Semi‐Automated Multi‐Label Classification of Autistic Mannerisms by Machine Learning on Post Hoc Skeletal Tracking
Autism Research · 2025
DOI: 10.1002/aur.70020 ↗Kurz gefasst
Fachartikel in der Zeitschrift Autism Research, 2025. Verfasst von Christian Lemler und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Autism Research and Intervention Center of Excellence, University Ho…. Hauptthemen laut MEDLINE: Machine Learning, Autism Spectrum Disorder, Stereotyped Behavior. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft.
Abstract (Originalsprache)
Mannerisms describe repetitive or unconventional body movements like arm flapping. These movements are early markers of restricted and repetitive behaviors (RRBs) in autism spectrum disorder (ASD). However, assessing mannerisms reliably is challenging. Even after extensive training in behavioral observations, inter‐rater agreements for mannerism items remain insufficient. The current study used machine learning (ML) to classify mannerisms from videotaped behavioral observations in children with ASD. We developed a classification scheme for mannerisms as ground truth and applied it to videotaped behavioral observations from an early intervention study. ML was used in two steps: First, the OpenPose algorithm post hoc extracted features based on body movements in the videos. Second, a long short‐term memory (LSTM) neural network classified the features in a multi‐label approach to distinguish between the absence of mannerisms, flapping, jumping, and both flapping + jumping. The trained models achieved 70.2% accuracy ( F 1 score: 31.8%) using nested cross‐validation. The analysis improves on previous videotaped ML classification studies by splitting training and test data subject‐wise, highlighting its clinical applicability. The LSTM models are made publicly available for use with other video datasets. Our results show that ML‐based classification of mannerisms is a promising tool for enhancing objective diagnostic methods of behavioral observations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Autism Research and Intervention Center of Excellence, University Hospital Frankfurt, Goethe-University, Frankfurt am Main, Germany.
ORCID-Profile: Christian Lemler, Solvejg K Kleber, Naisan Raji, Simeon Platte, Nico Bast
Förderung
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Lemler, C., Kleber, S. K., Polzer, L., Raji, N., Kitzerow-Cleven, J., Kim, Z., Platte, S., Freitag, C. M., & Bast, N. (2025). Semi‐Automated Multi‐Label Classification of Autistic Mannerisms by Machine Learning on Post Hoc Skeletal Tracking. Autism Research. https://doi.org/10.1002/aur.70020
Vancouver
Lemler C, Kleber SK, Polzer L, Raji N, Kitzerow-Cleven J, Kim Z, et al. Semi‐Automated Multi‐Label Classification of Autistic Mannerisms by Machine Learning on Post Hoc Skeletal Tracking. Autism Research. 2025. doi:10.1002/aur.70020
BibTeX
@article{Lemler2025,
author = {Lemler, Christian and Kleber, Solvejg K and Polzer, Leonie and Raji, Naisan and Kitzerow-Cleven, Janina and Kim, Ziyon and Platte, Simeon and Freitag, Christine M and Bast, Nico},
title = {Semi‐Automated Multi‐Label Classification of Autistic Mannerisms by Machine Learning on Post Hoc Skeletal Tracking},
journal = {Autism Research},
year = {2025},
doi = {10.1002/aur.70020}
}
EUVIMED