Abstract 7619: PanGIA Analysis System, a novel machine learning platform for non-invasive diagnosis of oral cancer through an oral sample

Le résumé fourni par la source

Abstract The PanGIA Analysis System (PAS) is an advanced diagnostic platform designed to characterize complex biological systems through machine learning-assisted biochemical profiling. Powered by trained algorithms and proprietary hydrogel microarrays known as NuTec Slides, PAS enables unbiased capture and analysis of biomolecular signatures from diverse biofluids. Oral samples represent a particularly valuable yet underexplored matrix for noninvasive disease assessment, offering insight into both local and systemic health conditions. In this study, a commercialization-ready PAS prototype was evaluated for its capacity to differentiate between cancer-spiked and unspiked oral samples. Oral fluid from healthy volunteers was pooled with TruSample Oral Buffer Cell and spiked with literature-validated analyte panels representative of oral cancer. Following incubation of NuTec Slides with both spiked and unspiked control samples, heat-based signal development and high-resolution scanning were performed. Extracted image feature data were analyzed by principal component analysis (PCA). This proof-of-concept study indicates that PAS can distinguish between control and spiked human oral samples containing literature supported oral cancer analytes. Conclusion: These findings establish proof-of-concept for the use of PAS in noninvasive cancer detection through oral fluid profiling. Further clinical validation is warranted to expand its diagnostic applications across additional cancer types and to explore its potential in longitudinal monitoring, risk stratification, and personalized medicine. Citation Format: Francis Lim, Abhignyan Nagesetti, Nick Gonzalez, Miguel Javiel, Pablo Hernandez, Kyle Ambert, Robert Cardwell, Obdulio Piloto. PanGIA Analysis System, a novel machine learning platform for non-invasive diagnosis of oral cancer through an oral sample [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 7619.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.