Leif Simmatis1,2, Carolina Barnett3,4,5, Reeman Marzouqah1, Babak Taati2,6,7, Mark Boulos4,8, Yana Yunusova1,2,8. 1. Department of Speech-Language Pathology, University of Toronto, Toronto, Ontario, Canada. 2. KITE-Toronto Rehabilitation Institute, University Health Network, Toronto, Ontario, Canada. 3. Institute of Health Policy Management and Evaluation, University of Toronto, Toronto, Ontario, Canada. 4. Division of Neurology, Department of Medicine, University of Toronto, Toronto, Ontario, Canada. 5. University Health Network, Toronto, Ontario, Canada. 6. Department of Computer Science, University of Toronto, Toronto, Ontario, Canada. 7. Institute of Biomedical Engineering, University of Toronto, Toronto, Ontario, Canada. 8. Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada.
Abstract
Introduction: Telehealth/remote assessment using readily available 2D mobile cameras and deep learning-based analyses is rapidly becoming a viable option for detecting orofacial and speech impairments associated with neurological and neurodegenerative disease during telehealth practice. However, the psychometric properties (e.g., internal consistency and reliability) of kinematics obtained from these systems have not been established, which is a crucial next step before their clinical usability is established. Methods: Participants were assessed in lab using a 3 dimensional (3D)-capable camera and at home using a readily-available 2D camera in a tablet. Orofacial kinematics was estimated from videos using a deep facial landmark tracking model. Kinematic features quantified the clinically relevant constructs of velocity, range of motion, and lateralization. In lab, all participants performed the same oromotor task. At home, participants were split into two groups that each performed a variant of the in-lab task. We quantified within-assessment consistency (Cronbach's α), reliability (intraclass correlation coefficient [ICC]), and fitted linear mixed-effects models to at-home data to capture individual-/task-dependent longitudinal trajectories. Results: Both in lab and at home, Cronbach's α was typically high (>0.80) and ICCs were often good (>0.70). The linear mixed-effect models that best fit the longitudinal data were those that accounted for individual- or task-dependent effects. Discussion: Remotely gathered orofacial kinematics were as internally consistent and reliable as those gathered in a controlled laboratory setting using a high-performance 3D-capable camera and could additionally capture individual- or task-dependent changes over time. These results highlight the potential of remote assessment tools as digital biomarkers of disease status and progression and demonstrate their suitability for novel telehealth applications.
Introduction: Telehealth/remote assessment using readily available 2D mobile cameras and deep learning-based analyses is rapidly becoming a viable option for detecting orofacial and speech impairments associated with neurological and neurodegenerative disease during telehealth practice. However, the psychometric properties (e.g., internal consistency and reliability) of kinematics obtained from these systems have not been established, which is a crucial next step before their clinical usability is established. Methods: Participants were assessed in lab using a 3 dimensional (3D)-capable camera and at home using a readily-available 2D camera in a tablet. Orofacial kinematics was estimated from videos using a deep facial landmark tracking model. Kinematic features quantified the clinically relevant constructs of velocity, range of motion, and lateralization. In lab, all participants performed the same oromotor task. At home, participants were split into two groups that each performed a variant of the in-lab task. We quantified within-assessment consistency (Cronbach's α), reliability (intraclass correlation coefficient [ICC]), and fitted linear mixed-effects models to at-home data to capture individual-/task-dependent longitudinal trajectories. Results: Both in lab and at home, Cronbach's α was typically high (>0.80) and ICCs were often good (>0.70). The linear mixed-effect models that best fit the longitudinal data were those that accounted for individual- or task-dependent effects. Discussion: Remotely gathered orofacial kinematics were as internally consistent and reliable as those gathered in a controlled laboratory setting using a high-performance 3D-capable camera and could additionally capture individual- or task-dependent changes over time. These results highlight the potential of remote assessment tools as digital biomarkers of disease status and progression and demonstrate their suitability for novel telehealth applications.
Authors: Ziad S Nasreddine; Natalie A Phillips; Valérie Bédirian; Simon Charbonneau; Victor Whitehead; Isabelle Collin; Jeffrey L Cummings; Howard Chertkow Journal: J Am Geriatr Soc Date: 2005-04 Impact factor: 5.562
Authors: Christian Scheller; Andreas Wienke; Marcos Tatagiba; Alireza Gharabaghi; Kristofer F Ramina; Konstanze Scheller; Julian Prell; Johannes Zenk; Oliver Ganslandt; Barbara Bischoff; Cordula Matthies; Thomas Westermaier; Gregor Antoniadis; Maria Teresa Pedro; Veit Rohde; Kajetan von Eckardstein; Thomas Kretschmer; Malte Kornhuber; Fred G Barker; Christian Strauss Journal: Acta Neurochir (Wien) Date: 2017-02-10 Impact factor: 2.216
Authors: Panying Rong; Yana Yunusova; Marziye Eshghi; Hannah P Rowe; Jordan R Green Journal: Amyotroph Lateral Scler Frontotemporal Degener Date: 2019-11-07 Impact factor: 4.092
Authors: Christina D Kay; Michael Seidenberg; Sally Durgerian; Kristy A Nielson; J Carson Smith; John L Woodard; Stephen M Rao Journal: J Clin Exp Neuropsychol Date: 2017-01-04 Impact factor: 2.475
Authors: Nima Toosizadeh; Hossein Ehsani; Christopher Wendel; Edward Zamrini; Kathy O' Connor; Jane Mohler Journal: Sci Rep Date: 2019-07-29 Impact factor: 4.379