Artificial Intelligence in Medicine: AI Helps Pinpoint Who Needs Imaging Most Where MRI is Scarce

“Nothing makes me angrier than calling my cable service and having to wade through voice menus to finally talk to a REAL PERSON after 10 minutes of following the stupid steps!” We’ve all been there, right? It used to be so simple to get the help you need from an empathic customer service representative.

Well, as irritating as it is to encounter delays and a positronic voice that could care less, here’s something to put it in perspective. What about a man whose urologist wants him to go for an MRI because his annual PSA test was concerningly high? This poor guy, already in a tizzy because he may have prostate cancer (PCa), understandably wants to get scheduled ASAP. In some locations, however, he may find a scheduling obstacle course similar to the voice menu. Only this time, the stakes are higher than having a poor TV connection.

Does he have PCa, or doesn’t he? A biopsy is the only way to gain a definitive diagnosis, but given the PSA test’s lack of specificity, any number of things can bump up the PSA number. Thus, it’s important to find out what’s causing the rise before putting a man through a needle biopsy. The latest diagnosis guidelines call for a multiparametric MRI (mpMRI) before biopsy. This is a perfect next step, because MRI findings can rule a biopsy in or out. But here’s the problem: not every potential PCa patient has equal access to MRI, causing a delay in pre-biopsy findings. In other words, for these men it’s like waiting through a phone voice menu waiting to talk to a real person. Frustrating, even infuriating!

Because pre-biopsy MRI has demonstrated its value, “… the demand has increased over the years, and this has resulted in prolonged wait times in some health systems. Some patients are waiting several months to get a prostate MRI, and this can delay diagnosis,” states a June 12, 2025 report in Urology Times. A long gap in time from initial suspicion to biopsy may result in increased tumor size and aggression level during the wait, reducing chances of treatment success. No wonder anxiety grows and patience wears thin. Unlike a robotic voice, PCa can become life-threatening.

How big is the inaccessibility problem? An in-depth analysis of trends in pre-biopsy MRI found inequities in access, especially in certain regions and rural areas. Here are the numbers:

Pre-biopsy MRI utilization increased significantly from 0.5% in 2007 to 35.5% in 2022, with faster adoption in urban areas (36.1% in 2022) versus rural areas (28.3% in 2022). Geographic disparities were notable, with higher utilization in California, New York, and Minnesota, and lower rates in the Southeast and Mountain West.^[i]

AI to the rescue

In order to address this imbalance, a team of clinical investigators turned to Artificial Intelligence (AI). A team of investigators harvested data from patient records to develop a machine learning tool to help predict which patients needed a timely MRI vs. those who could safely delay imaging (or possibly even avoid it). As described in the Urology Times report mentioned above, “Using data such as prostate-specific antigen (PSA), prostate volume, MRI history, and body mass index, the tool, called ProMT-ML, provides insights on the risk of a patient having an abnormal MRI, defined as a PI-RADS score of 3 or higher.”

Essentially, ProMT-ML would offer an efficient, practical way based on existing clinical factors to predict those who stand to gain the most by getting an MRI as quickly as possible before biopsy. The tool factors in things like a patient’s PSA, age, prostate volume, body mass index, etc. and can be done on a computer in the doctor’s office. If the program predicts a high risk level, and mpMRI cannot be quickly scheduled, a biopsy could be done without waiting for imaging. On the other hand, if the risk level is low, the patient can gain the time necessary to make future MRI arrangements and get a date on the calendar. In addition, equitable access to MRI based on patient risk level helps to thin out long wait times, fostering judicious use of MRI resources in areas where the technology is scarce.

Although this tool requires more testing on other patient databases, it’s a promising alternative to fretting and worrying about missing a treatment window. There’s no substitute for peace of mind and trusting that one’s needs have been identified, and a reasonable timeline has been established.

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] Soerensen SJC, Li S, Langston ME, Fan RE, Rusu M, Sonn GA. Trends in pre-biopsy MRI usage for prostate cancer detection, 2007-2022. Prostate Cancer Prostatic Dis. 2025 Jun;28(2):519-522.