The objective is to design, develop, and clinically assess DiSCERN, a standardized telemedicine tool for identifying patients with Parkinson?s disease (PD) who would benefit from advanced therapies (AT) and determining when AT recipients need therapy adjustments. Once chronic PD medication usage results in motor fluctuations and dyskinesias and all non-invasive therapies have been exhausted, AT (e.g., deep brain stimulation, drug pumps) is often recommended. While experts at academic medical centers may appropriately identify AT candidates, AT is underutilized due to limited access and inequitable utilization of limited evaluative resources for a sizable subset of the PD population. Remote screening and monitoring with DiSCERN will improve patient selection, reduce disparities, and expand access for rural populations and disadvantaged communities. The system will engage and empower patients, providers, and healthcare institutions and lead to improved health, healthcare delivery, and the reduction of health disparities. This mobile health technology will include a patient friendly smartphone app, non-motor assessments, and wireless wearable sensors for continuously monitoring PD motor symptoms, complications, and quality of life (QoL). We have previously commercialized wearables and mobile apps for remote monitoring of PD motor symptoms and side effects, which will significantly de-risk the project. Still, novel development and validation efforts are required to commercialize this new technology. Innovations include: 1) integration of PD monitoring algorithms with context aware activity detection for improved PD motor assessment and QoL quantification; 2) implementation of the algorithms on a smartphone and wearable device; 3) development of a predictive model that uses motor and non-motor features to accurately identify PD patients who would be good candidates for AT; and 4) implementation of a model that alerts clinicians when an AT recipient needs a therapy adjustment. Through integration with AT systems, DiSCERN will improve the clinician experience and allow the limited availability of specialists to scale care to a diverse and growing PD population, who may not otherwise have access to AT. Phase I includes: 1) validation of context aware activity detection algorithms on PD patient data; 2) determining the extent specific activities or activity levels correlate with PD QoL; 3) using clinician feedback to identify collected data features that are useful in informing AT clinical decisions; and 4) identification of wearables to be used in the final system. Phase II includes: 1) transition of context aware activity detection and PD symptom quantification algorithms onto a smartphone and wearable chips; 2) development of a smartphone app that integrates data collection, non-motor assessment, and data-transfer to the cloud; and 3) collecting data from AT candidates in the months before and after AT is initiated to develop models that accurately identify AT candidates and when AT adjustments are needed. DiSCERN will improve therapy efficiency, expand access, and result in more patients opting for AT.

Public Health Relevance

Advanced therapies such as deep brain stimulation and drug pumps are often recommended to patients with Parkinson?s disease when medication no longer provides sufficient relief of motor symptoms without causing undesirable side-effects. However, many patients do not have access to movement disorders specialty clinics and there is currently no standardized method for identifying when a patient is ready for an advanced therapy. DiSCERN will use wearable motion sensors and a smartphone app to continuously monitor motor symptoms, complications, and quality of life throughout the day during activities of daily living to identify when a patient is ready to consider an advanced therapy or recognize and notify a clinician when a patient needs a therapy adjustment.

National Institute of Health (NIH)
National Institute on Minority Health and Health Disparities (NIMHD)
Small Business Innovation Research Grants (SBIR) - Phase II (R44)
Project #
Application #
Study Section
Special Emphasis Panel (ZRG1)
Program Officer
Hailu, Benyam
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
Great Lakes Neurotechnologies
United States
Zip Code