Identifying treatment non-responders based on pre-treatment gait characteristics - A machine learning approach

Rosa M S Visscher; Julia Murer; Fatemeh Fahimi; Elke Viehweger; William R Taylor; Reinald Brunner; Navrag B Singh

doi:10.1016/j.heliyon.2023.e21242

Identifying treatment non-responders based on pre-treatment gait characteristics - A machine learning approach

Heliyon. 2023 Oct 23;9(11):e21242. doi: 10.1016/j.heliyon.2023.e21242. eCollection 2023 Nov.

Authors

Rosa M S Visscher^{1

2}, Julia Murer¹, Fatemeh Fahimi^{1

3}, Elke Viehweger^{2

4}, William R Taylor¹, Reinald Brunner^{2

4}, Navrag B Singh^{1

3}

Affiliations

¹ Laboratory for Movement Biomechanics, Institute for Biomechanics, Department of Health Science & Technology, ETH Zürich, Zürich, Switzerland.
² Department of Biomedical Engineering, University of Basel, Basel, Switzerland.
³ Singapore-ETH Centre, Future Health Technologies Program, CREATE campus, 1 CREATE Way, #06-01 CREATE Tower, Singapore 138602.
⁴ Laboratory of Movement Analysis, University Children's Hospital Basel (UKBB), Basel, Switzerland.

Abstract

Background: Paediatric movement disorders such as cerebral palsy often negatively impact walking behaviour. Although clinical gait analysis is usually performed to guide therapy decisions, not all respond positively to their assigned treatment. Identifying these individuals based on their pre-treatment characteristics could guide clinicians towards more appropriate and personalized interventions. Using routinely collected pre-treatment gait and anthropometric features, we aimed to assess whether standard machine learning approaches can be effective in identifying patients at risk of negative treatment outcomes.

Methods: Observational data of 119 patients with movement disorders were retrospectively extracted from a local clinical database, comprising sagittal joint angles and spatiotemporal parameters, derived from motion capture data pre- and post-treatment (physiotherapy, orthosis, botulin toxin injections, or surgery). Participants were labelled based on their change in gait profile score (GPS, non-responders with a decline in GPS of <1.6° vs. responders). Their pre-treatment features (sagittal joint angles, spatiotemporal parameters, anthropometrics) were used to train a support vector machine classifier with 5-fold cross-validation and Bayesian optimization within a MATLAB-based Classification Learner App.

Results: An average accuracy of 88.2 ± 0.5 % was achieved for identifying participants whose gait will not respond to treatment, with 64 % true negative rate and an area under the curve of 88 %.

Conclusion: Overall, a classical machine learning model was able to identify patients at risk of not responding to treatment, based on gait features and anthropometrics collected prior to treatment. The output of such a model could function as a warning signal, notifying clinicians that a certain individual might not respond well to the standard of care and that a more personalized intervention might be needed.

Keywords: Cerebral palsy; Clinical gait analysis; Machine learning; Treatment outcomes.