Researchers from Stony Brook University, Massachusetts General Hospital, Harvard Medical School, the Parkinson’s Disease and Movement Center of Silicon Valley, Silicon Valley Parkinson’s Center, and Apple have published a paper detailing how off-the-shelf smartwatches paired with machine learning can be used to remotely monitor Parkinson's patients — and even guide their treatment.
"Longitudinal, remote monitoring of motor symptoms in Parkinson’s disease (PD) could enable more precise treatment decisions," the team explains of its research, "We developed the Motor fluctuations Monitor for Parkinson’s Disease (MM4PD), an ambulatory monitoring system that used smartwatch inertial sensors to continuously track fluctuations in resting tremor and dyskinesia."
Based on Apple smartwatches, the research tracked 343 patients - 225 of whom were followed for a six-month period. Using data from the smartwatch's sensors, including changes in movement patterns and the timings and severity of tremors, the team was able to produce evaluations that managed prognoses produced by a clinician in 94 percent of cases — while the remaining six percent were able to receive improved advice on treatment plans and drug regimens.
The data gathered during the experiment showed changes in symptoms which, involved clinicians claim, could have been missed through traditional evaluations — and also offered early warning of emerging tremors and impairments that could require changes in medication schedules, which would have otherwise gone unnoticed until the next in-person check-up.
The team suggests that the same approach could be used for other purposes, including motivating patients' adherence to a particular treatment regime or providing additional long-term data during the development of new drugs.
The paper has been published in Science Translational Medicine under closed-access terms.