Institute (DCI) is helping uncover why some bladder cancer patients are less likely to benefit from a common treatment and how a patient’s cancer history may help guide more personalized care decisions in the future.For more than 50 years, Bacillus Calmette-Guérin (BCG) treatment has been the standard of care for patients with early-stage bladder cancer. It helps reduce the chances that cancer will come back after surgery, and it works well for many patients. But not all bladder cancers behave the same.Bladder cancer is one form of a broader group known as urothelial cancers, which can develop anywhere along the urinary tract. Most cases begin in the bladder itself and are often caught early because patients develop symptoms, such as blood in the urine. These early-stage cancers are typically treated with surgery followed by BCG, which is delivered directly into the bladder to help prevent recurrence.However, about 10 percent of urothelial cancers originate in the upper urinary tract—in the kidneys or ureters. Even after those tumors are treated, cancer can later reappear in the bladder.“Historically, we’ve treated these bladder recurrences the same way we treat primary bladder cancer,” said Yu Guang Tan, MD, a urology fellow at Duke and a collaborator from Duke-NUS Medical School in Singapore. “But the question is, are they really the same disease?”In a recent study published in Urologic Oncology, Tan worked with colleagues including Michael Abern, MD, co-chair of the DCI Center for Prostate and Urologic Cancers, to explore whether bladder cancers that arise after upper tract disease respond differently to BCG than cancers that originate in the bladder.Across both a single-institution study and a larger systematic review and meta-analysis of more than 1,300 patients worldwide, the team found a consistent pattern: patients with a history of upper tract urothelial cancer were significantly more likely to experience recurrence or disease progression after BCG treatment.“In some cases, nearly half of these patients did not respond well to BCG,” Tan said. “That’s a substantial number, and it suggests we may need to think differently about how we treat this group.”BCG has long been the backbone of therapy for non-muscle invasive bladder cancer, but it is not without limitations. In addition to variable effectiveness, the treatment has also faced periodic shortages, particularly in smaller or rural care settings.“This research gives us another piece of the puzzle,” Abern said. “If a patient has a history of upper tract disease, it may shape expectations about how well BCG will work and whether we should consider other options sooner, including clinical trials.”Tan and Abern both emphasize that BCG remains an important and effective therapy for many patients. The goal is not to replace it, but to better match treatments to the patients most likely to benefit.One of the most important implications of the study is its potential role in advancing precision medicine for bladder cancer. The team found that while these cancers may look similar under the microscope, they are likely biologically distinct. That difference may explain why they respond differently to treatment.“We think this history of upper tract cancer may act as a clinical biomarker,” Tan said. “It helps us predict how a patient might respond, but we still need to understand the biology behind it.”To answer that question, the researchers are now conducting whole genome sequencing studies to identify the genetic differences between these tumor types. They are also building a joint database between Duke and Duke-NUS to uncover additional factors that may influence treatment outcomes.“It’s an exciting time in bladder cancer research,” Tan said. “We have many new therapies emerging, and the challenge now is figuring out which treatment is best for which patient.”The research reflects a strong international partnership between Duke University and Duke-NUS Medical School in Singapore. By bringing together data from multiple countries and healthcare systems, the team was able to confirm that these findings are consistent across diverse patient populations.“That global perspective is really important,” Abern said. “It shows that this trend holds true across different regions, which makes the findings more robust and meaningful.”As new therapies, including immunotherapy and targeted treatments, continue to emerge, studies like this one will play a key role in shaping how patients are selected for different treatment approaches.“By better understanding these differences, we can improve how we counsel patients, design clinical trials, and ultimately deliver more personalized care,” Abern said.
New research from Duke Cancer Institute (DCI) is helping uncover why some bladder cancer patients are less likely to benefit from a common treatment and how a patient’s cancer history may help guide more personalized care decisions in the future.For more than 50 years, Bacillus Calmette-Guérin (BCG) treatment has been the standard of care for patients with early-stage bladder cancer. It helps reduce the chances that cancer will come back after surgery, and it works well for many patients. But not all bladder cancers behave the same.Bladder cancer is one form of a broader group known as urothelial cancers, which can develop anywhere along the urinary tract. Most cases begin in the bladder itself and are often caught early because patients develop symptoms, such as blood in the urine. These early-stage cancers are typically treated with surgery followed by BCG, which is delivered directly into the bladder to help prevent recurrence.However, about 10 percent of urothelial cancers originate in the upper urinary tract—in the kidneys or ureters. Even after those tumors are treated, cancer can later reappear in the bladder.“Historically, we’ve treated these bladder recurrences the same way we treat primary bladder cancer,” said Yu Guang Tan, MD, a urology fellow at Duke and a collaborator from Duke-NUS Medical School in Singapore. “But the question is, are they really the same disease?”In a recent study published in Urologic Oncology, Tan worked with colleagues including Michael Abern, MD, co-chair of the DCI Center for Prostate and Urologic Cancers, to explore whether bladder cancers that arise after upper tract disease respond differently to BCG than cancers that originate in the bladder.Across both a single-institution study and a larger systematic review and meta-analysis of more than 1,300 patients worldwide, the team found a consistent pattern: patients with a history of upper tract urothelial cancer were significantly more likely to experience recurrence or disease progression after BCG treatment.“In some cases, nearly half of these patients did not respond well to BCG,” Tan said. “That’s a substantial number, and it suggests we may need to think differently about how we treat this group.”BCG has long been the backbone of therapy for non-muscle invasive bladder cancer, but it is not without limitations. In addition to variable effectiveness, the treatment has also faced periodic shortages, particularly in smaller or rural care settings.“This research gives us another piece of the puzzle,” Abern said. “If a patient has a history of upper tract disease, it may shape expectations about how well BCG will work and whether we should consider other options sooner, including clinical trials.”Tan and Abern both emphasize that BCG remains an important and effective therapy for many patients. The goal is not to replace it, but to better match treatments to the patients most likely to benefit.One of the most important implications of the study is its potential role in advancing precision medicine for bladder cancer. The team found that while these cancers may look similar under the microscope, they are likely biologically distinct. That difference may explain why they respond differently to treatment.“We think this history of upper tract cancer may act as a clinical biomarker,” Tan said. “It helps us predict how a patient might respond, but we still need to understand the biology behind it.”To answer that question, the researchers are now conducting whole genome sequencing studies to identify the genetic differences between these tumor types. They are also building a joint database between Duke and Duke-NUS to uncover additional factors that may influence treatment outcomes.“It’s an exciting time in bladder cancer research,” Tan said. “We have many new therapies emerging, and the challenge now is figuring out which treatment is best for which patient.”The research reflects a strong international partnership between Duke University and Duke-NUS Medical School in Singapore. By bringing together data from multiple countries and healthcare systems, the team was able to confirm that these findings are consistent across diverse patient populations.“That global perspective is really important,” Abern said. “It shows that this trend holds true across different regions, which makes the findings more robust and meaningful.”As new therapies, including immunotherapy and targeted treatments, continue to emerge, studies like this one will play a key role in shaping how patients are selected for different treatment approaches.“By better understanding these differences, we can improve how we counsel patients, design clinical trials, and ultimately deliver more personalized care,” Abern said.
