Authors:
Nicoletta Balletti
1
;
2
;
Roberto Zinni
3
;
Marco Russodivito
1
;
Gennaro Laudato
1
;
Simone Scalabrino
1
;
4
and
Rocco Oliveto
1
;
4
Affiliations:
1
STAKE Lab, University of Molise, Pesche (IS), Italy
;
2
Defense Veterans Center, Ministry of Defense, Rome, Italy
;
3
Word Power SRL, Italy
;
4
Datasound srl, Pesche (IS), Italy
Keyword(s):
Gait Analysis, Motion Tracking, DGI, Machine Learning.
Abstract:
Strokes constitute a major cause of both mortality and disability, carrying significant economic implications for healthcare systems. Evaluating the quality of gait in post-stroke patients during rehabilitation is essential for providing effective care. The Dynamic Gait Index (DGI) is a valuable metric for evaluating gait quality. However, the assessment of such an index typically requires invasive tests or specialized sensors. In this paper, we introduce a machine learning-based approach for estimating DGI exclusively from video recordings. Our research encompasses a comprehensive set of experiments, including data preprocessing, feature selection, and the application of various machine learning algorithms. To ensure the robustness of our findings, we employ the Leave 1 Subject Out (L1SO) cross-validation method. Our results underscore the challenge of accurately estimating DGI using solely video data. We achieved an R-squared (R2 ) value of only 0.19 and a mean absolute error (MAE)
of 2.2. Notably, we observed that our approach yielded notably poorer results for a specific subset of three patients. Upon excluding this subset, the R2 increased to 0.30, and the MAE improved to 1.9. This observation suggests that incorporating patient-specific features into the model may hold the key to enhancing its overall accuracy.
(More)