Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders

Abstract

Smartwatches provide technology-based assessments in Parkinson’s disease (PD). We present results for sensor validation and disease classification via Machine Learning (ML). A comparison setup was designed with two different series of Apple smartwatches, one Nanometrics seismometer and a high-precision shaker to measure tremor-like amplitudes and frequencies. Clinical smartwatch measurements were acquired from a prospective study including 450 participants with PD, differential diagnoses (DD) and healthy participants. All participants wore two smartwatches and within a 15-min examination. Symptoms and medical history were captured on the paired smartphone. A broad range of different ML classifiers were cross-validated. Amplitude and frequency differences between smartwatches and the seismometer were under the level of clinical significance. The most advanced task of distinguishing PD vs DD was evaluated with 74,1% balanced accuracy, 86,5% precision and 90,5% recall by Multilayer Perceptrons. Deep Learning architectures significantly underperformed in all classification tasks. Smartwatches are capable of capturing subtle-tremor signs with low noise. This study provided the largest PD sample size of two-hand smartwatch measurements and our preliminary ML-evaluation shows that such a system provides powerful means for diagnosis classification and new digital biomarkers but it remains challenging for distinguishing similar disorders.

Digital Phenotyping in Clinical Neurology

“…110 Wrist sensor data collected during stationary assessments at home in individuals with Huntington's disease were used to train a model to estimate the probability of chorea 111 and studies have demonstrated the utility of IMUs in smartphones and wrist devices to capture characteristics of tremor in Parkinson disease and essential tremor. 81 112 113 114 115 116 117 118 Passive data from wrist sensors have been shown to be useful for assessment of arm motor function in acute/subacute stroke, 119 120 121 122 123 prediction of 3-month poststroke disability, 124 and assessment of daily arm use months to years after stroke. 125 126 127 Wrist sensor data have also been shown to correlate with improvement in upper extremity function during stroke recovery.…”