Abstract
Cumulative exposure to head impacts during contact sports can elicit potentially deleterious brain white matter alterations in young athletes. Head impact exposure is commonly quantified using wearable sensors; however, these sensors tend to overestimate the number of true head impacts that occur and may obfuscate potential relationships with longitudinal brain changes. The purpose of this study was to examine whether data-driven filtering of head impact exposure using machine learning classification could produce more accurate quantification of exposure and whether this would reveal more pronounced relationships with longitudinal brain changes. Season-long head impact exposure was recorded for 22 female high school soccer athletes and filtered using three methods—threshold-based, heuristic filtering, and machine learning (ML) classification. The accuracy of each method was determined using simultaneous video recording of a subset of the sensor-recorded impacts, which was used to confirm which sensor-recorded impacts corresponded with true head impacts and the ability of each method to detect the true impacts. Each filtered dataset was then associated with the athletes’ pre- and post-season MRI brain scans to reveal longitudinal white matter changes. The threshold-based, heuristic, and ML approaches achieved 22.0% accuracy, 44.6%, and 83.5% accuracy, respectively. ML classification also revealed significant longitudinal brain white matter changes, with negative relationships observed between head impact exposure and reductions in mean and axial diffusivity and a positive relationship observed between exposure and fractional anisotropy (all p < 0.05).
Similar content being viewed by others
Abbreviations
- Unit:
-
Description
- AD:
-
Axial diffusivity; a DTI measure of brain WM integrity
- CG:
-
Control group; the non-experimental group in the present study
- DTI:
-
Diffusion tensor imaging
- FA:
-
Fractional anisotropy; a DTI measure of brain WM integrity
- MD:
-
Mean diffusivity; a DTI measure of brain WM integrity
- ML:
-
Machine learning
- MRI:
-
Magnetic resonance imaging
- RD:
-
Radial diffusivity; a DTI measure of brain WM integrity
- ROC:
-
Receiver operating characteristic
- mTBI:
-
Sports-related mild traumatic brain injury
- SCI:
-
Sub-concussive head impacts, or head impacts that do not result in overt clinical symptoms that lead to a clinical diagnosis of concussion
- SVM:
-
Support vector machine
- TG:
-
Training group; the experimental group in the present study
- WM:
-
(Brain) white matter
- XGBoost:
-
Extreme gradient boosted classification model
References
Allison, M. A., Y. S. Kang, J. H. Bolte, M. R. Maltese, and K. B. Arbogast. Validation of a helmet-based system to measure head impact biomechanics in ice hockey. Med. Sci. Sports Exerc. 46:115–123, 2014.
Bahrami, N., D. Sharma, S. Rosenthal, E. M. Davenport, J. E. Urban, B. Wagner, Y. Jung, C. G. Vaughan, G. A. Gioia, J. D. Stitzel, C. T. Whitlow, and J. A. Maldjian. Subconcussive head impact exposure and white matter tract changes over a single season of youth football. Radiology 281:919–926, 2016.
Bazarian, J. J., T. Zhu, B. Blyth, A. Borrino, and J. Zhong. Subject-specific changes in brain white matter on diffusion tensor imaging after sports-related concussion. Magn. Reson. Imaging 30:171–180, 2012.
Bazarian, J. J., T. Zhu, J. Zhong, D. Janigro, E. Rozen, A. Roberts, H. Javien, K. Merchant-Borna, B. Abar, and E. G. Blackman. Persistent, long-term cerebral white matter changes after sports-related repetitive head impacts. PLoS ONE 9:e94734, 2014.
Broglio, S. P., D. Martini, L. Kasper, J. T. Eckner, and J. S. Kutcher. Estimation of head impact exposure in high school football: implications for regulating contact practices. Am. J. Sports Med. 41:2877–2884, 2013.
Broglio, S. P., R. M. Williams, K. L. O’Connor, and J. Goldstick. Football players’ head-impact exposure after limiting of full-contact practices. J. Athl. Train. 51:511–518, 2016.
Brolinson, P. G., S. Manoogian, D. McNeely, M. Goforth, R. Greenwald, and S. Duma. Analysis of linear head accelerations from collegiate football impacts. Curr. Sports Med. Rep. 5:23–28, 2006.
Chen, T., and C. Guestrin. XGBoost: reliable large-scale tree boosting system. Paper Presented at Proceedings of the 22nd SIGKDD Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016.
Chiang, M. C., M. Barysheva, A. D. Lee, S. Madsen, A. D. Klunder, A. W. Toga, K. L. McMahon, G. I. de Zubicaray, M. Meredith, M. J. Wright, A. Srivastava, N. Balov, and P. M. Thompson. Brain fiber architecture, genetics, and intelligence: a high angular resolution diffusion imaging (HARDI) study. Med. Image Comput. Comput. Assist. Interv. 11:1060–1067, 2008.
Cortes, N., A. E. Lincoln, G. D. Myer, L. Hepburn, M. Higgins, M. Putukian, and S. V. Caswell. Video analysis verification of head impact events measured by wearable sensors. Am. J. Sports Med. 45:2379–2387, 2017.
Davenport, E. M., C. T. Whitlow, J. E. Urban, M. A. Espeland, Y. Jung, D. A. Rosenbaum, G. A. Gioia, A. K. Powers, J. D. Stitzel, and J. A. Maldjian. Abnormal white matter integrity related to head impact exposure in a season of high school varsity football. J. Neurotrauma 31:1617–1624, 2014.
Dudley, J., W. Yuan, J. Diekfuss, K. D. Barber Foss, C. A. DiCesare, M. Altaye, K. Logan, J. L. Leach, and G. D. Myer. Internal jugular vein compression applied during competitive female soccer season preserves functional and structural connectome organization. Brain Connect. 1000:1000, 2020. https://doi.org/10.1089/brain.2019.0729.
Duma, S. M., S. J. Manoogian, W. R. Bussone, P. G. Brolinson, M. W. Goforth, J. J. Donnenwerth, R. M. Greenwald, J. J. Chu, and J. J. Crisco. Analysis of real-time head accelerations in collegiate football players. Clin. J. Sport Med. 15:3–8, 2005.
Friedman, J. H. Greedy function approximation: a gradient boosting machine. Ann. Stat. 29:1189–1232, 2001.
Kindschi, K., M. Higgins, A. Hillman, G. Penczek, and A. Lincoln. Video analysis of high-magnitude head impacts in men’s collegiate lacrosse. BMJ Open Sport Exerc. Med. 3:e000165, 2017.
Kuo, C., L. Wu, J. Loza, D. Senif, S. C. Anderson, and D. B. Camarillo. Comparison of video-based and sensor-based head impact exposure. PLoS ONE 13:e0199238, 2018.
Kuzminski, S. J., M. D. Clark, M. A. Fraser, C. C. Haswell, R. A. Morey, C. Liu, K. R. Choudhury, K. M. Guskiewicz, and J. R. Petrella. White matter changes related to subconcussive impact frequency during a single season of high school football. AJNR Am. J. Neuroradiol. 39:245–251, 2018.
Langlois, J. A., W. Rutland-Brown, and M. M. Wald. The epidemiology and impact of traumatic brain injury: a brief overview. J. Head Trauma Rehabil. 21:375–378, 2006.
Livne, M., J. K. Boldsen, I. K. Mikkelsen, J. B. Fiebach, J. Sobesky, and K. Mouridsen. Boosted tree model reforms multimodal magnetic resonance imaging infarct prediction in acute stroke. Stroke 49:912–918, 2018.
Lyons, T. J., M. Caruana, and T. Lévy. Differential Equations Driven by Rough Paths, Vol. 1908. Heidelberg: Springer, pp. 81–93, 2007.
Marar, M., N. M. McIlvain, S. K. Fields, and R. D. Comstock. Epidemiology of concussions among United States high school athletes in 20 sports. Am. J. Sport Med. 40:747–755, 2012.
Mayinger, M. C., K. Merchant-Borna, J. Hufschmidt, M. Muehlmann, I. R. Weir, B. S. Rauchmann, M. E. Shenton, I. K. Koerte, and J. J. Bazarian. White matter alterations in college football players: a longitudinal diffusion tensor imaging study. Brain Imaging Behav. 12:44–53, 2018.
McAllister, T., and M. McCrea. Long-term cognitive and neuropsychiatric consequences of repetitive concussion and head-impact exposure. J. Athl. Train. 52:309–317, 2017.
McCuen, E., D. Svaldi, K. Breedlove, N. Kraz, B. Cummiskey, E. L. Breedlove, J. Traver, K. F. Desmond, R. E. Hannemann, E. Zanath, A. Guerra, L. Leverenz, T. M. Talavage, and E. A. Nauman. Collegiate women’s soccer players suffer greater cumulative head impacts than their high school counterparts. J. Biomech. 48:3720–3723, 2015.
Mori, S., K. Oishi, H. Y. Jiang, L. Jiang, X. Li, K. Akhter, K. G. Hua, A. V. Faria, A. Mahmood, R. Woods, A. W. Toga, G. B. Pike, P. R. Neto, A. Evans, J. Y. Zhang, H. Huang, M. I. Miller, P. Zijl, and J. Mazziotta. Stereotaxic white matter atlas based on diffusion tensor imaging in an ICBM template. Neuroimage. 40:570–582, 2008.
Myer, G. D., W. Yuan, K. D. Barber Foss, D. Smith, M. Altaye, A. Reches, J. Leach, A. W. Kiefer, J. C. Khoury, M. Weiss, S. Thomas, C. Dicesare, J. Adams, P. J. Gubanich, A. Geva, J. F. Clark, W. P. Meehan, III, J. P. Mihalik, and D. Krueger. The effects of external jugular compression applied during head impact exposure on longitudinal changes in brain neuroanatomical and neurophysiological biomarkers: a preliminary investigation. Front. Neurol. 7:74, 2016.
Myer, G. D., W. Yuan, K. D. Barber Foss, S. Thomas, D. Smith, J. Leach, A. W. Kiefer, C. Dicesare, J. Adams, P. J. Gubanich, K. Kitchen, D. K. Schneider, D. Braswell, D. Krueger, and M. Altaye. Analysis of head impact exposure and brain microstructure response in a season-long application of a jugular vein compression collar: a prospective, neuroimaging investigation in American football. Br. J. Sports Med. 50:1276–1285, 2016.
Myer, G. D., K. Barber-Foss, S. Thomas, R. Galloway, C. A. DiCesare, J. Dudley, B. Gadd, J. Leach, D. Smith, P. Gubanich, W. P. Meehan, III, M. Altaye, P. Lavin, and W. Yuan. Altered brain microstructure in association with repetitive subconcussive head impacts and the potential protective effect of jugular vein compression: a longitudinal study of female soccer athletes. Br. J. Sports Med. 53:1359–1551, 2019.
Nishio, M., M. Nishizawa, O. Sugiyama, R. Kojima, M. Yakami, T. Kuroda, and K. Togashi. Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization. PLoS ONE 13:e0195875, 2018.
Pfaller, A. Y., M. A. Brooks, S. Hetzel, and T. A. McGuine. Effect of a new rule limiting full contact practice on the incidence of sport-related concussion in high school football players. Am. J. Sports Med. 47:2294–2299, 2019.
Press, J. N., and S. Rowson. Quantifying head impact exposure in collegiate women’s soccer. Clin. J. Sport Med. 27:104–110, 2017.
Schneider, D. K., R. Galloway, J. J. Bazarian, J. A. Diekfuss, J. Dudley, J. L. Leach, R. Mannix, T. M. Talavage, W. Yuan, and G. D. Myer. Diffusion tensor imaging in athletes sustaining repetitive head impacts: a systematic review of prospective studies. J. Neurotrauma 36:2831–2849, 2019.
Smith, S. M., M. Jenkinson, H. Johansen-Berg, D. Rueckert, T. E. Nichols, C. E. Mackay, K. E. Watkins, O. Ciccarelli, M. Z. Cader, P. M. Matthews, and T. E. Behrens. Tract-based spatial statistics: voxelwise analysis of multi-subject diffusion data. NeuroImage. 31:1487–1505, 2006.
Smith, S. M., and T. E. Nichols. Threshold-free cluster enhancement: addressing problems of smoothing, threshold dependence and localisation in cluster inference. Neuroimage. 44:83–98, 2009.
Wallace, E. J., J. L. Mathias, and L. Ward. Diffusion tensor imaging changes following mild, moderate and severe adult traumatic brain injury: a meta-analysis. Brain Imaging Behav. 12:1607–1621, 2018.
Wu, L. C., L. Zarnescu, V. Nangia, B. Cam, and D. B. Camarillo. A head impact detection system using SVM classification and proximity sensing in an instrumented mouthguard. IEEE Trans. Biomed. Eng. 61:2659–2668, 2014.
Wu, L. C., V. Nangia, K. Bui, B. Hammoor, M. Kurt, F. Hernandez, C. Kuo, and D. B. Camarillo. In vivo evaluation of wearable head impact sensors. Ann. Biomed. Eng. 44:1234–1245, 2016.
Wu, L. C., C. Kuo, J. Loza, M. Kurt, K. Laksari, L. Z. Yanez, D. Senif, S. C. Anderson, L. E. Miller, J. E. Urban, J. D. Stitzel, and D. B. Camarillo. Detection of American football head impacts using biomechanical features and support vector machine classification. Sci. Rep. 8:855, 2017.
Acknowledgments
The authors would acknowledge the coaching and training staff from Seton High School: Ron Quinn, Lisa Larosa, Holly Laiveling and the entire soccer coaching staff, athletic trainer Cindy Busse, the Seton administration and athletic director Wendy Smith; and from Madeira High School: Dan Brady, athletic trainer Glenna Knapp, athletic director Joe Kimling, and principal David Kennedy for their support and assistance to conduct this study. The authors would also like to thank Danielle Reddington and Casey McCall for their daily accelerometer tracking and work in reviewing video and coding impacts, as well as Lacey Haas, Brynne Williams, Kaley Bridgewater and Matt Lanier in the Cincinnati Children’s Hospital Imaging Research Center as their support made this study possible. Finally, the authors would also like to acknowledge that, while Q30 Innovations, LLC provided funding for the parent study, no funding sources were included for the present study.
Author information
Authors and Affiliations
Corresponding author
Additional information
Associate Editor Jillian Urban oversaw the review of this article.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
DiCesare, C.A., Green, B., Yuan, W. et al. Machine Learning Classification of Verified Head Impact Exposure Strengthens Associations with Brain Changes. Ann Biomed Eng 48, 2772–2782 (2020). https://doi.org/10.1007/s10439-020-02662-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10439-020-02662-2