A new study validates a machine-learning platform that detects prostate cancer through biochemical patterns in urine samples.

A peer-reviewed clinical study published in Diagnostics has demonstrated the clinical validation of a urine-based liquid biopsy platform for the detection of prostate cancer. The platform uses machine learning to identify biomolecular signature patterns in urine, achieving 97.8% sensitivity across all Gleason grades.

The study, based on the GH-215 clinical program, evaluated 283 participants across 26 US urology practices. Results showed 97.3% specificity for high-grade cancers and an area under the curve (AUC) of 0.91. The findings suggest that the approach can detect disease through pattern-based analysis of metabolites and other biochemical signals rather than relying on single biomarkers.

“This marks an important external validation of our platform and reinforces the clinical and scientific foundation underlying our diagnostic pipeline,” says Holly Magliochetti, PanGIA Biotech ceo and co-founder, in a release. “It reflects both the rigor of the work and the potential for broader application across multiple cancer types.”

The research highlights how a non-invasive urine-based liquid biopsy could reduce the need for unnecessary surgical biopsies while supporting earlier clinical decision-making. The system integrates sample collection with machine-learning-driven analysis to capture signals across the full spectrum of the disease.

“This study reflects a different way of approaching cancer detection,” says Obdulio Piloto, PhD, chief scientific officer and co-founder of PanGIA Biotech, in a release. “Rather than targeting a single biomarker, this urine-based liquid biopsy uses machine learning to interpret complex biochemical patterns. That allows us to capture signals that may be missed by more reductionist approaches and supports detection across the full spectrum of disease.”

ID 244810910 © Alexander Limbach | Dreamstime.com

Related Reading: