SUPER-PD (Sensor Use to Monitor Progression and Evaluate Symptoms Remotely in Parkinson’s Disease) was designed to test and compare the ability of four novel technologies to monitor symptoms and progression of Parkinson’s disease. All participants use a video analytics tool (PARK Video Analytics/Research Project 4.2), and have the opportunity to choose which of the three other technologies to assess. Approximately 200 individuals will be enrolled in video analytics + at least one optional technology. The Super Users cohort will be comprised of 50 individuals (35 with PD, 15 without) who use at least 3 of the 4 technologies.
The team has successfully conducted 62 baseline visits
with a varied combination of technologies.
The study team has transitioned 6-month visits to a virtual format due to COVID-19 restrictions. This has presented several challenges, especially related to the MC10 wearable sensors. Dr. Gaurav Sharma, the Project Lead for the wearable sensors study (Project 4.1), uses videotapes in his algorithm. The study team conducted two virtual visits involving the sensors to assess the feasibility and evaluate video quality. It was determined that the video quality needs improvement and guidelines were developed. Assessments with smartphones have continued without interruption during the pandemic and have allowed researchers to collect data pre-and post COVID for analysis. Enrollment in the PARK Video Analytics study (Project 4.2)has continued and increased due to the web-based design.Continuous passive measurement in the home with the Emerald radio wave device (Project 4.3), pre-and post-public health emergency, has shown substantial differences in behavior that we are currently analyzing. The team is planning to submit a protocol amendment to allow flexibility for research participation to be conducted remotely after COVID-19 restrictions are lifted.
Remote health assessments that gather real-world data (RWD) outside clinic settings require a clear understanding of appropriate methods for data collection, quality assessment, analysis and interpretation. Here we examine the performance and limitations of smartphones in collecting RWD in the remote mPower observational study of Parkinson’s disease (PD). Within the first 6 months of study commencement, 960 participants had enrolled and performed at least five self-administered active PD symptom assessments (speeded tapping, gait/balance, phonation or memory). Task performance, especially speeded tapping, was predictive of self-reported PD status and correlated with in-clinic evaluation of disease severity when compared with motor Movement Disorder Society-Unified Parkinson’s Disease Rating Scale (MDS-UPDRS). Although remote assessment requires careful consideration for accurate interpretation of RWD, our results support the use of smartphones and wearables in objective and personalized disease assessments.
The mPower data is collected to develop a smartphone-based remote diagnosis system for PD's patients. Subjects are required to conduct well-designed activities that could reveal the PD's symptoms. Here we conduct adversarial debiasing for the finger tapping task, where patients will tap their phones alternatively with two fingers. The mPower data has a bias on age, and detailed statistics are provided in the supplemental material. We develop an adversarial debiasing model to eliminate the age bias. According to our experiments, our model improves over the results of other methods, suggesting that the learned representation of our method is more robust to the age bias.