Paperdoi:10.1038/s41598-026-60095-8
Automated quantification of stereotypical motor movements in autism using persistent homology
Scientific Reports 2026
TL;DR
Goodwin's group return to the six-person stereotypy recordings and quantify flap, rock and flap-rock with persistent homology, comparing wrist/torso accelerometer period features to video pose. Under leave-one-individual-out, a random forest on the accelerometer features reached a binary weighted F1 of 0.91 and a four-class weighted F1 of 0.88, ahead of the pose model. The paper is licensed CC BY-NC-ND 4.0.
- Form factor: wearable
Abstract
Stereotypical motor movements (SMM) are a core diagnostic feature of autism and remain difficult to quantify across individuals and developmental stages in an efficient and valid way. The current paper presents a novel pipeline that leverages Topological Data Analysis to quantify and characterize recurrent movement patterns. Specifically, we use persistent homology to construct low-dimensional, interpretable feature vectors that capture geometric properties associated with SMM in autistic people by extracting periodic structure from time series derived from pose estimation landmarks in video data and accelerometer signals from wearable sensors. We demonstrate that these features, combined with simple classifiers, enable accurate automated quantification of SMM in autistic people. Visualization of the learned feature space reveals that extracted features generalize across individuals and are not dominated by person-specific SMM. Our results highlight the potential of using mathematically principled features to support more scalable, interpretable, and person-agnostic characterization of SMM in autistic people in naturalistic settings.
Verbatim from Europe PMC (opens in a new tab) · Licence: cc by-nc-nd
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Signals
Keywords
How it works
Cite this paper
MBaye, A. A., Perea, J. A., Tralie, C. J., & Goodwin, M. S. (2026). Automated quantification of stereotypical motor movements in autism using persistent homology. Scientific Reports 2026. https://doi.org/10.1038/s41598-026-60095-8
MBaye, Austin A., José A. Perea, Christopher J. Tralie, and Matthew S. Goodwin. 2026. "Automated quantification of stereotypical motor movements in autism using persistent homology." Scientific Reports 2026. https://doi.org/10.1038/s41598-026-60095-8.
MBaye, A. A., Perea, J. A., Tralie, C. J. and Goodwin, M. S. (2026) 'Automated quantification of stereotypical motor movements in autism using persistent homology', Scientific Reports 2026. doi: 10.1038/s41598-026-60095-8.
MBaye, Austin A., et al. "Automated quantification of stereotypical motor movements in autism using persistent homology." Scientific Reports 2026, 2026. https://doi.org/10.1038/s41598-026-60095-8.
A. A. MBaye, J. A. Perea, C. J. Tralie, and M. S. Goodwin, "Automated quantification of stereotypical motor movements in autism using persistent homology," Scientific Reports 2026, 2026, doi: 10.1038/s41598-026-60095-8.
@article{mbaye2026automated,
title = {{Automated quantification of stereotypical motor movements in autism using persistent homology}},
author = {MBaye, Austin A. and Perea, José A. and Tralie, Christopher J. and Goodwin, Matthew S.},
year = {2026},
journal = {Scientific Reports 2026},
doi = {10.1038/s41598-026-60095-8}
}Added to the ChatPPG research hub