The kinectome: a comprehensive kinematic map of human motion in health and disease
Troisi Lopez, E.; Sorrentino, P.; Liparoti, M.; Minino, R.; Carotenuto, A.; Amico, E.; Sorrentino, G.
Show abstract
Effective human movement requires the coordinated participation of the whole musculoskeletal system. Here we propose to represent the human body movements as a network (that we named "kinectome"), where nodes are body parts, and edges are defined as the correlations of the accelerations between each pair of body parts during gait. We apply this framework in healthy individuals and patients with Parkinsons disease (PD). The network dynamics in Parkinsons display high variability, as conveyed by the high variance and the modular structure in the patients kinectomes. Furthermore, our analysis identified a set of anatomical elements that are specifically related to the balance impairment in PD. Furthermore, each participant could be identified based on its kinectome patterns, akin to a "fingerprint" of movement, confirming that our approach captures relevant features of gait. We hope that applying network approaches to human kinematics yields new insights to characterize human movement.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Discovering individual-specific gait signatures from data-driven models of neuromechanical dynamics 94%
- Cortical propagation as a biomarker for recovery after stroke 94%
- A neurocomputational theory of action regulation predicts motor behavior in neurotypical individuals and patients with Parkinsons disease 93%
Similar papers in this journal
- Identification of Spared and Proportionally Controllable Hand Motor Dimensions in Motor Complete Spinal Cord Injuries Using Latent Manifold Analysis 94%
- Identification of distinct subtypes of post-stroke and neurotypical gait behaviors using neural network analysis of kinematic time series data 93%
- Multi-grip classification-based prosthesis control with two EMG-IMU sensors 91%
Similar papers in this journal
- Quantifying normal and parkinsonian gait features from home movies: Practical application of a deep learning-based 2D pose estimator 95%
- Autocorrelation-based method to identify disordered rhythm in Parkinsons disease tasks: a novel approach applicable to multimodal devices 94%
- Sex-specific tuning of modular muscle activation patterns for locomotion in young and older adults 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.