-
Salivary fingerprinting and neural network identified high-risk periodontitis in diabetes
Lightweight neural networks analyze salivary metabolics via mass spectrometry to screen for periodontitis and diabetes, achieving 91.9% accuracy with minimal computational resources for clinical.
-
Human and bacterial genetics shape oral microbiome variation
Study of 12,519 individuals reveals how human genetic variants control oral microbiome composition and link to tooth decay risk through salivary enzyme abundance.