Parkinson’s Disease (PD) is a progressive neurodegenerative disorder marked by motor symptoms such as bradykinesia, rigidity, and tremor. Traditional clinical assessments often lack the sensitivity to detect subtle changes in motor symptoms, especially in the early stages of the disease. Recent advancements in machine learning (ML) and video analysis offer a promising alternative to enhance PD evaluation by providing more accurate and detailed quantification of movement kinematics. This presentation reviews our recent work on applying ML algorithms to video recordings of motor tasks commonly used in clinical PD assessment. By analyzing videos of these tasks, we conduct virtual motor evaluations that can distinguish PD patients from healthy controls, quantify disease severity, and identify early motor deficits in individuals with idiopathic REM sleep behavior disorder (iRBD)—a population at high risk of developing PD. Our research applies ML to automatically extract kinematic features from videos, enabling the detection of movement patterns associated with early-stage PD and other neurological disorders. This approach presents a scalable, objective method that could complement traditional clinical assessments. Additionally, we introduce VisionMD, an open-source tool developed to automate and standardize video-based motor assessments for clinical and research use. Our findings show that ML-enhanced video analysis can outperform traditional clinical evaluations in detecting early PD symptoms, potentially enabling earlier interventions and supporting more personalized treatment strategies.

Dr. Diego L. Guarín has been an Assistant Professor in the Applied Physiology and Kinesiology Department at the University of Florida since August 2022. Before joining UF, Dr. Guarín was an assistant professor at the Florida Institute of Technology (2020-2022). Dr. Guarín completed his master's and Doctoral degrees at McGill University and was a postdoctoral fellow at Harvard Medical school and the Toronto Rehabilitation Institute. His research focuses on understanding how movement is affected by neurodegenerative diseases and developing novel techniques to measure movement, assess disease severity, and evaluate the effectiveness of therapies. Dr. Guarín's research lives in the intersection between neuroscience, machine learning, and signal processing. His overall research goal is to improve current clinical practices and facilitate remote, early assessment of neurological conditions that affect movement.  

Dr. Guarín has published more than 20 papers in international journals, including JAMA, Parkinsonism & Related Disorders, Journal of Speech, Language, and Hearing Research, Plastic and Reconstructive Surgery, IEEE Journal of Biomedical and Health Informatics, and IEEE Trans. on Neural Systems and Rehabilitation Engineering. His research has been supported by The National Institutes of Health (NIH), Michael J. Fox Foundation (MJFF), Vector Institute for Artificial Intelligence, Natural Sciences and Engineering Research Council of Canada (NSERC), and the Colombian Department of Science, Technology, and Innovation (COLCIENCIAS).