A Clinically Interpretable Computer-Vision Based Method for Quantifying Gait in Parkinson’s Disease

Abstract

Gait is a core motor function and is impaired in numerous neurological diseases, including Parkinson’s disease (PD). Treatment changes in PD are frequently driven by gait assessments in the clinic, commonly rated as part of the Movement Disorder Society (MDS) Unified PD Rating Scale (UPDRS) assessment (item 3.10). We proposed and evaluated a novel approach for estimating severity of gait impairment in Parkinson’s disease using a computer vision-based methodology. The system we developed can be used to obtain an estimate for a rating to catch potential errors, or to gain an initial rating in the absence of a trained clinician—for example, during remote home assessments. Videos (n=729) were collected as part of routine MDS-UPDRS gait assessments of Parkinson’s patients, and a deep learning library was used to extract body key-point coordinates for each frame. Data were recorded at five clinical sites using commercially available mobile phones or tablets, and had an associated severity rating from a trained clinician. Six features were calculated from time-series signals of the extracted key-points. These features characterized key aspects of the movement including speed (step frequency, estimated using a novel Gamma-Poisson Bayesian model), arm swing, postural control and smoothness (or roughness) of movement. An ordinal random forest classification model (with one class for each of the possible ratings) was trained and evaluated using 10-fold cross validation. Step frequency point estimates from the Bayesian model were highly correlated with manually labelled step frequencies of 606 video clips showing patients walking towards or away from the camera (Pearson’s r=0.80, p<0.001). Our classifier achieved a balanced accuracy of 50% (chance = 25%). Estimated UPDRS ratings were within one of the clinicians’ ratings in 95% of cases. There was a significant correlation between clinician labels and model estimates (Spearman’s ρ=0.52, p<0.001). We show how the interpretability of the feature values could be used by clinicians to support their decision-making and provide insight into the model’s objective UPDRS rating estimation. The severity of gait impairment in Parkinson’s disease can be estimated using a single patient video, recorded using a consumer mobile device and within standard clinical settings; i.e., videos were recorded in various hospital hallways and offices rather than gait laboratories. This approach can support clinicians during routine assessments by providing an objective rating (or second opinion), and has the potential to be used for remote home assessments, which would allow for more frequent monitoring.

A Vision-Based System for Stage Classification of Parkinsonian Gait Using Machine Learning and Synthetic Data

“…Several studies have proposed a similar methodology to perform a stage classification of PG. For example, in [20], a vision-based system was introduced to estimate the severity of PG and compare the classification results to the Unified PD Rating Scale (UPDRS) ratings.…”

“…To test all three classifiers, three data sets were generated using Equation ( 1). The following number of linear combinations, corresponding to the number of ω factors, were used to create such data sets: [20,40,60,80,100,200,250]. Each model was tested with the generated data sets, and only the ones that showed no overfitting or underfitting were selected for each model.…”

“…In the advanced stages of the disease, for example, the use of deep brain stimulation (DBS) can benefit from adjustments according to these features [20]. The development of technologies that quantify Parkinsonian gait can therefore aid clinicians in making adequate beneficial changes in patient treatments.…”

“…Nevertheless, although these studies have been able to quantify severity levels of PD according to the patients' gait, their reproducibility is often limited by the restrictions applied to the data used, as well as by the impracticality introduced by the sensor-based methodologies [17,20]. This lack of access to large data sets exemplifies a significant challenge in the study of vision-based systems in the clinical field, as it not only restricts the analysis of PG to only the specific available examples but also can lead to inaccurate conclusions obtained from possibly overfitted results [21].…”

Computer Vision and Machine Learning-Based Gait Pattern Recognition for Flat Fall Prediction

“…A person’s pattern of walking can be understood by gait analysis. Gait and balance functions decline through the course of disorders including stroke, dementia, Parkinson’s disease, arthritis, and others [ 7 , 8 , 9 ]. Gait can serve as a marker of changes in physical status and fall risk [ 10 ].…”