Are Multilevel functional models the next step in sports biomechanics and wearable technology? A case study of Knee Biomechanics patterns in typical training sessions of recreational runners

Marcos Matabuena1,∗, Sherveen Riazati, Nick Caplan, Phil Hayes CiTIUS (Centro Singular de Investigación en Tecnoloxías Intelixentes), Universidade de Santiago de Compostela, Spain Biomechanics, Rehabilitation and Integrative Neuroscience (BRaIN), School of Medicine, University of Davis, United States Department of Sport and Exercise Sciences, School of Life Sciences, Northumbria University, Newcastle upon Tyne, United Kingdom ∗marcos.matabuena@usc.es

[1]  Philip Hoole,et al.  Mixed modeling for irregularly sampled and correlated functional data: Speech science applications. , 2017, The Journal of the Acoustical Society of America.

[2]  Bas Van Hooren,et al.  Real-time feedback by wearables in running: Current approaches, challenges and suggestions for improvements , 2019, Journal of sports sciences.

[3]  Christian Barton,et al.  Biomechanical Risk Factors Associated with Running-Related Injuries: A Systematic Review , 2019, Sports Medicine.

[4]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[5]  Antonio Cuevas,et al.  Variable selection in functional data classification: a maxima-hunting proposal , 2013, 1309.6697.

[6]  P. Reiss,et al.  Generalized reliability based on distances , 2019, Biometrics.

[7]  Jessilyn Dunn,et al.  Wearables and the medical revolution. , 2018, Personalized medicine.

[8]  Klaus-Robert Müller,et al.  Explaining the unique nature of individual gait patterns with deep learning , 2018, Scientific Reports.

[9]  C. Crainiceanu,et al.  Corrected Confidence Bands for Functional Data Using Principal Components , 2013, Biometrics.

[10]  Ciprian Crainiceanu,et al.  Longitudinal scalar-on-functions regression with application to tractography data. , 2013, Biostatistics.

[11]  Michael Ian Lambert,et al.  Measuring training load in sports. , 2010, International journal of sports physiology and performance.

[12]  Marcos Matabuena,et al.  An Improved Version of the Classical Banister Model to Predict Changes in Physical Condition , 2019, Bulletin of Mathematical Biology.

[13]  Jiawei Bai,et al.  Multilevel Matrix-Variate Analysis and its Application to Accelerometry-Measured Physical Activity in Clinical Populations , 2018, Journal of the American Statistical Association.

[14]  G. Robinson.  That BLUP is a Good Thing: The Estimation of Random Effects , 1991 .

[15]  Luca Pappalardo,et al.  Effective injury forecasting in soccer with GPS training data and machine learning , 2017, PloS one.

[16]  P. Devita,et al.  Risk factors and mechanisms of knee injury in runners. , 2008, Medicine and science in sports and exercise.

[17]  Ana-Maria Staicu,et al.  Functional Additive Mixed Models , 2012, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[18]  V. Vovk,et al.  E-values: Calibration, combination, and applications , 2019 .

[19]  M. B. Nebel,et al.  Quantifying the reliability of image replication studies: The image intraclass correlation coefficient (I2C2) , 2013, Cognitive, affective & behavioral neuroscience.

[20]  Ciprian M Crainiceanu,et al.  Multilevel sparse functional principal component analysis , 2014, Stat.

[21]  P. Vargha,et al.  A critical discussion of intraclass correlation coefficients. , 1997, Statistics in medicine.

[22]  J. Hertel,et al.  Validation of a Wearable Sensor for Measuring Running Biomechanics , 2018, Digital Biomarkers.

[23]  P. Hall,et al.  On properties of functional principal components analysis , 2006 .

[24]  Ana-Maria Staicu,et al.  Bootstrap‐based inference on the difference in the means of two correlated functional processes , 2012, Statistics in medicine.

[25]  Igor Fischer,et al.  A Decision Support System to Facilitate Identification of Musculoskeletal Impairments and Propose Recommendations Using Gait Analysis in Children With Cerebral Palsy , 2020, Frontiers in Bioengineering and Biotechnology.

[26]  Brian Caffo,et al.  Longitudinal High-Dimensional Principal Components Analysis with Application to Diffusion Tensor Imaging of Multiple Sclerosis. , 2015, The annals of applied statistics.

[27]  A. Coutts,et al.  Unpacking the Black Box: Applications and Considerations for Using GPS Devices in Sport. , 2017, International journal of sports physiology and performance.

[28]  Mark A Robinson,et al.  PCA of waveforms and functional PCA: A primer for biomechanics. , 2020, Journal of biomechanics.

[29]  Ana-Maria Staicu,et al.  Modeling Functional Data with Spatially Heterogeneous Shape Characteristics , 2012, Biometrics.

[30]  Manuel Febrero-Bande,et al.  Statistical Computing in Functional Data Analysis: The R Package fda.usc , 2012 .

[31]  Zhongyi Zhu,et al.  Regression Analysis of Asynchronous Longitudinal Functional and Scalar Data , 2020, Journal of the American Statistical Association.

[32]  Cai Li,et al.  Fast covariance estimation for sparse functional data , 2016, Statistics and Computing.

[33]  Hans-Georg Müller,et al.  Functional Data Analysis , 2016 .

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

[35]  S. Ibrahim.  Artificial intelligence for disparities in knee pain assessment , 2021, Nature medicine.

[36]  Raymond J Carroll,et al.  Selecting the Number of Principal Components in Functional Data , 2013, Journal of the American Statistical Association.

[37]  J. Giacino,et al.  Recovery of Consciousness and Functional Outcome in Moderate and Severe Traumatic Brain Injury. , 2021, JAMA neurology.

[38]  Andrew J Harrison,et al.  Functional data analysis of running kinematics in chronic Achilles tendon injury. , 2008, Medicine and science in sports and exercise.

[39]  Ciprian M Crainiceanu,et al.  Adaptive empirical pattern transformation (ADEPT) with application to walking stride segmentation. , 2019, Biostatistics.

[40]  S. Ghosh,et al.  Two sample hypothesis testing for functional data , 2013 .

[41]  B. Caffo,et al.  MULTILEVEL FUNCTIONAL PRINCIPAL COMPONENT ANALYSIS. , 2009, The annals of applied statistics.

[42]  Judd T. Kalkhoven,et al.  Training Load and Injury: Causal Pathways and Future Directions , 2021, Sports Medicine.

[43]  Angkoon Phinyomark,et al.  Kinematic gait patterns in healthy runners: A hierarchical cluster analysis. , 2015, Journal of biomechanics.

[44]  Raymond J Carroll,et al.  A Study of Mexican Free-Tailed Bat Chirp Syllables: Bayesian Functional Mixed Models for Nonstationary Acoustic Time Series , 2013, Journal of the American Statistical Association.

[45]  Caroline F Finch,et al.  Applications of functional data analysis: A systematic review , 2013, BMC Medical Research Methodology.

[46]  Christopher D. Chambers,et al.  Redefine statistical significance , 2017, Nature Human Behaviour.

[47]  I. Clay,et al.  Predicting Subjective Recovery from Lower Limb Surgery Using Consumer Wearables , 2020, Digital Biomarkers.

[48]  Alessia Pini,et al.  Test–retest reliability measures for curve data: an overview with recommendations and supplementary code , 2019, Sports biomechanics.

[49]  Piotr Kokoszka,et al.  Inference for Functional Data with Applications , 2012 .

[50]  M. Morris,et al.  The biomechanics and motor control of gait in Parkinson disease. , 2001, Clinical biomechanics.

[51]  Luo Xiao,et al.  Fast covariance estimation for high-dimensional functional data , 2013, Stat. Comput..

[52]  Milica Đurić-Jovičić,et al.  Artificial intelligence for assisting diagnostics and assessment of Parkinson’s disease—A review , 2019, Clinical Neurology and Neurosurgery.

[53]  L. F. Barrett,et al.  Superconsistent estimation of points of impact in non‐parametric regression with functional predictors , 2019, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[54]  N. Caplan,et al.  Fatigue Induced Changes in Muscle Strength and Gait Following Two Different Intensity, Energy Expenditure Matched Runs , 2020, Frontiers in Bioengineering and Biotechnology.

[55]  So Young Park,et al.  Simple fixed‐effects inference for complex functional models , 2016, Biostatistics.

[56]  Fabian Scheipl,et al.  Fast symmetric additive covariance smoothing , 2016, Comput. Stat. Data Anal..

[57]  Christos Davatzikos,et al.  Multilevel Functional Principal Component Analysis for High-Dimensional Data , 2011, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[58]  Ilaria Carpinella,et al.  Human kinematic, kinetic and EMG data during different walking and stair ascending and descending tasks , 2019, Scientific Data.

[59]  B. Van Gheluwe,et al.  Reliability and accuracy of biomechanical measurements of the lower extremities. , 2002, Journal of the American Podiatric Medical Association.

[60]  Matthew C Varley,et al.  Wearable Training-Monitoring Technology: Applications, Challenges, and Opportunities. , 2017, International journal of sports physiology and performance.

[61]  S. Fonseca,et al.  Complex systems approach for sports injuries: moving from risk factor identification to injury pattern recognition—narrative review and new concept , 2016, British Journal of Sports Medicine.

[62]  Wonyul Lee,et al.  Bayesian Semiparametric Functional Mixed Models for Serially Correlated Functional Data, With Application to Glaucoma Data , 2018, Journal of the American Statistical Association.

[63]  Timothy S. Church,et al.  Toward Exercise as Personalized Medicine , 2013, Sports Medicine.

[64]  Ciprian M Crainiceanu,et al.  Short-term variability in measures of glycemia and implications for the classification of diabetes. , 2007, Archives of internal medicine.

[65]  J. Ramsay,et al.  Introduction to Functional Data Analysis , 2007 .

[66]  Marina Vannucci,et al.  Wavelet-Based Nonparametric Modeling of Hierarchical Functions in Colon Carcinogenesis , 2003 .

[67]  Ciprian M Crainiceanu,et al.  Structured functional principal component analysis , 2013, Biometrics.

[68]  S. Delp,et al.  Personalization improves the biomechanical efficacy of foot progression angle modifications in individuals with medial knee osteoarthritis , 2020, medRxiv.

[69]  Reed Ferber,et al.  Gait biomechanics in the era of data science. , 2016, Journal of biomechanics.

[70]  Ana-Maria Staicu,et al.  Generalized Multilevel Functional Regression , 2009, Journal of the American Statistical Association.

[71]  Jukka-Pekka Kauppi,et al.  A hierarchical cluster analysis to determine whether injured runners exhibit similar kinematic gait patterns , 2020, Scandinavian journal of medicine & science in sports.

[72]  L. Ferrucci,et al.  Quantifying the lifetime circadian rhythm of physical activity: a covariate-dependent functional approach. , 2015, Biostatistics.

[73]  Ana-Maria Staicu,et al.  Fast methods for spatially correlated multilevel functional data. , 2010, Biostatistics.

[74]  Sean Williams,et al.  Monitoring the heart rate variability responses to training loads in competitive swimmers using a smartphone application and the Banister Impulse-Response model , 2020 .

[75]  Christian A. Clermont,et al.  Runners’ Perspectives on ‘Smart’ Wearable Technology and Its Use for Preventing Injury , 2020, Int. J. Hum. Comput. Interact..

[76]  B. Koes,et al.  Incidence and determinants of lower extremity running injuries in long distance runners: a systematic review , 2007, British Journal of Sports Medicine.

[77]  Cai Li,et al.  Fast covariance estimation for multivariate sparse functional data , 2018, Stat.