General method for automated feature extraction and selection and its application for gender classification and biomechanical knowledge discovery of sex differences in spinal posture during stance and gait

Modern technologies enable to capture multiple biomechanical parameters often resulting in relational data. The current work proposes a generally applicable method comprising automated feature extraction, ensemble feature selection and classification to best capture the potentials of the data also for generating new biomechanical knowledge. Its benefits are demonstrated in the concrete biomechanically and medically relevant use case of gender classification based on spinal data for stance and gait. Very good results for accuracy were obtained using gait data. Dynamic movements of the lumbar spine in sagittal and frontal plane and of the pelvis in frontal plane best map gender differences.

[1]  D Casey Kerrigan,et al.  Gender differences in pelvic motions and center of mass displacement during walking: stereotypes quantified. , 2002, Journal of women's health & gender-based medicine.

[2]  D. B. Lucas,et al.  An in vivo study of the axial rotation of the human thoracolumbar spine. , 1967, The Journal of bone and joint surgery. American volume.

[3]  Bertram Taetz,et al.  Towards an Inertial Sensor-Based Wearable Feedback System for Patients after Total Hip Arthroplasty: Validity and Applicability for Gait Classification with Gait Kinematics-Based Features , 2019, Sensors.

[4]  David R. Bowden,et al.  Sex differences in whole body gait kinematics at preferred speeds. , 2015, Gait & posture.

[5]  Verónica Bolón-Canedo,et al.  A review of feature selection methods on synthetic data , 2013, Knowledge and Information Systems.

[6]  M P Kadaba,et al.  Measurement of lower extremity kinematics during level walking , 1990, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[7]  Angkoon Phinyomark,et al.  Analysis of Big Data in Gait Biomechanics: Current Trends and Future Directions , 2017, Journal of Medical and Biological Engineering.

[8]  Nachiappan Chockalingam,et al.  Multi-segment kinematic model to assess three-dimensional movement of the spine and back during gait , 2016, Prosthetics and orthotics international.

[9]  Melanie Hilario,et al.  Knowledge and Information Systems , 2007 .

[10]  V. Cyril Raj,et al.  Accurate and Stable Feature Selection Powered by Iterative Backward Selection and Cumulative Ranking Score of Features , 2015 .

[11]  Raquel Lucas,et al.  Sagittal Standing Posture, Back Pain, and Quality of Life Among Adults From the General Population: A Sex-Specific Association , 2014, Spine.

[12]  Rossitza Setchi,et al.  Feature selection using Joint Mutual Information Maximisation , 2015, Expert Syst. Appl..

[13]  J. Sarrafzadeh,et al.  Gender-Related Differences in Reliability of Thorax, Lumbar, and Pelvis Kinematics During Gait in Patients With Non-specific Chronic Low Back Pain , 2018, Annals of rehabilitation medicine.

[14]  Kengo Yamamoto,et al.  Sagittal lumbar and pelvic alignment in the standing and sitting positions , 2012, Journal of orthopaedic science : official journal of the Japanese Orthopaedic Association.

[15]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[16]  Antonius Rohlmann,et al.  Age-Related Loss of Lumbar Spinal Lordosis and Mobility – A Study of 323 Asymptomatic Volunteers , 2014, PloS one.

[17]  V P Stokes,et al.  Rotational and translational movement features of the pelvis and thorax during adult human locomotion. , 1989, Journal of biomechanics.

[18]  Cara M. Wall-Scheffler,et al.  Gender differences in walking and running on level and inclined surfaces. , 2008, Clinical biomechanics.

[19]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[20]  Jeffrey M. Hausdorff,et al.  Sex-specific differences in gait patterns of healthy older adults: results from the Baltimore Longitudinal Study of Aging. , 2011, Journal of biomechanics.

[21]  Verónica Bolón-Canedo,et al.  On developing an automatic threshold applied to feature selection ensembles , 2018, Inf. Fusion.

[22]  Allison Bailey,et al.  Risk factors for low back pain in women: still more questions to be answered. , 2009, Menopause.

[23]  Jing Xu,et al.  An ensemble feature selection method for high-dimensional data based on sort aggregation , 2019, Systems Science & Control Engineering.

[24]  Manoj Mohan,et al.  Sex Differences in the Spine , 2019, Current Physical Medicine and Rehabilitation Reports.

[25]  J. Schröder,et al.  Referenzdaten in der Wirbelsäulenformanalyse , 2011, Manuelle Medizin.

[26]  Huan Liu,et al.  Toward integrating feature selection algorithms for classification and clustering , 2005, IEEE Transactions on Knowledge and Data Engineering.

[27]  Moreno D'Amico,et al.  Normative 3D opto-electronic stereo-photogrammetric sagittal alignment parameters in a young healthy adult population , 2018, PloS one.

[28]  Walter Rapp,et al.  Evaluation of a Novel Spine and Surface Topography System for Dynamic Spinal Curvature Analysis during Gait , 2013, PloS one.

[29]  M. Panjabi,et al.  Normal motion of the lumbar spine as related to age and gender , 2004, European Spine Journal.

[30]  Eric Fleury,et al.  Tracking Clinical Staff Behaviors in an Operating Room , 2019, Sensors.

[31]  O. Kwon,et al.  Gender differences in three dimensional gait analysis data from 98 healthy Korean adults. , 2004, Clinical biomechanics.

[32]  Jean-Michel Poggi,et al.  Variable selection using random forests , 2010, Pattern Recognit. Lett..

[33]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[34]  Danilo Bzdok,et al.  Points of Significance: Statistics versus machine learning , 2018, Nature Methods.

[35]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[36]  J. Allum,et al.  The influence of walking speed and gender on trunk sway for the healthy young and older adults. , 2010, Age and ageing.

[37]  Daniel Schmitt,et al.  Adaptive value of ambling gaits in primates and other mammals , 2006, Journal of Experimental Biology.

[38]  A. Gipsman,et al.  Evaluating the Reproducibility of Motion Analysis Scanning of the Spine during Walking , 2014, Advances in medicine.

[39]  Verónica Bolón-Canedo,et al.  Ensembles for feature selection: A review and future trends , 2019, Inf. Fusion.

[40]  R. Fillingim,et al.  Sex, gender, and pain: a review of recent clinical and experimental findings. , 2009, The journal of pain : official journal of the American Pain Society.

[41]  Mohamed Limam,et al.  Ensemble feature selection for high dimensional data: a new method and a comparative study , 2017, Advances in Data Analysis and Classification.

[42]  Verónica Bolón-Canedo,et al.  Ensemble feature selection: Homogeneous and heterogeneous approaches , 2017, Knowl. Based Syst..

[43]  Samuel Schülein,et al.  The Validity of Rasterstereography: A Systematic Review , 2015, Orthopedic reviews.

[44]  Roongtiwa Vachalathiti,et al.  Age, gender and speed effects on spinal kinematics during walking , 1997 .