Progressive micrographia in Parkinson's disease is associated with multidimensional cognitive and motor features.

Abstract

Progressive micrographia, characterized by a gradual reduction in handwriting size, is a common yet incompletely understood feature of Parkinson's disease (PD). It has been associated with both motor and cognitive impairment; however, the clinical characteristics associated with progressive micrographia and the relative contributions of motor and cognitive factors remain unclear. This study aimed to investigate the motor, cognitive, and disease-related clinical features associated with progressive micrographia in PD. Thirty-nine individuals with PD underwent handwriting assessment, the Mini-Mental State Examination, the Movement Disorder Society-Unified Parkinson's Disease Rating Scale Part III, and evaluation of disease duration and levodopa equivalent daily dose. Participants were classified as having progressive micrographia (n = 14) or not having progressive micrographia (n = 25) based on normative handwriting data from healthy older adults. Four machine learning models (logistic regression, elastic net logistic regression, linear support vector machine [SVM], and radial basis function SVM) were evaluated using nested leave-one-out cross-validation. The linear SVM showed the highest numerical area under the receiver operating characteristic curve (AUC; 0.877, 95% CI 0.749-0.977; accuracy = 82.1%). Exploratory feature contribution analyses indicated that classification involved a combination of cognitive and motor features. These findings suggest that progressive micrographia is associated with clinical characteristics extending beyond handwriting impairment alone; however, the identified associations are exploratory and require validation in larger, independent cohorts.