EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Semi‐Automated Multi‐Label Classification of Autistic Mannerisms by Machine Learning on Post Hoc Skeletal Tracking

Christian Lemler iD, Solvejg K Kleber iD, Leonie Polzer, Naisan Raji iD, Janina Kitzerow-Cleven, Ziyon Kim, Simeon Platte iD, Christine M Freitag, Nico Bast iD

Autism Research · 2025

DOI: 10.1002/aur.70020 ↗

At a glance

Journal article in Autism Research, 2025. Written by Christian Lemler and 8 co-authors. Institution: Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Autism Research and Intervention Center of Excellence, University Ho…. Major MEDLINE topics: Machine Learning, Autism Spectrum Disorder, Stereotyped Behavior. Cited 6 times so far (Crossref); 47 references. The full text is freely available (open access, CC BY 4.0). Funded by: Deutsche Forschungsgemeinschaft.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

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.

Subjects

MeSH terms (MEDLINE)

Machine LearningAutism Spectrum DisorderStereotyped BehaviorHumansMaleFemaleChildVideo RecordingChild, PreschoolAlgorithmsNeural Networks, ComputerMovement

Author keywords

autism spectrum disordermachine learningmannerismsmulti‐label classificationstereotypic behavior

Authors and institutions

  • 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 profiles: Christian Lemler, Solvejg K Kleber, Naisan Raji, Simeon Platte, Nico Bast

Funding

  • Deutsche Forschungsgemeinschaft

Cite

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}
}
Start for free →