Automated objective dystonia identification using smartphone-quality gait videos acquired in clinic
Miao, H.; Ueda, K.; Pearson, T. S.; Aravamuthan, B. R.
Show abstract
BackgroundDystonia diagnosis is subjective and often difficult, particularly when co-morbid with spasticity as occurs in cerebral palsy. ObjectiveTo develop an objective clinical screening method for dystonia MethodsWe analyzed 30 gait videos (640x360 pixel resolution, 30 frames/second) of subjects with spastic cerebral palsy acquired during routine clinic visits. Dystonia was identified by consensus of three movement disorders specialists (15 videos with and 15 without dystonia). Limb position was calculated using deep neural network-guided pose estimation (DeepLabCut) to determine inter-knee distance variance, foot angle variance, and median foot angle difference between limbs. ResultsAll gait variables were significant predictors of dystonia. An inter-knee distance variance greater than 14 pixels together with a median foot angle difference greater than 10 degrees yielded 93% sensitivity and specificity for dystonia. ConclusionsOpen-source automated video gait analysis can identify features of expert-identified dystonia. Methods like this could help clinically screen for dystonia.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Technology-aided assessment of functionally relevant sensorimotor impairments in arm and hand of post-stroke individuals 94%
- Longitudinal interaction between muscle impairments and gait pathology in growing children with Duchenne muscular dystrophy 94%
- Overground robotic walker use in the home and community: a six-month prospective cohort study 92%
Similar papers in this journal
- The importance of a consistent workflow to estimate muscle-tendon lengths based on joint angles from the conventional gait model 95%
- Evaluation of gait initiation parameters using inertial sensors in Huntington's Disease: Insights into anticipatory postural adjustments and cognitive interference 94%
- Synergies analysis produces consistent results between motion analysis laboratories 94%
Similar papers in this journal
- Beyond the Wrist: Finger-Worn Accelerometers Enhance Assessment of Post-Stroke Motor Performance 93%
- Pre-frontal cortical activity during gait is altered in pre-manifest and early spinocerebellar ataxia 93%
- Does Subthalamic Deep Brain Stimulation Impact Asymmetry and Dyscoordination of Gait in Parkinson’s Disease? 92%
Similar papers in this journal
- Modulation of Corticospinal Excitability and Muscle Synergies During Complex Locomotor Task in Individuals With and Without Cerebral Palsy: A TMS and EMG Study 94%
- Application of Digital Tools and Artificial Intelligence to the Myasthenia Gravis Core Examination 93%
- Exploring Motor Imagery as a Therapeutic Intervention for Parkinson’s Disease Patients: A Scoping Review 92%
Similar papers in this journal
- Validity and reliability of Kinect v2 for quantifying upper body kinematics during seated reaching 94%
- An explainable spatial-temporal graphical convolutional network to score freezing of gait in parkinsonian patients 93%
- Development of a Tremor Detection Algorithm for use in an Academic Movement Disorders Center 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.