Early Detection and Classification of Parkinsonism: Leveraging the Lognormal Model to Aid Clinical Assessment

Abstract

Individuals living with Parkinsonism experience motor and non-motor symptoms that impair their daily functioning and quality of life. Early and precise diagnosis is crucial for optimizing care. This study investigates the use of movement attributes to differentiate asymptomatic elderly individuals from those living with Parkinson’s disease and explores the potential characteristic differences between two forms of Parkinsonism: idiopathic and atypical. By analyzing rapid scripted strokes, the study demonstrates that lognormal movement attributes reveal differences in timing parameters between asymptomatic elderly and those with parkinsonism. Additionally, it identifies a potential discriminating factor between idiopathic and atypical parkinsonism. These findings pave the way to further investigation into the capabilities of this technic to support clinical diagnosis.