Longitudinal Prognosis of Parkinsons Outcomes using Causal Connectivity

TL;DR

This study develops a predictive model using functional MRI connectivity patterns to forecast Parkinson's disease progression, differentiate it from similar disorders, and identify key brain connections involved.

Contribution

The paper introduces a novel approach combining interregional dysconnectivity patterns from fMRI to predict disease progression and differentiate Parkinson's from lookalike disorders.

Findings

Achieved mean absolute errors of 1.8 and 0.6 in predicting disease progression scales.

Balanced accuracy of 0.68 in distinguishing PD from lookalikes and controls.

Identified key brain connections related to prognosis and diagnosis.

Abstract

Parkinsons disease (PD) is a movement disorder and the second most common neurodengerative disease but despite its relative abundance, there are no clinically accepted neuroimaging biomarkers to make prognostic predictions or differentiate between the similar atypical neurodegenerative diseases Multiple System Atrophy and Progressive Supranuclear Palsy. Abnormal connectivity in circuits including the motor circuit and basal ganglia have been previously shown as early markers of neurodegeneration. Therefore, we postulate the combination patterns of interregional dysconnectivity across the brain can be used to form a patient-specific predictive model of disease state and progression in PD. These models, which employ connectivity calculated from noninvasively measured functional MRI, differentially predict between PD and the atypical lookalikes, predict progression on a disease-specific scale, and predict cognitive decline. Further, we identify the connections most informative for progression and diagnosis. When predicting the one-year progression in the Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) and Montreal Cognitive assessment (MoCA), mean absolute errors of 1.8 and 0.6 basis points in the prediction are achieved respectively. A balanced accuracy of 0.68 is attained when distinguishing idiopathic PD versus the lookalikes and healthy controls. We additionally find network components strongly associated with the prognostic and diagnostic tasks, particularly incorporating connections within deep nuclei, motor regions, and the Thalamus. These predictions, using an MRI modality readily available in most clinical settings, demonstrate the strong potential of fMRI connectivity as a prognostic biomarker in Parkinsons disease.