Evaluating the ability of a predictive vision-based machine learning model to measure changes in gait in response to medication and DBS within individuals with Parkinson’s disease

Abstract

Introduction Gait impairments in Parkinson’s disease (PD) are treated with dopaminergic medication or deep-brain stimulation (DBS), although the magnitude of the response is variable between individuals. Computer vision-based approaches have previously been evaluated for measuring the severity of parkinsonian gait in videos, but have not been evaluated for their ability to identify changes within individuals in response to treatment. This pilot study examines whether a vision-based model, trained on videos of parkinsonism, is able to detect improvement in parkinsonian gait in people with PD in response to medication and DBS use. Methods A spatial–temporal graph convolutional model was trained to predict MDS-UPDRS-gait scores in 362 videos from 14 older adults with drug-induced parkinsonism. This model was then used to predict MDS-UPDRS-gait scores on a different dataset of 42 paired videos from 13 individuals with PD, recorded while ON and OFF medication and DBS treatment during the same clinical visit. Statistical methods were used to assess whether the model was responsive to changes in gait in the ON and OFF states. Results The MDS-UPDRS-gait scores predicted by the model were lower on average (representing improved gait; p = 0.017, Cohen’s d = 0.495) during the ON medication and DBS treatment conditions. The magnitude of the differences between ON and OFF state was significantly correlated between model predictions and clinician annotations (p = 0.004). The predicted scores were significantly correlated with the clinician scores (Kendall’s tau-b = 0.301, p = 0.010), but were distributed in a smaller range as compared to the clinician scores. Conclusion A vision-based model trained on parkinsonian gait did not accurately predict MDS-UPDRS-gait scores in a different PD cohort, but detected weak, but statistically significant proportional changes in response to medication and DBS use. Large, clinically validated datasets of videos captured in many different settings and treatment conditions are required to develop accurate vision-based models of parkinsonian gait.

Special collection in association with the 2023 International Conference on aging, innovation and rehabilitation

“…While covering diverse topics, articles in this collection are linked through multiple connecting themes, such as functional electrical stimulation [ 1 , 2 ] or the application of signal processing and artificial intelligence in solving aging and rehabilitation problems [ 2 – 8 ]. Specifically, a number of the papers in this collection [ 4 – 7 ] explore the application of computer vision techniques in various healthcare domains, particularly focusing on rehabilitation and mobility assistance. Lim et al [ 2 ], for instance, investigate the feasibility of using depth cameras and pressure mats in a balance training system for individuals with spinal cord injuries.…”

“…Lim et al [ 2 ] experimentally demonstrate that depth cameras and pressure mats can accurately track the body center of mass and center of pressure. As another example, Sabo et al [ 7 ] demonstrate the responsiveness of a previously developed predictive vision-based machine learning model [ 11 , 12 ] to measure changes in gait in response to medication and deep brain stimulation in individuals with Parkinson’s disease.…”