Scientific Challenge: Rapid, non-invasive biomarkers are needed to distinguish different radiation exposure scenarios and assess oxidative stress-related injury.
Study Type: Urinary Metabolomics | Biomarker Discovery | Machine Learning
Our Contribution: Nelson Scientific Labs applied targeted and untargeted metabolomics together with machine learning to characterize urinary metabolic responses following multiple radiation exposure models.
Key Findings: Radiation exposure produced distinct urinary metabolic signatures associated with oxidative stress, and machine learning models accurately differentiated radiation exposure types based on metabolite profiles.
Research Impact: This work demonstrates the potential of metabolomics combined with artificial intelligence to improve radiation biodosimetry and support rapid assessment following radiation exposure.
Publication: https://doi.org/10.3390/antiox14010024