Watching Parkinson’s disease with wrist-based sensors

Parkinson’s disease lacks sensitive, objective, and reliable measures for disease progression and response. This presents a challenge for clinical trials given the multifaceted and fluctuating nature of disease symptoms. Innovations in digital health and wearable sensors promise to more precisely measure aspects of patient function and well-being. A recent study from Verily Life Sciences presents results for a smartwatch-based motor exam intended to accelerate the development and evaluation of therapies for parkinson.

Smartwatches now have nearly half a billion active users, enabling longitudinal and multimodal health monitoring at unprecedented scale. In particular, digital biomarkers and clinical outcome assessments may improve on qualitative evaluations for conditions like Parkinson’s disease. A team from Verily (formerly Google Life Sciences) developed and validated a smartwatch-based motor exam for parkinson that is concordant with standard disease severity ratings, responsive to medication effects, and reliable across repeat measurements. A virtual motor exam could complement in-clinic visits and passive monitoring strategies to unlock more precise insights for parkinson treatment. Remaining challenges include integration of data streams across complementary monitoring techniques and alignment of digital measurements with outcomes most meaningful to patients.

Co-sponsored by Verily, the Personalized Parkinson’s Project (PPP) is a prospective single-center study of patients with early-stage PD in the Netherlands. Participants are monitored at 4-month intervals via on-site clinical assessments and continuously via the Verily Study Watch. Using accelerometer data from the Study Watch, the authors developed a PD virtual motor exam (PD-VME) consisting of eight self-guided tasks. Each task corresponds to elements of the Movement Disorder Society-Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) Part III exam, currently the “gold-standard” for motor evaluation of PD.

In total, 370 participants logged 22,668 virtual exams over 70 weeks.

Although a solid evidence base on clinical utility is needed for regulatory approval and commercial acceptance, it can be argued that compared to in-clinic testing, virtual testing offers more frequent and convenient monitoring in natural living environments. In this scenario virtual testing may represent a good synergy with passive monitoring. 

Future research may also integrate measures from other sensors, such as microphones for speech, video recordings for facial expression, and insoles for postural instability.

The bar is rightfully high. But with proper research and validation, remote sensors may soon provide a more powerful and precise set of tools for studying this devastating disease.

Source: Watching Parkinson’s disease with wrist-based sensors (NPJ Digital Medicine)

Share this Post!