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.

Parkinson’s disease (PD) is a common neurological disorder, with bradykinesia being one of its cardinal features. Objective quantification of bradykinesia using computer vision has the potential to standardise decision-making, for patient treatment and clinical trials, while facilitating remote assessment. We utilised a dataset of part-3 MDS-UPDRS motor assessments, collected at four independent clinical and one research sites on two continents, to build computer-vision-based models capable of inferring the correct severity rating robustly and consistently across all identifiable subgroups of patients. These results contrast with previous work limited by small sample sizes and small numbers of sites. Our bradykinesia estimation corresponded well with clinician ratings (interclass correlation 0.74). This agreement was consistent across four clinical sites. This result demonstrates how such technology can be successfully deployed into existing clinical workflows, with consumer-grade smartphone or tablet devices, adding minimal equipment cost and time.

No abstract

Human vision is attuned to the subtle differences between individual faces. Yet we lack a quantitative way of predicting how similar two face images look and whether they appear to show the same person. Principal component–based three-dimensional (3D) morphable models are widely used to generate stimuli in face perception research. These models capture the distribution of real human faces in terms of dimensions of physical shape and texture. How well does a “face space” based on these dimensions capture the similarity relationships humans perceive among faces? To answer this, we designed a behavioral task to collect dissimilarity and same/different identity judgments for 232 pairs of realistic faces. Stimuli sampled geometric relationships in a face space derived from principal components of 3D shape and texture (Basel face model [BFM]). We then compared a wide range of models in their ability to predict the data, including the BFM from which faces were generated, an active appearance model derived from face photographs, and image-computable models of visual perception. Euclidean distance in the BFM explained both dissimilarity and identity judgments surprisingly well. In a comparison against 16 diverse models, BFM distance was competitive with representational distances in state-of-the-art deep neural networks (DNNs), including novel DNNs trained on BFM synthetic identities or BFM latents. Models capturing the distribution of face shape and texture across individuals are not only useful tools for stimulus generation. They also capture important information about how faces are perceived, suggesting that human face representations are tuned to the statistical distribution of faces.