Park is an online framework allowing individuals to perform neurological tests whenever and wherever they want.

There are about 900,000 people with Parkinson’s disease (PD) in the United States, with an economic burden of $53B per year. Even though there are benefits of early treatment, unfortunately, over 40% of individuals with PD over 65 years old do not see a neurologist. These individuals often struggle to get to a physician’s office for diagnosis and subsequent monitoring. Telemedicine is the only option to give easy access to health screening and symptom monitoring to individuals, including those from rural areas and disadvantaged backgrounds. 

To address this problem, we have developed PARK, Parkinson’s Analysis with Remote Kinetic-tasks. PARK instructs and guides users’ UPDRS tasks, including motor/audio/facial tasks, and records their performance via a webcam. 

One can access our data collection framework at parktest.net.

Through a series of studies, we have showcased AI’s capability to screen for Parkinson’s disease and remotely assess the severity of tremors, often outperforming primary care physicians and achieving accuracy comparable to, or slightly below, that of expert neurologists.

Publications

Md. S. Islam, T. Adnan, J. Freyberg, S. Lee, A. Abdelkader, M. Pawlik, C. Schwartz, K. Jaffe, R. B. Schneider, E Dorsey, E. Hoque, Accessible, At-Home Detection of Parkinson’s Disease via Multi-task Video Analysis, to appear in AAAI 2025

W. Rahman, A. Abdelkaer, S. Lee, P. Yang, M. S. Islam, T. Adnan, M. Hasan, E. Wagner, S. Park, E. R. Dorsey, C. Schwartz, K. Jaffee, E. Hoque, A User-Centered Framework to Empower People with Parkinson’s Disease, Proceedings of ACM on Interactive, Mobile, Warble, and Ubiquitous Computing (IMWUT), Volume 7, Issue 4, January 2024

M. S. Islam, W. Rahman, A. Abdelkader, P. T. Yang, S. Lee, J. L. Adams, R. B. Schneider, E. R. Dorsey, E. Hoque, Using AI to Measure Parkinson’s Disease Severity at Home, npj Digital Medicine, 2023

K. Haut, A. Blumenthal, S. Atterbury, X. Zhou, W. Rahman, E. Natali, M. R. Ali, E. Hoque, Assistive Video Filters for People with Parkinson’s Disease to Remove Tremors and Adjust Voice, Affective Computing and Intelligent Interaction (ACII), October 2022 [best paper nomination]

P. T. Yang et al. Analyzing gait videos to identify and evaluate spinocerebellar ataxia types 1 and 3. In: Movement Disorders Society; September 15-18, 2022; Madrid, Spain.

E. A Hartman et al., A Week in the Life with Parkinson’s Disease: A Holistic Overview from Four Digital Technologies, In: Movement Disorder Society; September 15-18, 2022; Madrid, Spain

W. Rahman et al., Detecting Parkinson’s Disease from an Online Speech Task, Journal of Medical Internet Research (JMIR), Vol 23, No 10, October 2021

K. Sibley, C. Girges, E. Hoque, T. Foltynie, Video-Based Analyses of Parkinson’s Disease Severity: A Brief ReviewJournal of Parkinson’s Disease, March 2021.

M. R. Ali, T. K. Sen, Q. Li, R. Langevin, T. Myers, S. Sharma, E. R. Dorsey, E. Hoque, Analyzing Head Pose in Remotely-Collected Videos of People with Parkinson’s Disease, ACM Transactions on Computing for Healthcare, Vol 2, Issue 4, October 2021

M. R. Ali, J. Hernandez, E. R. Dorsey, M. E. Hoque, D. McDuff, Spatio-Temporal Attention and Magnification for Classification of Parkinson’s Disease from Videos Collected via the InternetIEEE International Conference on Automated Face and Gesture Recognition (FG), Argentina, May 2020

E. R. Dorsey et al., Deep Phenotyping of Parkinson’s DiseaseJournal of Parkinson’s Disease, May 2020

R. Langevin, M. R. Ali, T. Sen, C. Snyder, T. Myers, E. R. Dorsey, M. E. Hoque, The PARK Framework for Automated Analysis of Parkinson’s Disease CharacteristicsProceedings of ACM on Interactive, Mobile, Warble, and Ubiquitous Computing (IMWUT), London, September 2019

 

Funding