Premium
A novel automatic method for monitoring Tourette motor tics through a wearable device
Author(s) -
Bernabei Michel,
Preatoni Ezio,
Mendez Martin,
Piccini Luca,
Porta Mauro,
Andreoni Giuseppe
Publication year - 2010
Publication title -
movement disorders
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.352
H-Index - 198
eISSN - 1531-8257
pISSN - 0885-3185
DOI - 10.1002/mds.23188
Subject(s) - tics , gold standard (test) , wearable computer , computer science , context (archaeology) , tourette syndrome , accelerometer , artificial intelligence , psychology , pattern recognition (psychology) , physical medicine and rehabilitation , medicine , statistics , mathematics , neuroscience , paleontology , psychiatry , biology , operating system , embedded system
The aim of this study was to propose a novel automatic method for quantifying motor‐tics caused by the Tourette Syndrome (TS). In this preliminary report, the feasibility of the monitoring process was tested over a series of standard clinical trials in a population of 12 subjects affected by TS. A wearable instrument with an embedded three‐axial accelerometer was used to detect and classify motor tics during standing and walking activities. An algorithm was devised to analyze acceleration data by: eliminating noise; detecting peaks connected to pathological events; and classifying intensity and frequency of motor tics into quantitative scores. These indexes were compared with the video‐based ones provided by expert clinicians, which were taken as the gold‐standard. Sensitivity, specificity, and accuracy of tic detection were estimated, and an agreement analysis was performed through the least square regression and the Bland‐Altman test. The tic recognition algorithm showed sensitivity = 80.8% ± 8.5% (mean ± SD), specificity = 75.8% ± 17.3%, and accuracy = 80.5% ± 12.2%. The agreement study showed that automatic detection tended to overestimate the number of tics occurred. Although, it appeared this may be a systematic error due to the different recognition principles of the wearable and video‐based systems. Furthermore, there was substantial concurrency with the gold‐standard in estimating the severity indexes. The proposed methodology gave promising performances in terms of automatic motor‐tics detection and classification in a standard clinical context. The system may provide physicians with a quantitative aid for TS assessment. Further developments will focus on the extension of its application to everyday long‐term monitoring out of clinical environments. © 2010 Movement Disorder Society