The objective is to design, build, and clinically assess ParkinPal, an interactive patient-centered system for individuals with Parkinson?s disease (PD). The app-based platform will enable data-driven decisions to optimize treatment using a personalized interface with intelligent algorithms based on quantitative symptom assessment. The system will include a wrist-worn wearable device that communicates wirelessly with an engaging smartphone software application that provides actionable feedback for treatment optimization. When optimizing PD therapy, the patient is in the middle of a complex system where drug types, doses, and times interact to create fluctuating patterns of motor symptoms and side effects. Tools for patients to monitor (let alone act on) these temporal patterns are severely lacking. Clinical rating scales provide a limited snapshot of symptom severity in the clinic. Likewise, handwritten diaries can be burdensome, leading to inaccurate entries and poor compliance. These limitations can make decisions about medication adjustments challenging and require a costly trial-and-error process. Wearable technology has shown great promise for providing an objective evidence base for clinical decision making. We have previously commercialized Kinesia, a clinically validated system to quantify motor symptoms that is being used to measure outcomes in clinical trials and help clinicians with patient care. Kinesia, however, generates reports that require interpretation by a neurologist and does not provide patient-facing feedback ? something patients greatly want. While some existing smartphone apps provide tracking of symptoms, none have been clinically validated and it is likely that these simple trackers will see a big drop off in usage as there is no incentive to stay engaged. ParkinPal will address this major limitation by providing patients with visual feedback and actionable suggestions to discuss with their doctor to optimize treatment. The primary innovations of ParkinPal include an interactive smartphone app that: 1) uses data mining algorithms to analyze temporal patterns and identify clinical indicators of sub-optimal treatment and 2) provides actionable suggestions for changes that patients can discuss with their doctors to improve treatment. Treatment regimen recommendation algorithms will be based on expert clinician suggestions and adapt based on a knowledgebase of actual outcomes as more and more patients use the system. Clinicians will view treatment change recommendations and monitor their patient?s progress via a secure web interface. In Phase I, we will use an interactive design process including PD patient focus groups to develop the user interface and validate algorithms for identification of indicators of sub-optimal treatment. We will also work with a clinical consultant to develop an initial knowledgebase of best practices for managing motor complications. Finally, we will leverage the system in a data collection study to demonstrate feasibility. The final ParkinPal system will empower patients with PD to become more involved in their disease management and allow a personalized approach to treatment, which will ultimately improve symptomatic control and quality of life.
The objective is to design, build, and clinically assess ParkinPal, an interactive patient-centered system for patients with Parkinson?s disease to track their symptoms that provides actionable suggestions on ways to optimize treatment. Successful commercialization of ParkinPal will improve patient quality of life by maximizing drug effectiveness, reducing the time and costs associated with clinic visits, and improve access for geographic disparate populations.
