A simplified MyProstateScore2.0 for high-grade prostate cancer

Area of Science:

• Urology
• Biomarker Discovery
• Genomics

Background:

• Prostate-specific antigen (PSA) screening for prostate cancer (PCa) has limited diagnostic accuracy.
• Innovative solutions like the 18-gene MyProstateScore2.0 (MPS2) urine test improve PCa detection.
• There is a need for more accessible, non-invasive PCa diagnostic tools.

Purpose of the Study:

• To develop a simplified 7-gene urine test (sMPS2) for high-grade PCa.
• To achieve diagnostic accuracy comparable to the 18-gene MPS2 test.
• To enhance accessibility for routine clinical care through a reduced gene set.

Main Methods:

• Utilized the Predictability, Computability, and Stability (PCS) framework for data science.
• Employed a stability-driven PCS ranking procedure for gene selection.
• Validated the sMPS2 model on a blinded external cohort.

Main Results:

• The 7-gene sMPS2 achieved an AUROC of 0.784 for predicting high-grade PCa.
• Performance was only 2.3% lower than the 18-gene MPS2.
• The gene selection process ensured robustness and predictive power.

Conclusions:

• The 7-gene sMPS2 demonstrates high accuracy for non-invasive PCa screening.
• This simplified test offers a viable alternative for broader clinical application.
• sMPS2 has the potential to significantly expand the reach of PCa screening.