 Our study demonstrated the potential of using features extracted from reaching tasks involving the upper limbs to differentiate between healthy controls and individuals suffering from Parkinson's disease. We found that the most important features for discriminating between the two groups were maximum acceleration, smoothness, duration, maximum jerk, and kurtosis. These features can be used to develop a model that accurately classifies Parkinson's patients from healthy controls. This article was authored by Giuseppe Cesarelli, Leandro Donisai, Francesco Amato, and others.