A brief clinical test battery for functional assessment in Parkinson’s disease

Abstract

Background: Parkinson disease (PD) is a progressive neurological disorder characterized by motor and non-motor impairments that significantly affect functional independence in activities of daily living (ADLs). Accurate assessment of functional disability is essential for guiding clinical decision-making and rehabilitation planning. However, comprehensive multidimensional assessments are often time-consuming and difficult to implement in routine clinical settings. Therefore, brief and clinically feasible assessment approaches may facilitate functional screening and support more efficient evaluation in neurorehabilitation practice. Objective: To identify and evaluate a brief clinical test battery capable of estimating functional disability in activities of daily living in people with Parkinson disease. Methods: An observational cross-sectional study was conducted using clinical data from 309 individuals with idiopathic Parkinson disease across Hoehn and Yahr stages 1–5. Disability in activities of daily living was assessed using the Unified Parkinson’s Disease Rating Scale Part II (UPDRS-II). Predictor variables included commonly used clinical tests assessing mobility, balance, manual dexterity and cognition. Gradient boosting regression models were used to estimate functional disability, with internal cross-validation and independent hold-out validation to assess model performance. Results: The model demonstrated good predictive performance in the development dataset (MAE 2.56; RMSE 3.32; R² 0.84) and moderate performance in the hold-out dataset (MAE 4.60; RMSE 6.04; R² 0.43). The predicted score showed high accuracy in distinguishing mild from moderate disability (AUC 0.94 in the development dataset and 0.83 in the hold-out dataset). Motor, balance, dexterity and cognitive measures contributed to the prediction of functional disability. Conclusion: Functional disability in activities of daily living in Parkinson disease can be estimated using a brief clinical test battery composed of commonly used performance-based assessments. This approach may support rapid functional screening and more efficient clinical decision-making in neurorehabilitation practice.