Automated Motor Tic Detection: A Machine Learning Approach

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung

Beitragende

  • Nele Sophie Brügge - , Universität zu Lübeck, Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI) (Autor:in)
  • Gesine Marie Sallandt - , Universitätsklinikum Schleswig-Holstein Campus Lübeck, University of Economics in Katowice (Autor:in)
  • Ronja Schappert - , Universitätsklinikum Schleswig-Holstein Campus Lübeck (Autor:in)
  • Frédéric Li - , Universität zu Lübeck (Autor:in)
  • Alina Siekmann - , Universitätsklinikum Schleswig-Holstein Campus Lübeck (Autor:in)
  • Marcin Grzegorzek - , Universität zu Lübeck, Universität Trier (Autor:in)
  • Tobias Bäumer - , Universitätsklinikum Schleswig-Holstein Campus Lübeck (Autor:in)
  • Christian Frings - , Klinik und Poliklinik für Kinder- und Jugendpsychiatrie (Autor:in)
  • Christian Beste - , Klinik und Poliklinik für Kinder- und Jugendpsychiatrie, Shandong Normal University, Universität zu Lübeck (Autor:in)
  • Roland Stenger - , Universität zu Lübeck (Autor:in)
  • Veit Roessner - , Klinik und Poliklinik für Kinder- und Jugendpsychiatrie (Autor:in)
  • Sebastian Fudickar - , Universität zu Lübeck (Autor:in)
  • Heinz Handels - , Universität zu Lübeck, Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI) (Autor:in)
  • Alexander Münchau - , Universitätsklinikum Schleswig-Holstein Campus Lübeck (Autor:in)

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.

Details

OriginalspracheEnglisch
Seiten (von - bis)1327-1335
Seitenumfang9
FachzeitschriftMovement disorders
Jahrgang38 (2023)
Ausgabenummer7
PublikationsstatusVeröffentlicht - 11 Mai 2023
Peer-Review-StatusJa

Externe IDs

PubMed 37166278
ORCID /0000-0002-2989-9561/work/146788813
WOS 000985902300001

Schlagworte

ASJC Scopus Sachgebiete

Schlagwörter

  • deep neural networks, Face Mesh, machine learning, Random Forest, tic detection, Tourette syndrome, Tic detection, Deep neural networks, Machine learning, Tics/diagnosis, Reproducibility of Results, Humans, Tourette Syndrome/diagnosis, Machine Learning, Tic Disorders/diagnosis

Bibliotheksschlagworte