Interpretable and granular video-based quantification of motor characteristics from the finger-tapping test in Parkinson’s disease

Accurately quantifying motor characteristics in Parkinson's disease is crucial for monitoring disease progression and optimizing treatment strategies. The finger-tapping test is a standard motor assessment. Clinicians visually evaluate a patient's tapping performance and assign an overall severity score based on tapping amplitude, speed, and irregularity. Simultaneous video recording during the standard test enables a more objective, continuous quantification of detailed motor characteristics, thereby reducing the subjectivity and inter-rater variability inherent in clinical evaluations. This paper introduces a computer vision-based method for quantifying granular PD motor characteristics from video recordings. Four sets of clinically relevant features are proposed to characterize hypokinesia, bradykinesia, sequence effect, and hesitation-halts. We evaluate our approach on video recordings and clinical evaluations of 446 people with PD from the Personalized Parkinson Project. Using principal component analysis with varimax rotation, we show that the extracted features largely align with the four clinically defined motor deficits, while additionally revealing finer-grained substructures within the sequence effect and hesitation-halts domains. In addition, we have used these features to train machine learning classifiers to estimate the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS) finger-tapping severity score. Compared to state-of-the-art approaches, our method achieves a higher accuracy in MDS-UPDRS score prediction, while still providing an interpretable quantification of individual finger-tapping motor characteristics. In addition, we present the first large-scale dataset of finger-tapping, comprising 4073 video recordings. In summary, the proposed framework provides a practical solution for the objective assessment of PD motor characteristics, that can potentially be applied in both clinical and remote settings. Future work is needed to assess its responsiveness to symptomatic treatment and disease progression.