Exploring unsupervised feature extraction of IMU-based gait data in stroke rehabilitation using a variational autoencoder

• Published in: PloS one 2024-10, Vol.19 (10), p.e0304558
• Main Authors: Felius, Richard, Punt, Michiel, Geerars, Marieke, Wouda, Natasja, Rutgers, Rins, Bruijn, Sjoerd, David, Sina, van Dieën, Jaap
• Format: Article
• Language: English
• Subjects: Accelerometers; Adult; Aged; Algorithms; Care and treatment; Case-Control Studies; Data processing; Electrocardiography; Error analysis; Error reduction; Evaluation; Feature extraction; Female; Gait; Gait - physiology; Health aspects; Humans; Information processing; Male; Measurement; Middle Aged; Reconstruction; Rehabilitation; Reliability; Reproducibility of Results; Sensors; Stroke; Stroke - physiopathology; Stroke patients; Stroke Rehabilitation - methods; Velocity; Walk Test; Walking; Walking Speed
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0304558

Variational AutoEncoders (VAE) might be utilized to extract relevant information from an IMU-based gait measurement by reducing the sensor data to a low-dimensional representation. The present study explored whether VAEs can reduce IMU-based gait data of people after stroke into a few latent features with minimal reconstruction error. Additionally, we evaluated the psychometric properties of the latent features in comparison to gait speed, by assessing 1) their reliability; 2) the difference in scores between people after stroke and healthy controls; and 3) their responsiveness during rehabilitation. We collected test-retest and longitudinal two-minute walk-test data using an IMU from people after stroke in clinical rehabilitation, as well as from a healthy control group. IMU data were segmented into 5-second epochs, which were reduced to 12 latent-feature scores using a VAE. The between-day test-retest reliability of the latent features was assessed using ICC-scores. The differences between the healthy and the stroke group were examined using an independent t-test. Lastly, the responsiveness was determined as the number of individuals who significantly changed during rehabilitation. In total, 15,381 epochs from 107 people after stroke and 37 healthy controls were collected. The VAE achieved data reconstruction with minimal errors. Five latent features demonstrated good-to-excellent test-retest reliability. Seven latent features were significantly different between groups. We observed changes during rehabilitation for 21 and 20 individuals in latent-feature scores and gait speed, respectively. However, the direction of the change scores of the latent features was ambiguous. Only eleven individuals exhibited changes in both latent-feature scores and gait speed. VAEs can be used to effectively reduce IMU-based gait assessment to a concise set of latent features. Some latent features had a high test-retest reliability and differed significantly between healthy controls and people after stroke. Further research is needed to determine their clinical applicability.