Causality Analysis of Inertial Body Sensors for Multiple Sclerosis Diagnostic Enhancement

Inertial body sensors have emerged in recent years as an effective tool for evaluating mobility impairment resulting from various diseases, disorders, and injuries. For example, body sensors have been used in 6-min walk (6 MW) tests for multiple sclerosis (MS) patients to identify gait features useful in the study, diagnosis, and tracking of the disease. However, most studies to date have focused on features localized to the lower or upper extremities and do not provide a holistic assessment of mobility. This paper presents a causality analysis method focused on the coordination between extremities to identify subtle whole-body mobility impairment that may aid disease diagnosis. This method was developed for and utilized in an MS pilot study with 41 subjects (28 persons with MS (PwMS) and 13 healthy controls) performing 6 MW tests. Compared with existing methods, the causality analysis provided better discrimination between healthy controls and PwMS and a deeper understanding of MS disease impact on mobility.

[1]  G. Johansson.  Visual perception of biological motion and a model for its analysis , 1973 .

[2]  David C. Burr,et al.  Seeing biological motion , 1998, Nature.

[3]  Suzanne G. Leveille,et al.  Upper and lower limb muscle power relationships in mobility-limited older adults. , 2005, The journals of gerontology. Series A, Biological sciences and medical sciences.

[4]  Jeffrey A. Cohen,et al.  Evaluation of the six-minute walk in multiple sclerosis subjects and healthy controls , 2008, Multiple sclerosis.

[5]  K. Müller,et al.  Robustly estimating the flow direction of information in complex physical systems. , 2007, Physical review letters.

[6]  Kenneth Meijer,et al.  Activity identification using body-mounted sensors—a review of classification techniques , 2009, Physiological measurement.

[7]  John Lach,et al.  TEMPO 3.1: A Body Area Sensor Network Platform for Continuous Movement Assessment , 2009, 2009 Sixth International Workshop on Wearable and Implantable Body Sensor Networks.

[8]  Toyoaki Nishida,et al.  Mining Causal Relationships in Multidimensional Time Series , 2010, Smart Information and Knowledge Management.

[9]  S. Beer,et al.  Assessment of gait parameters and fatigue in MS patients during inpatient rehabilitation: a pilot trial , 2011, Journal of Neurology.

[10]  Andreas Ziehe,et al.  Comparison of Granger Causality and Phase Slope Index , 2008, NIPS Causality: Objectives and Assessment.

[11]  Taeyoung Kim,et al.  Characterizing and minimizing synchronization and calibration errors in inertial body sensor networks , 2010, BODYNETS.

[12]  Isabelle Guyon,et al.  Causality : Objectives and Assessment , 2010 .

[13]  Aapo Hyvärinen,et al.  Estimation of a Structural Vector Autoregression Model Using Non-Gaussianity , 2010, J. Mach. Learn. Res..

[14]  Jan Rueterbories,et al.  Methods for gait event detection and analysis in ambulatory systems. , 2010, Medical engineering & physics.

[15]  Maik C. Stüttgen,et al.  Computation of measures of effect size for neuroscience data sets , 2011, The European journal of neuroscience.

[16]  F. Horak,et al.  Body-worn motion sensors detect balance and gait deficits in people with multiple sclerosis who have normal walking speed. , 2012, Gait & posture.

[17]  L. Craighero,et al.  Leadership in Orchestra Emerges from the Causal Relationships of Movement Kinematics , 2012, PloS one.

[18]  Vladimir Pavlovic,et al.  Sparse Granger causality graphs for human action classification , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[19]  Tao Liu,et al.  Gait Analysis Using Wearable Sensors , 2012, Sensors.

[20]  Shanshan Chen,et al.  Aiding diagnosis of normal pressure hydrocephalus with enhanced gait feature separability , 2012, Wireless Health.

[21]  Chong-Wah Ngo,et al.  Trajectory-Based Modeling of Human Actions with Motion Reference Points , 2012, ECCV.

[22]  Gracián Triviño,et al.  Linguistic description of the human gait quality , 2013, Eng. Appl. Artif. Intell..

[23]  Ilaria Carpinella,et al.  Quantitative assessment of upper limb motor function in Multiple Sclerosis using an instrumented Action Research Arm Test , 2014, Journal of NeuroEngineering and Rehabilitation.

[24]  Manuela Galli,et al.  Summary measures for clinical gait analysis: a literature review. , 2014, Gait & posture.

[25]  Begonya Garcia-Zapirain,et al.  Gait Analysis Methods: An Overview of Wearable and Non-Wearable Systems, Highlighting Clinical Applications , 2014, Sensors.

[26]  K. R. Ramakrishnan,et al.  A Cause and Effect Analysis of Motion Trajectories for Modeling Actions , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  F. Horak,et al.  Body-worn sensors capture variability, but not decline, of gait and balance measures in multiple sclerosis over 18 months. , 2014, Gait & posture.

[28]  Hermie Hermens,et al.  Optimal Sensor Placement for Measuring Physical Activity with a 3D Accelerometer , 2014, Sensors.

[29]  Bernt Schiele,et al.  A tutorial on human activity recognition using body-worn inertial sensors , 2014, CSUR.

[30]  Yanjun Qi,et al.  Piecewise Linear Dynamical Model for Actions Clustering from Inertial Body Sensors with Considerations of Human Factors , 2014, BODYNETS.

[31]  Nicholas D. Lane,et al.  Can Deep Learning Revolutionize Mobile Sensing? , 2015, HotMobile.

[32]  Yanjun Qi,et al.  Causal analysis of inertial body sensors for enhancing gait assessment separability towards multiple sclerosis diagnosis , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[33]  Barry R. Greene,et al.  Assessment and Classification of Early-Stage Multiple Sclerosis With Inertial Sensors: Comparison Against Clinical Measures of Disease State , 2015, IEEE Journal of Biomedical and Health Informatics.