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

ABSTRACT: 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, co

SUBMITTER: Tozzi F 

PROVIDER: S-EPMC11897687 | biostudies-literature | 2025 Mar

REPOSITORIES: biostudies-literature