2025 · Scientific reports · open access
Saliva-derived transcriptomic signature for gastric cancer detection using machine learning and leveraging publicly available datasets
Lopes et al.
The finding, in our words
A saliva-derived transcriptomic signature using support vector machine learning detected gastric cancer with an AUC of 0.87, sensitivity of 79% and specificity of 70%. Tissue-based gene expression models performed poorly when applied to saliva, indicating that saliva-specific biomarker panels are needed for effective non-invasive gastric cancer screening.
A paraphrase to the Library’s standard, never the abstract. The source is one link away and is always the authority.