Getty Images

AI could improve prostate cancer risk stratification

A deep learning tool could identify intermediate-risk prostate cancer patients more likely to experience rapid disease progression and help inform personalized treatment plans.

A research team from the Icahn School of Medicine at Mount Sinai have developed an AI tool that could improve prostate cancer prognostication and management, according to a recent European Urology study.

The American Cancer Society indicates that aside from skin cancer, prostate cancer is the most common cancer diagnosis for men in the United States, leading to an estimated 299,010 new cases and 35,250 deaths from the disease in 2024.

While the number of prostate cancer diagnoses declined significantly from 2007 to 2014, since then incidence rates have increased by roughly 3% overall and 5% for advanced-stage prostate cancers.

Improving outcomes for prostate cancer patients requires early interventions to slow disease prognosis and personalize treatments, but limitations in prognostication for certain patient subgroups make this difficult.

"About 60 percent of patients in the intermediate-risk group don't have a clear treatment plan, and around 30 to 50 percent see their cancer progress after the first round of therapy. We're finding that some of these patients are at higher risk for rapid progression, so identifying them early is critical," explained the study's co-corresponding author Ash Tewari, MD, MBBS, MCh, professor and chair of the Milton and Carroll Petrie department of urology at Icahn Mount Sinai, in a press release.

To overcome these hurdles, the researchers sought to explore whether AI-driven analysis of medical images could improve prostate cancer risk stratification.

The model, PATHOMIQ_PRAD, is designed to utilize deep learning to extract morphological features from whole-slide biopsy and surgical images. In doing so, the tool could identify intermediate-risk patients at higher risk of rapid prostate cancer progression, enabling clinicians to more accurately predict prognosis and develop personalized treatment plans.

"We developed this tool to analyze samples from biopsies or surgeries, providing a clearer understanding of which patients may require more aggressive treatment earlier to improve their outcomes. PATHOMIQ_PRAD has the potential to become a routine part of clinical decision-making," Tewari noted.

PATHOMIQ_PRAD provides a patient risk score from zero to one, with a higher score indicating the presence of high-risk features in the imaging.

To test the model, the research team tasked it with classifying large cohorts of patients into high- and low-risk groups based on established cutoffs for metastasis and biochemical recurrence, which can shed light on the chances of the cancer returning.

The tool outperformed existing five-year cancer outcome benchmarks when compared with other risk stratification tools.

"One key advantage of the tool is its ability to analyze specific regions of tissue that may hold clues to previously undiscovered drivers of prostate cancer progression. This insight could potentially lead to advancements in understanding racial disparities in prostate cancer outcomes, helping us explore why certain populations face more aggressive disease," said co-corresponding author Sujit S. Nair, Ph.D., assistant professor and director of GU immunotherapy research in the department of urology at Icahn Mount Sinai. "These developments are exciting, and we are working toward further validation studies."

The research team indicated that PATHOMIQ_PRAD is a first in the realm of healthcare-driven risk stratification AI, designed to be a scalable, generalizable and affordable option for intermediate-risk prostate cancer management.

"Our study pioneers an innovative design, and we're thrilled about the AI tool's potential to transform risk stratification for prostate cancer patients, paving the way for future advances," stated study co-author Rachel Brody, MD, Ph.D., professor of pathology, molecular and cell-based medicine at Icahn Mount Sinai.

Shania Kennedy has been covering news related to health IT and analytics since 2022.

Dig Deeper on Predictive analytics in healthcare

xtelligent Health IT and EHR
xtelligent Healthtech Security
xtelligent Healthcare Payers
xtelligent Pharma Life Sciences
Close