EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Forestwalk: A Machine Learning Workflow Brings New Insights Into Posture and Balance in Rodent Beam Walking

Francesca Tozzi, Yan-Ping Zhang, Ramanathan Narayanan, Damian Roqueiro, Eoin C O'Connor iD

European Journal of Neuroscience · 2025

DOI: 10.1111/ejn.70033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Neuroscience, 2025. Verfasst von Francesca Tozzi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Neuroscience and Rare Diseases Discovery and Translational Area, Roche Pharma Research and Early Development, Roche Innovation Center Basel, F. Hoffm…. Hauptthemen laut MEDLINE: Machine Learning, Postural Balance, Walking, Posture. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: F. Hoffmann-La Roche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The beam walk is widely used to study coordination and balance in rodents. While the task has ethological validity, the main endpoints of “foot slip counts” and “time to cross” are prone to human‐rater variability and offer limited sensitivity and specificity. We asked if machine learning–based methods could reveal previously hidden, but biologically relevant, insights from the task. Marker‐less pose estimation, using DeepLabCut, was deployed to label 13 anatomical key points on mice traversing the beam. Next, we automated classical endpoint detection, including foot slips, with high recall (> 90%) and precision (> 80%). Using data derived from key point tracking, a total of 395 features were engineered and a random forest classifier deployed that, together with skeletal visualizations, could test for group differences and identify determinant features. This workflow, named Forestwalk, uncovered pharmacological treatment effects in C57BL/6J mice, revealed phenotypes in transgenic mice used to study Angelman syndrome and SLC6A1‐related neurodevelopmental disorder, and will facilitate a deeper understanding of how the brain controls balance in health and disease.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPostural BalanceWalkingPostureAnimalsMiceMice, Inbred C57BLMaleMice, TransgenicWorkflow

Stichwörter der Autor:innen

Angelman syndromeSLC6A1‐related neurodevelopmental disorderbalancebeam walkmouse

Autor:innen und Institutionen

  • Neuroscience and Rare Diseases Discovery and Translational Area, Roche Pharma Research and Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd, Basel, Switzerland.
  • Data and Analytics, Roche Pharma Research and Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd, Basel, Switzerland.

ORCID-Profile: Eoin C O'Connor

Förderung

  • F. Hoffmann-La Roche

Zitieren

APA

Tozzi, F., Zhang, Y. P., Narayanan, R., Roqueiro, D., & O'Connor, E. C. (2025). Forestwalk: A Machine Learning Workflow Brings New Insights Into Posture and Balance in Rodent Beam Walking. European Journal of Neuroscience. https://doi.org/10.1111/ejn.70033

Vancouver

Tozzi F, Zhang YP, Narayanan R, Roqueiro D, O'Connor EC. Forestwalk: A Machine Learning Workflow Brings New Insights Into Posture and Balance in Rodent Beam Walking. European Journal of Neuroscience. 2025. doi:10.1111/ejn.70033

BibTeX
@article{Tozzi2025,
  author = {Tozzi, Francesca and Zhang, Yan-Ping and Narayanan, Ramanathan and Roqueiro, Damian and O'Connor, Eoin C},
  title = {Forestwalk: A Machine Learning Workflow Brings New Insights Into Posture and Balance in Rodent Beam Walking},
  journal = {European Journal of Neuroscience},
  year = {2025},
  doi = {10.1111/ejn.70033}
}
Kostenlos starten →