Modeling the heterogeneity of cognitive dysfunction in Parkinson’s disease using partially ordered set models

Abstract Traditional binary classifications of Parkinson’s disease (PD) cognitive dysfunction fail to capture its inherent heterogeneity. This study introduces the Partially Ordered Set (POSET) model, a Bayesian framework, to analyze cognitive heterogeneity using Parkinson’s Precision Medicine Initiative (PPMI) data. Five cognitive domains: Attention, Visuospatial Judgement, Executive Functioning, Working Memory, and Episodic Memory, were mapped onto nine neuropsychological measures to calculate Cognitive Performance Scores (CPS). Of 264 participants without baseline cognitive dysfunction, 21.2% developed dysfunction by Year 3. After demographic adjustment and Bonferroni correction, cognitive dysfunction at Year 3 was inversely associated with median CPS values for: Attention (across all visits); Executive Functioning and Working Memory (Year 1 onward); and Visuospatial Judgement (baseline only). In multivariable logistic regression, both baseline Attention and Visuospatial Judgement CPS were significant predictors of future impairment without adjustment for baseline disease duration, however, only Visuospatial Judgement CPS remained a significant predictor after the adjustment. POSET modeling provides a sophisticated approach to characterizing PD cognitive decline, offering greater granularity than conventional schemes. Further large-cohort studies are needed to confirm these findings.