NeuralCipher Research overview
The text below is the source article’s original abstract under a verified reuse license. cc by
Abstract Parkinson’s disease (PD) is characterized by marked clinical heterogeneity. We applied Subtype and Stage Inference (SuStaIn), an unsupervised machine-learning algorithm, identifies distinct subtypes and their hypothesized progression from cross-sectional imaging, to identify MRI-based subtypes in PD. A total of 183 patients with PD and 107 healthy controls underwent T1-weighted MRI and clinical assessments covering motor, cognitive, psychiatric, sleep, autonomic, and olfactory functions, quality of life, and DAT-SPECT. SuStaIn identified three distinct PD subtypes with unique atrophy trajectories and clinical profiles. Subtype 0 showed early brainstem and frontal atrophy with executive dysfunction. Subtype 1 began with subcortical and temporal atrophy and was associated with hallucinations and sleep, autonomic, and DAT-SPECT dysfunction. Subtype 2 exhibited early parietal-occipital atrophy with later brainstem involvement and progressive cognitive and psychiatric symptoms. These findings highlight the utility of MRI-based subtyping to characterize clinical variability and may inform personalized disease management in PD.
Scientific assessment
Research question
Assess the question within the original study’s scope.
Methods & sample
Check the source article for study design and sample details.
Key findings
An editorially approved findings summary is not yet published for this record.
Limitations
Generalizability, bias and clinical meaning require separate assessment.
Methods, samples and clinical conclusions are not inferred from bibliographic metadata.