Quantification of tremor using consumer product accelerometry is feasible in patients with essential tremor and Parkinson’s disease: a comparative study

Abstract

Background: To quantify pharmacological effects on tremor in patients with essential tremor (ET) or Parkinson's Disease (PD), laboratory-grade accelerometers have previously been used. Over the last years, consumer products such as smartphones and smartwatches have been increasingly applied to measure tremor in an easy way. However, it is unknown how the technical performance of these consumer product accelerometers (CPAs) compares to laboratory-grade accelerometers (LGA). This study was performed to compare the technical performance of CPAs with LGA to measure tremor in patients with Parkinson's Disease (PD) and essential tremor (ET). Methods: In ten patients with PD and ten with ET, tremor peak frequency and corresponding amplitude were measured with 7 different CPAs (Apple iPhone 7, Apple iPod Touch 5, Apple watch 2, Huawei Nexus 6P, Huawei watch, mbientlabMetaWear (MW) watch, mbientlab MW clip) and compared to a LGA (Biometrics ACL300) in resting and extended arm position. Results: Both in PD and ET patients, the peak frequency of CPAs did not significantly differ from the LGA in terms of limits of agreement. For the amplitude at peak frequency, only the iPhone and MW watch performed comparable to the LGA in ET patients, while in PD patients all methods performed comparable except for the iPod Touch and Huawei Nexus. Amplitude was higher when measured with distally-located CPAs (Clip, iPhone, iPod) compared with proximally-located CPAs (all watches). The variability between subjects was higher than within subjects for frequency (25.1% vs. 13.4%) and amplitude measurement (331% vs. 53.6%). Resting arm position resulted in lower intra-individual variability for frequency and amplitude (13.4 and 53.5%) compared to extended arm position (17.8 and 58.1%).

First Clinical Study with AP30663 ‐ a KCa2 Channel Inhibitor in Development for Conversion of Atrial Fibrillation

“…After calculating the Power Spectrum Density for each axis, the L1‐norm was calculated. Then, the peak frequency and corresponding amplitude were used as read‐outs, as also described elsewhere 12 …”

Automatic Resting Tremor Assessment in Parkinson’s Disease Using Smartwatches and Multitask Convolutional Neural Networks

“…A total of 18 subjects with PD were recruited from different Parkinson associations located in Spain and Portugal who were in early stages (≤2) of the disease according to the Hoehn and Yahr (H&Y) scale [ 79 ] (age: 64.9 ± 7.6 [ 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 ] years; gender: 8 M/10 F; stage H&Y I/II/: 4/14). Patients had a good clinical response to levodopa and/or dopamine agonists and did not present dementia according to the diagnostic and statistical manual of mental disorders IV (DSM IV) criteria [ 78 ].…”

“…Some approaches have proposed the use of several sensors placed on different parts of the body [ 32 , 33 , 35 , 36 , 37 , 38 , 39 ], while recent approaches tend to use sensors placed on the wrist, fingers [ 40 , 41 , 42 , 43 ], foot [ 44 ], and smartphones with writs adapters or watch-like devices [ 45 , 46 , 47 , 48 , 49 , 50 ]. Also, these approaches have been used in companion with automatic classification algorithms [ 36 , 37 , 38 , 39 , 40 , 46 ], threshold approaches [ 51 , 52 , 53 , 54 , 55 ], and deep learning technics [ 15 , 49 , 50 , 56 ] to provide low cost and non-invasive solutions for remote monitoring [ 45 , 57 ].…”

“…In recent years, most of the works concerning the analysis of tremors have used supervised machine learning techniques to identify the presence of tremors using different types of “hand-crafted” features extracted from inertial signals in both time and frequency domains [ 15 , 36 , 37 , 38 , 39 , 40 , 46 , 55 , 56 , 57 ]. Other authors have used threshold-based algorithms, taking advantage of the heuristic knowledge of the symptom to determine objective indicators for monitoring the symptom [ 43 , 45 , 47 , 51 , 52 , 53 , 54 , 55 ].…”

“…Among the solutions based on wearable technology, the use of consumer devices such as smartphones [ 45 , 57 ] and smartwatches [ 51 , 54 ] has been identified. These studies show that the use of smart devices is feasible, reliable, and well-related to clinical scores, whereas in the case of smartwatches they show good acceptance from the patients, which may allow their use as continuous monitoring devices.…”