AI Improves Treatment Planning for Intermediate Prostate Cancer

When a patient is told, “You have prostate cancer,” it’s not a simple one-size-fits-all diagnosis. The doctor will then give the patient an idea of how severe his cancer is. If his prostate cancer (PCa) is still localized (that is, contained within the gland), the doctor will specify if it is low, intermediate, or high risk. These describe how likely it is to start progressing to a greater level of danger.

Low risk clearly means there’s very little chance of progression, whereas high risk clearly means the tumor may very soon expand beyond the gland (if it has not already done so). However, the situation with intermediate risk disease is a bit murky. Not all intermediate risk PCa behaves the same. Some will progress more rapidly than others. Thus, intermediate risk PCa is now subdivided into favorable intermediate and unfavorable intermediate risk. “Unfavorable” is a predictor of recurrence after treatment. The issue is, how to pin down the characteristics based on actual prostate tissue samples?

In September, 2024 researchers at the Icahn School of Medicine at Mount Sinai announced the development of a new Artificial Intelligence (AI) tool to improve the management of intermediate risk PCa by distinguishing cellular features that predict recurrence.^[i] This helps doctors plan treatment: the more dangerous the tumor, the more aggressive treatment will need to be.

The new tool, called PATHOMIQ_PRAD, was trained on large datasets of PCa cell features that can be seen on tissue samples from biopsy slides. The researchers collaborated with a Silicon Valley AI company, Pathomiq, using a Deep Learning (DL) program designed to swiftly identify cellular warning signs. Ultimately, this will “…provide more timely, accurate predictions for earlier interventions and more targeted, personalized, treatment plans.”^[ii]

The results of this AI breakthrough were published in the journal European Urology as “A Novel Artificial Intelligence–powered Tool for Precise Risk Stratification of Prostate Cancer Progression in Patients with Clinical Intermediate Risk.”^[iii] Early identification is critical for treatment planning. One of the study authors, renowned urologist Dr. Ash Tewari, described to a medical reporter why he and his team are so excited about their new program:

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.^[iv]

Our Sperling Prostate Center team congratulates the clinicians, scientists and developers who designed and tested this tool. It has the power to improve long-term treatment success for intermediate risk PCa patients, especially for those with less favorable disease.

NOTE: This content is solely for purposes of information and does not substitute for diagnostic or medical advice. Talk to your doctor if you are experiencing pelvic pain, or have any other health concerns or questions of a personal medical nature.

References

[i] Mt. Sinai Medical Center press release. “New AI Tool by Mount Sinai Researchers Could Reshape Prostate Cancer Care.” Sep. 23, 2024.
[ii] Ibid.
[iii] Nair S, Muhammad H, Jain P, Xie C et al. A Novel Artificial Intelligence–powered Tool for Precise Risk Stratification of Prostate Cancer Progression in Patients with Clinical Intermediate Risk. Eur Urol. 2024 Sep 3:S0302-2838(24)02496-5
[iv] “New AI tool could reshape prostate cancer care by identifying those at higher risk of rapid disease progression.” Medical Express. Sep. 23, 2024. https://medicalxpress.com/news/2024-09-ai-tool-reshape-prostate-cancer.html