Rapid and noninvasive artificial intelligence-assisted diagnostic method for oral squamous cell carcinoma - PubMed
4 hours ago
- #Oral Cancer
- #Artificial Intelligence
- #Noninvasive Diagnostics
- The study developed an AI-assisted noninvasive diagnostic method for oral squamous cell carcinoma (OSCC) using breath and saliva analysis.
- Diagnostic framework integrated proton transfer reaction-time-of-flight mass spectrometry (PTR-TOF-MS) breath analysis and metagenomic sequencing with artificial intelligence.
- Identified OSCC-specific biomarkers such as methanethiol and Fusobacterium nucleatum from samples collected in discovery (n=222) and validation cohorts (n=83).
- AI-driven model achieved high accuracy with a ROC-AUC of 0.92 in external validation for distinguishing OSCC patients from healthy controls.
- Created an interactive online platform for real-time predictions and biomarker interpretability to support OSCC screening.