Identifying unique gait phenotypes across neuromotor conditions using wearable inertial sensors and topological data analysis
- 1Max Näder Lab for Rehabilitation Technologies and Outcomes Research, Shirley Ryan AbilityLab
Abstract
Wearable sensors quantify gait and mobility in detail, but translating high-dimensional data into clinically actionable insights remains challenging in precision rehabilitation. We applied Topological Data Analysis (TDA) to inertial sensor recordings from multiple gait assessments in 81 individuals with stroke, Parkinson’s disease, lower-limb difference, functional neurological disorders, and healthy controls. TDA generated a unified functional map that organized participants based on shared gait patterns across conditions. Within stroke, three phenotypes, corresponding to low, moderate, and high gait function emerged and aligned with clinical outcomes, while Parkinson’s disease shows a smoother transition from low- to high-function phenotypes. Individuals with lower-limb difference were distributed across other conditions which reflected their variable and shared gait patterns. Supervised machine-learning analysis further identified gait signatures for each phenotype. This framework enables mapping new patients into interpretable functional phenotypes, supports targeted intervention planning, and permits clinical decision-making from sensor data.
Related
- Identifying High-Care-Need Phenotypes After Hip Fracture Surgery Using Nursing-Actionable Registry Variables
- Physical activity phenotypes from volume-based versus intensity-based wearable metrics: discordant classification and divergent metabolomic, body composition, and cardiac magnetic resonance associations
- Cross-validation of wearable light loggers across electric and natural light conditions: focus on illuminance, melanopic EDI, and CCT
- Case-Based Diagnostic Performance, Challenges and Tool Development in Identifying Orofacial Conditions Among Pediatric Dentists: A Mixed-Methods Study.
- Identifying Register-Based Severity Trajectories in Anorexia Nervosa: Associations with Polygenic Scores, Psychiatric and Somatic Conditions
BibTeX
@article{daneshgar2026identifying,
title = {{Identifying unique gait phenotypes across neuromotor conditions using wearable inertial sensors and topological data analysis}},
author = {Sajjad Daneshgar and Silvia Campagnini and Rebecca Macaluso and Megan K. O’Brien and Richard L. Lieber and Arun Jayaraman},
journal = {npj Digital Medicine},
year = {2026},
month = jul,
doi = {10.1038/s41746-026-02940-8},
url = {https://doi.org/10.1038/s41746-026-02940-8},
note = {CC BY},
}
RIS
TY - JOUR
TI - Identifying unique gait phenotypes across neuromotor conditions using wearable inertial sensors and topological data analysis
AU - Sajjad Daneshgar
AU - Silvia Campagnini
AU - Rebecca Macaluso
AU - Megan K. O’Brien
AU - Richard L. Lieber
AU - Arun Jayaraman
PY - 2026
DA - 2026/07/01
JO - npj Digital Medicine
DO - 10.1038/s41746-026-02940-8
UR - https://doi.org/10.1038/s41746-026-02940-8
AB - Wearable sensors quantify gait and mobility in detail, but translating high-dimensional data into clinically actionable insights remains challenging in precision rehabilitation. We applied Topological Data Analysis (TDA) to inertial sensor recordings from multiple gait assessments in 81 individuals with stroke, Parkinson’s disease, lower-limb difference, functional neurological disorders, and healthy controls. TDA generated a unified functional map that organized participants based on shared gait patterns across conditions. Within stroke, three phenotypes, corresponding to low, moderate, and high gait function emerged and aligned with clinical outcomes, while Parkinson’s disease shows a smoother transition from low- to high-function phenotypes. Individuals with lower-limb difference were distributed across other conditions which reflected their variable and shared gait patterns. Supervised machine-learning analysis further identified gait signatures for each phenotype. This framework enables mapping new patients into interpretable functional phenotypes, supports targeted intervention planning, and permits clinical decision-making from sensor data.
SN - 2398-6352
ER -