Related Papers
Manuscripts underpinning our multimodal biomarker program. Each card summarizes a key finding and links to the full paper.
Manuscripts
Pathway Anchored Multimodal Clustering Reveals Circuit Level Signatures in Parkinson's Disease
Presents a pathway-anchored co-clustering framework (SRVCC) integrating structural MRI, DTI, and DaT-SPECT within six predefined neuroanatomical circuits. Multimodal Pathway Integrity Scores reveal circuit-level imaging heterogeneity linked to motor severity and cognitive function across five imaging-driven patient clusters in the PPMI cohort.
Integrated Genetic, Molecular, and Wearable Sensor Biomarkers Enable Bayesian Machine Learning-Driven Precision Stratification in Parkinson's Disease
Integrates LRRK2 G2019S genetic status, urinary phospho-LRRK2, CSF alpha-synuclein seed amplification, and IMU-derived gait metrics into a Bayesian clustering framework. Identifies four motor phenotypes across 4,775 PPMI patients and 627 LRRK2 Consortium participants, with a risk prediction model enabling personalized prognostic counseling.