A Vision-Based Framework for Predicting Multiple Sclerosis and Parkinson's Disease Gait Dysfunctions-A Deep Learning Approach

• Published in: IEEE journal of biomedical and health informatics Vol. 27; no. 1; pp. 190 - 201
• Main Authors: Kaur, Rachneet, Motl, Robert W., Sowers, Richard, Hernandez, Manuel E.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Aged; Algorithms; Artificial neural networks; Body height; Cameras; Classification; Clinical trials; Deep Learning; Digital cameras; Feature extraction; Foot; Gait; gait videos; Humans; Legged locomotion; Machine learning; Movement disorders; Multiple Sclerosis; Neural networks; Neurodegenerative diseases; Neurological diseases; Older people; Parkinson Disease; Parkinson's disease; pose estimation; Pulse width modulation; Task analysis; Three-dimensional displays; Video data; Vision systems; Walking
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2022.3208077

This study examined the effectiveness of a v ision-based framework for m ultiple s clerosis (MS) and Parkinson's disease (PD) gait dysfunction prediction. We collected gait video data from multi-view digital cameras during self-paced walking from MS, PD patients and age, weight, height and gender-matched healthy older adults (HOA). We then extracted characteristic 3D joint keypoints from the collected videos. In this work, we proposed a data-driven methodology to classify strides in persons with MS (PwMS), persons with PD (PwPD) and HOA that may generalize across different walking tasks and subjects. We presented a comprehensive quantitative comparison of 16 diverse traditional machine and deep learning (DL) algorithms. When generalizing from comfortable walking (W) to walking-while-talking (WT), multi-scale residual neural network achieved perfect accuracy and AUC for classifying individuals with a given gait disorder; for subject generalization in W trials, residual neural network resulted in the highest accuracy and AUC of <inline-formula><tex-math notation="LaTeX">\mathbf {78.1\%}</tex-math></inline-formula> and 0.87 (resp.), and 1D convolutional neural network (CNN) had highest accuracy of <inline-formula><tex-math notation="LaTeX">\mathbf {75\%}</tex-math></inline-formula> in WT trials. Finally, when generalizing over new subjects in different tasks, again 1D CNN had the top classification accuracy and AUC of <inline-formula><tex-math notation="LaTeX">\mathbf {79.3\%}</tex-math></inline-formula> and 0.93 (resp.). This work is the first attempt to apply and demonstrate the potential of DL with a multi-view digital camera-based gait analysis framework for neurological gait dysfunction prediction. This study suggests the viability of inexpensive vision-based systems for diagnosing certain neurological disorders.