Artificial Intelligence Helps Predict Prostate Cancer Progression

Artificial intelligence (AI) is being used in a wide variety of fields and circumstances today, ranging from financial analysis, educational tutoring, aviation stimulators, and robotics. Medical research is another hot area, and recently one of the many questions investigators have asked is, can artificial intelligence help predict prostate cancer progression after surgery?

Even though prostate cancer is usually a slow-growing disease and the majority of men who undergo surgery (prostatectomy) emerge with a good prognosis, up to about 30 percent of patients experience a recurrence post-surgery. To help lower that percentage, clinicians need better tools to help them determine the risk of progression and alternative ways to monitor and treat the disease after surgery.

Researchers have been evaluating numerous prognostic factors associated with prostate cancer progression to help them distinguish the more aggressive from the more slow-growing tumors to help establish the best treatment strategies.

One of the newest attempts in that arena has been the introduction of artificial intelligence.

Prostate cancer progression using AI

At Mount Sinai Hospital/School of Medicine, a team of experts used a pathology test that utilizes artificial intelligence to characterize prostate cancer tissue samples from 590 patients who had undergone radical prostatectomy. The test, which is called the Precise MD post-op test, involves the use of an algorithm that automates the Gleason score and integrates image analysis with protein biomarkers.

The Precise MD test combines the latest microscopy with multispectral immunofluorescence plus highly developed mathematical features to evaluate cancer tissue biomarkers and structure and thus identify the aggressive nature of the tumor. In this study, the authors reported that the test “predicted significant disease progression with a greater degree of accuracy as compared with models that incorporated only clinical features,” which include the prostate-specific antigen (PSA) test and the Gleason score.

In addition, the Precise MD test allowed clinicians to reclassify 58 percent of the men originally deemed to be at intermediate risk to low risk and 42 percent as high risk. The reclassification as high risk is especially important because these men can then be slated for better treatment options, which may include aggressive monitoring, radiation, and/or chemotherapy.

According to the study’s lead author, Michael Donovan, MD, PhD, Research Professor of Pathology at the Icahn School of Medicine at Mount Sinai, this new test gives experts “the ability to generate more quantitative, less subjective, and enhanced cancer-grading systems,” which will allow them to “bring precision medicine to the practicing pathologist and provide treating physicians and their patients important information for guiding management decisions.”

For now, the use of AI to assist in accurately identify prostate cancer progression is in its early stages, but experts are aggressively continuing research in this area. More intelligence to follow–stay tuned.

Read more in our Prostate Cancer Health Center.


Mount Sinai School of Medicine. Pathology test uses AI to predict prostate cancer progression following surgery. 2018 Oct. 15.

Protein bars that taste like candy bars Get 12% OFF your first order plus FREE shipping