Miniaturized and wearable sensor-based measurements enable the assessment of Parkinson’s disease (PD) motor-related features like never before and hold great promise as non-invasive biomarkers for early and accurate diagnosis, and monitoring the progression of PD. High-fidelity human movement reconstruction and simulation can already be conducted in a clinical setting with increasingly precise and affordable motion technology enabling access to high-quality labeled data on patients’ subcomponents of movement (kinematics and kinetics). At the same time, body-worn sensors now allow us to extend some quantitative movement-related measurements to patients’ daily living activities. This era of patient movement “cognification” is bringing us previously inaccessible variables that encode patients’ movement, and that, together with measures from clinical examinations, poses new challenges in data analysis. We present herein examples of the application of an unsupervised methodology to classify movement behavior in healthy individuals and patients with PD where no specific knowledge on the type of behaviors recorded is needed. We are most certainly leaving the early stage of the exponential curve that describes the current technological evolution and soon will be entering its steep ascent. But there is already a benefit to be derived from current motion technology and sophisticated data science methods to objectively measure parkinsonian impairments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.