Canine cognitive dysfunction syndrome (CCDS) affects up to half of senior dogs, yet its diagnosis often relies on subjective questionnaires such as the Canine Cognitive Dysfunction Rating (CCDR) scale. In a groundbreaking study, Kim and colleagues (2024) developed an objective diagnostic approach by analyzing blood-based biomarkers with machine learning methods.
The researchers measured levels of retinol-binding protein 4 (RBP4), C-X-C motif chemokine ligand 10 (CXCL10), and NADPH oxidase 4 (NOX4) in dogs with CCDR scores above 25, indicating cognitive decline. Results showed that lower biomarker levels were strongly correlated with higher CCDR scores, confirming their relevance to CCDS progression.
To improve predictive power, the team applied machine learning algorithms. The combination of RBP4 and NOX4, analyzed with a support vector machine model, yielded the highest accuracy in distinguishing CCDS from normal aging. This approach highlights the potential of artificial intelligence in veterinary neurology and strengthens the case for biomarker-based diagnostics.
These findings suggest that blood-based biomarkers could enable earlier detection and intervention, not only improving the welfare of aging dogs but also offering valuable insights for human neurodegenerative diseases such as Alzheimer’s. The integration of machine learning provides an innovative step toward precision medicine in both veterinary and human healthcare.
Source: Kim, C.-Y., Kim, J., Yoon, S., Yi, I. J., Lee, H., Seo, S., Kim, D. W., Ko, S., Kim, S.-A., Kwon, C., & Yi, S. (2024). Advancing the early detection of canine cognitive dysfunction syndrome with machine learning-enhanced blood-based biomarkers. Frontiers in Veterinary Science, 11, published August 7, 2024.
