Automated Motor Tic Detection: A Machine Learning Approach

Abstract

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.

Automatic identification of facial tics using selfie-video

“…Previous studies on tic detection from videos have utilized diverse algorithms to learn spatial and temporal properties for identifying tics. Similar to our methodology, other studies [24], [25] have emphasized the significance of incorporating tic-related features, such as facial landmarks or facial action unit intensities, into the input data of the model. Selecting tic-related features contributes to achieving more interpretable results compared to the visual features extracted by deep neural networks [24], [25].…”

“…In comparison, close-up video recordings have the capacity to capture facial movements and thus are well-suited for facial tic identification. Previous studies detected facial tics from short video recordings conducted in clinical settings [23]- [25]. However, these videos provide only snapshots of the current state and lack a comprehensive representation of the natural expression of tics in everyday environments.…”

“…Diverse machine learning algorithms have been proposed to address the challenge of detecting facial tics from video data. While some approaches involve architectures incorporating unsupervised visual feature learning and deep feature extraction [23], [26], others have shown the contribution of tic-related feature extraction (e.g., facial landmarks, facial action unit intensities) for enhancing network performance [24], [25].…”

A Novel Video-Based Methodology for Automated Classification of Dystonia and Choreoathetosis in Dyskinetic Cerebral Palsy During a Lower Extremity Task

“…Previous comparable studies made use of classical supervised machine learning approach such as k-Nearest Neighbors, Support Vector Machine, Random Forests, and Quadratic Discriminant Analysis using handcrafted features as well as deep learning approaches. [10][11][12][13] A comparison between HIVE-COTE 2.0 and the use of different algorithms on the current use case is deemed necessary in the future.…”

“…Key point detection by markerless motion analysis-also referred to as human pose estimation in the field of computer vision-can be used to process video data as an input for subsequent machine learning or deep learning models. [10][11][12][13][14] Several open-source toolbox codes facilitate key point detection based on convolutional neural networks. 15 Examples of these toolbox codes are OpenPose 16 and DeepLabCut.…”