Unfold AI outperforms conventional methods in prostate cancer risk prediction

A recently published study in BJUI Compass confirms the groundbreaking potential of Unfold AI™, an FDA-cleared artificial intelligence (AI) algorithm developed by Avenda Health, a leader in personalized prostate cancer care. In conjunction with UCLA, the study used Unfold AI’s technology to map 3D cancer probability and estimate extracapsular extension (ECE) risk, comparing it to conventional methodologies such as MRI, PSMA PET/CT imaging and nomograms. The results revealed that Unfold AI accurately predicted ECE risk and outperformed conventional methodologies, helping surgeons more accurately predict extraprostatic disease extensions.

ECE, the spread of cancer beyond the prostate gland into the surrounding soft tissue, can lead to a higher risk of positive surgical margins, which in turn can increase the likelihood of recurrence or metastatic disease. The presence of ECE is critical in determining treatment options and assessing the risk to quality of life among prostate cancer patients, making its accurate identification crucial for reducing cancer recurrence.

The study retrospectively analyzed data from 147 patients who received MRI-targeted biopsy followed by radical prostatectomy, finding Unfold AI had significantly higher predictors for patient-level ECE prediction than all other standard of care methods evaluated. Unfold AI also demonstrated a substantial 40%-60% reduction in false negatives compared to MRI.

By providing a more precise assessment of extracapsular extension, our AI tool empowers physicians to make better-informed decisions, ultimately improving patient outcomes and setting a new benchmark for diagnostic accuracy. This advancement not only enhances the precision of cancer detection but also represents a milestone in our commitment to personalized medicine and better patient care.”

Shyam Natarajan, CEO, Avenda

This study builds on prior research published in The Journal of Urology, which demonstrated Unfold AI’s ability to enhance physicians’ accuracy in identifying the extent of prostate cancer with 84% accuracy. In addition to these milestones, Unfold AI has been included in the American Medical Association’s 2024 Current Procedural Terminology code set as a Category III code. This new classification allows Unfold AI to be billable by insurance, improving access to personalized prostate cancer care.