Therefore, motor-symptom data (e.g., ambulatory activity data) or non-motor symptoms data (e.g., voice data) can be used to evaluate the effect of medication on the PD symptoms, based on the chaotic nature of PD. As mentioned, pathological dysfunction, especially PD, alters the chaotic property of biological systems. In chaotic states, each time we record the data, different quantities are achieved. It is worth noting that, at any minute, error or noise in experimental conditions leads to a great change in chaotic system results, because chaotic systems are very sensitive to initial and environmental conditions. Hence, some global features of data related to deterministic chaos are needed to evaluate biological behavior.6 Methods based on non-linear dynamics, including general dimension (Hausdorff dimension, information dimension, correlation dimension, etc.), entropy (Kolmogrov entropy, second-order entropy, etc.), and Lyapunov exponents, enable us to quantitatively describe chaotic behavior.3,4 Non-linear features extracted from signals coming from PD patients can be classified by proper classifiers—such as the ones we used in our previous works7—to evaluate the effect of medication on the PD symptoms. Clinical observations are needed to gather labeled data for PD symptoms, especially PD non-motor symptoms (e.g., voice data) during treatment.