Peer-reviewed clinical research published in diagnosis demonstrated clinical validation of a urine-based liquid biopsy platform for the detection of prostate cancer. The platform uses machine learning to identify signature patterns of biomolecules in urine, achieving a sensitivity of 97.8% across all Gleason grades.
The study was based on the GH-215 clinical program and evaluated 283 participants across 26 urological institutions in the United States. Results showed a specificity for high-grade cancer of 97.3% and an area under the curve (AUC) of 0.91. This finding suggests that this approach can detect disease through pattern-based analysis of metabolites and other biochemical signals, rather than relying on a single biomarker.
“This represents important external validation of our platform and strengthens the underlying clinical and scientific foundations of our diagnostic pipeline,” PanGIA Biotech CEO and co-founder Holly Magliochetti said in the release. “This reflects both the rigor of the study and its potential for broader application across multiple cancer types.”
This study highlights how non-invasive urine-based liquid biopsy can reduce the need for unnecessary surgical biopsies and provide support at the same time. Earlier clinical decision making. The system integrates sample collection and machine learning analysis to capture signals across the spectrum of disease.
“This study reflects a different approach to cancer detection,” Obdulio Piloto, Ph.D., chief scientific officer and co-founder of PanGIA Biotech, said in the release. “Rather than targeting single biomarkers, this urine-based liquid biopsy uses machine learning to interpret complex biochemical patterns. This allows us to capture signals that may be missed by more reductionist approaches, supporting detection across the entire spectrum of disease.”
ID 244810910 © Alexander Limbach | Dreamstime.com
Related books:
