AI and the World's Hard Problems · Medicine & drug discovery · arXiv · 2026-10-21
Cross-disorder Learning of Imaging-derived Joint Mophometric Markers in Alzheimer's and Parkinson's Diseases
Alzheimer's disease and Parkinson's disease share commonalities in symptoms and pathophysiology, but the extent and nature of their overlap remain underexplored. The study proposes an explicit, interpretable, and spatially adaptive transfer learning framework and applies it to the ADNI and PPMI neuroimaging datasets to identify morphometric biomarkers linked to both diseases. The cross-disorder classifier revealed neuro-anatomical alteration patterns consistent with previous findings, and the classifier trained with a shared prior achieved statistically superior diagnostic performance over the respective individual models.