Automated Motor Tic Detection: A Machine Learning Approach.

BACKGROUND: Video-based tic detection and scoring is useful to independently and objectively assess tic frequency and severity in patients with Tourette syndrome. In trained raters, interrater reliability is good. However, video ratings are time-consuming and cumbersome, particularly in large-scale studies. Therefore, we developed two machine learning (ML) algorithms for automatic tic detection. OBJECTIVE: The aim of this study was to evaluate the performances of state-of-the-art ML approaches for automatic video-based tic detection in patients with Tourette syndrome. METHODS: We used 64 videos of n = 35 patients with Tourette syndrome. The data of six subjects (15 videos with ratings) were used as a validation set for hyperparameter optimization. For the binary classification task to distinguish between tic and no-tic segments, we established two different supervised learning approaches. First, we manually extracted features based on landmarks, which served as input for a Random Forest classifier (Random Forest). Second, a fully automated deep learning approach was used, where regions of interest in video snippets were input to a convolutional neural network (deep neural network). RESULTS: Tic detection F1 scores (and accuracy) were 82.0% (88.4%) in the Random Forest and 79.5% (88.5%) in the deep neural network approach. CONCLUSIONS: ML algorithms for automatic tic detection based on video recordings are feasible and reliable and could thus become a valuable assessment tool, for example, for objective tic measurements in clinical trials. ML algorithms might also be useful for the differential diagnosis of tics. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Urge-tic associations in children and adolescents with Tourette syndrome.

Premonitory urges preceding tics are a cardinal feature of Gilles de la Tourette syndrome (GTS), a developmental disorder usually starting during middle childhood. However, the temporal relation between urges and tics has only been investigated in adults. In 25 children and adolescents with GTS (8-18 years), we assess urge-tic associations, including inter-individual differences, correlation to clinical measures, and in comparison to a previously reported sample of adult GTS patients. Group-level analyses confirmed positive associations between urges and tics. However, at the individual level, less than half of participants showed positive associations, a similar proportion did not, and in two participants, the association was reversed. Tic expression and subjective urge levels correlated with corresponding clinical scores and participants with more severe tics during the urge monitor exhibited stronger urge-tic associations. Associations between reported urge levels and instantaneous tic intensity tended to be less pronounced in children and adolescents than in adult GTS patients. The observed heterogeneity of urge-tic associations cast doubt on the notion that tics are directly caused by urges. More severe tics may facilitate anticipation of tics and thereby lead to more pronounced urge-tic associations, consistent with a hypothesis of urges as a byproduct of tics.

Somatosensory perception-action binding in Tourette syndrome.

It is a common phenomenon that somatosensory sensations can trigger actions to alleviate experienced tension. Such "urges" are particularly relevant in patients with Gilles de la Tourette (GTS) syndrome since they often precede tics, the cardinal feature of this common neurodevelopmental disorder. Altered sensorimotor integration processes in GTS as well as evidence for increased binding of stimulus- and response-related features ("hyper-binding") in the visual domain suggest enhanced perception-action binding also in the somatosensory modality. In the current study, the Theory of Event Coding (TEC) was used as an overarching cognitive framework to examine somatosensory-motor binding. For this purpose, a somatosensory-motor version of a task measuring stimulus-response binding (S-R task) was tested using electro-tactile stimuli. Contrary to the main hypothesis, there were no group differences in binding effects between GTS patients and healthy controls in the somatosensory-motor paradigm. Behavioral data did not indicate differences in binding between examined groups. These data can be interpreted such that a compensatory "downregulation" of increased somatosensory stimulus saliency, e.g., due to the occurrence of somatosensory urges and hypersensitivity to external stimuli, results in reduced binding with associated motor output, which brings binding to a "normal" level. Therefore, "hyper-binding" in GTS seems to be modality-specific.

Tourette syndrome as a motor disorder revisited - Evidence from action coding.

Because tics are the defining clinical feature of Tourette syndrome, it is conceptualized predominantly as a motor disorder. There is some evidence though suggesting that the neural basis of Tourette syndrome is related to perception-action processing and binding between perception and action. However, binding processes have not been examined in the motor domain in these patients. If it is particularly perception-action binding but not binding processes within the motor system, this would further corroborate that Tourette syndrome it is not predominantly, or solely, a motor disorder. Here, we studied N = 22 Tourette patients and N = 24 healthy controls using an established action coding paradigm derived from the Theory of Event Coding framework and concomitant EEG-recording addressing binding between a planned but postponed, and an interleaved immediate reaction with different levels of overlap of action elements. Behavioral performance during interleaved action coding was normal in Tourette syndrome. Response locked lateralized readiness potentials reflecting processes related to motor execution were larger in Tourette syndrome, but only in simple conditions. However, pre-motor processes including response preparation and configuration reflected by stimulus-locked lateralized readiness potentials were normal. This was supported by a Bayesian data analysis providing evidence for the null hypothesis. The finding that processes integrating different action-related elements prior to motor execution are normal in Tourette syndrome suggests that Tourette it is not solely a motor disorder. Considering other recent evidence, the data show that changes in "binding" in Tourette syndrome are specific for perception-action integration but not for action coding.

Questioning the definition of Tourette syndrome-evidence from machine learning.

Tics in Tourette syndrome are often difficult to discern from single spontaneous movements or vocalizations in healthy people. In this study, videos of patients with Tourette syndrome and healthy controls were taken and independently scored according to the Modified Rush Videotape Rating Scale. We included n = 101 patients with Tourette syndrome (71 males, 30 females, mean age 17.36 years ± 10.46 standard deviation) and n = 109 healthy controls (57 males, 52 females, mean age 17.62 years ± 8.78 standard deviation) in a machine learning-based analysis. The results showed that the severity of motor tics, but not vocal phenomena, is the best predictor to separate and classify patients with Tourette syndrome and healthy controls. This finding questions the validity of current diagnostic criteria for Tourette syndrome requiring the presence of both motor and vocal tics. In addition, the negligible importance of vocalizations has implications for medical practice, because current recommendations for Tourette syndrome probably also apply to the large group with chronic motor tic disorders.