Abstract
A percentage of the population suffers prolonged and persistent post-concussion symptoms (PCS) following average head injuries or develops severe neurological dysfunction following minor head trauma. Genetic variants that may contribute to individual response to head trauma have been investigated in some studies, but to date none have explored the use of machine learning (ML) methods with genomic data to specifically explore outcomes of head trauma. Whole exome sequencing (WES) was completed for three groups of individuals (N = 60): (a) 16 individuals with severe neurological responses to minor head trauma, (b) 26 individuals with persistent PCS and (c) 18 individuals with normal recovery from concussion or mTBI. Gradient boosted tree algorithms were applied to the data using XGBoost. By using variants with CADD scores above 15 in the training set (randomly sampled 70%), we identified signatures that accurately distinguish to accurately distinguish the test groups with an average area under the curve (AUC) of 0.8 (SE = 0.019). Metrics including positive and negative prediction values, as well as kappa were all within acceptable range to support the prediction accuracy. This study illustrates how ML methods in combination with WES data have the potential to predict severe or prolonged responses to head trauma from healthy recovery.
Key messages
-
Linear association analysis has been inconclusive in concussion genetics.
-
Non-linear methods as boosted trees can offer better insights in small samples.
-
Strong discrimination trends can be achieved from exome data of cases and controls.
Similar content being viewed by others
Availability of data and material
Summary-level data is available at the author’s discretion.
Code availability
All the codes used for this study are freely available upon request.
References
Messina R, Filippi M, Goadsby PJ (2018) Recent advances in headache neuroimaging. Curr Opin Neurol 31(4):379–385. https://doi.org/10.1097/wco.0000000000000573
Rocca MA, Ceccarelli A, Falini A, Colombo B, Tortorella P, Bernasconi L, Comi G, Scotti G, Filippi M (2006) Brain gray matter changes in migraine patients with T2-visible lesions: a 3-T MRI study. Stroke 37(7):1765–1770. https://doi.org/10.1161/01.STR.0000226589.00599.4d
Iverson GL, Gardner AJ, Terry DP, Ponsford JL, Sills AK, Broshek DK, Solomon GS (2017) Predictors of clinical recovery from concussion: a systematic review. Br J Sports Med 51(12):941–948. https://doi.org/10.1136/bjsports-2017-097729
McDevitt J, Krynetskiy E (2017) Genetic findings in sport-related concussions: potential for individualized medicine? Concussion (London, England) 2(1):CNC26–CNC26. https://doi.org/10.2217/cnc-2016-0020
Coyle HL, Ponsford J, Hoy KE (2018) Understanding individual variability in symptoms and recovery following mTBI: a role for TMS-EEG? Neurosci Biobehav Rev 92:140–149. https://doi.org/10.1016/j.neubiorev.2018.05.027
Johnson B, Zhang K, Gay M, Horovitz S, Hallett M, Sebastianelli W, Slobounov S (2012) Alteration of brain default network in subacute phase of injury in concussed individuals: resting-state fMRI study. Neuroimage 59(1):511–518. https://doi.org/10.1016/j.neuroimage.2011.07.081. Epub 2011 Aug 7. PMID: 21846504; PMCID: PMC3196274
Yang J et al (2010) Common SNPs explain a large proportion of the heritability for human height. Nat Genet 42(7):565
Romagnoni A, Jégou S, Van Steen K, Wainrib G, Hugot J-P (2019) Comparative performances of machine learning methods for classifying Crohn disease patients using genome-wide genotyping data. Sci Rep 9(1):1–18
González-Recio O, Jiménez-Montero J, Alenda R (2013) The gradient boosting algorithm and random boosting for genome-assisted evaluation in large data sets. J Dairy Sci 96(1):614–624
Auffray C, Griffin JL, Khoury MJ, Lupski JR, Schwab M (2019) Ten years of Genome Medicine. Genome Med 11(1):7. https://doi.org/10.1186/s13073-019-0618-x
Ashley EA (2015) The precision medicine initiative: a new national effort. JAMA 313(21):2119–2120. https://doi.org/10.1001/jama.2015.3595
Trakadis YJ, Sardaar S, Chen A, Fulginiti V, Krishnan A (2019) Machine learning in schizophrenia genomics, a case-control study using 5,090 exomes. Am J Med Genet B Neuropsychiatr Genet 180(2):103–112. https://doi.org/10.1002/ajmg.b.32638
Er F, Iscen P, Sahin S, Çinar N, Karsidag S, Goularas D (2017) Distinguishing age-related cognitive decline from dementias: a study based on machine learning algorithms. J Clin Neurosci 42:186–192. https://doi.org/10.1016/j.jocn.2017.03.021
Kassahun Y, Perrone R, De Momi E, Berghöfer E, Tassi L, Canevini MP, Spreafico R, Ferrigno G, Kirchner F (2014) Automatic classification of epilepsy types using ontology-based and genetics-based machine learning. Artif Intell Med 61(2):79–88. https://doi.org/10.1016/j.artmed.2014.03.001
Pare G, Mao S, Deng WQ (2017) A machine-learning heuristic to improve gene score prediction of polygenic traits. Sci Rep 7(1):1–11
Ibrahim O, Sutherland HG, Maksemous N, Smith R, Haupt LM, Griffiths LR (2020) Exploring neuronal vulnerability to head trauma using a whole exome approach. J Neurotrauma 37(17):1870–1879. https://doi.org/10.1089/neu.2019.6962
Li H (2011) A statistical framework for SNP calling, mutation discovery, association mapping and population genetical parameter estimation from sequencing data. Bioinformatics (Oxford, England) 27(21):2987–2993. https://doi.org/10.1093/bioinformatics/btr509
Danecek P et al (2011) The variant call format and VCFtools. Bioinformatics 27(15):2156–2158. https://doi.org/10.1093/bioinformatics/btr330
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining 785–794. https://doi.org/10.1145/2939672.2939785. PMID: 30767786; PMCID: PMC6376775.KDD
Wray NR, Yang J, Goddard ME, Visscher PM (2010) The genetic interpretation of area under the ROC curve in genomic profiling. PLoS Genet 6(2):e1000864. https://doi.org/10.1371/journal.pgen.1000864
Park JH, Shin SD, Song KJ, Hong KJ, Ro YS, Choi JW, Choi SW (2019) Prediction of good neurological recovery after out-of-hospital cardiac arrest: a machine learning analysis. Resuscitation 142:127–135. https://doi.org/10.1016/j.resuscitation.2019.07.020
Giza CC et al (2013) Summary of evidence-based guideline update: evaluation and management of concussion in sports: report of the Guideline Development Subcommittee of the American Academy of Neurology. Neurology 80(24):2250–2257. https://doi.org/10.1212/WNL.0b013e31828d57dd
Maksemous N et al (2019) Targeted next generation sequencing identifies a genetic spectrum of DNA variants in patients with hemiplegic migraine. Cephalalgia Rep 2:2515816319881630
Sweadner KJ, Toro C, Whitlow CT, Snively BM, Cook JF, Ozelius LJ, Markello TC, Brashear A (2016) ATP1A3 mutation in adult rapid-onset ataxia. PLoS ONE 11(3):e0151429–e0151429. https://doi.org/10.1371/journal.pone.0151429
Fadó R, Rodríguez-Rodríguez R, Casals N (2021) The return of malonyl-CoA to the brain: cognition and other stories. Prog Lipid Res 81:101071. https://doi.org/10.1016/j.plipres.2020.101071
Zhang L et al (2015) Mitochondria-focused gene expression profile reveals common pathways and CPT1B dysregulation in both rodent stress model and human subjects with PTSD. Transl Psychiatry 5(6):e580–e580
Chung RS, Leung YK, Butler CW, Chen Y, Eaton ED, Pankhurst MW, West AK, Guillemin GJ (2009) Metallothionein treatment attenuates microglial activation and expression of neurotoxic quinolinic acid following traumatic brain injury. Neurotox Res 15(4):381–389. https://doi.org/10.1007/s12640-009-9044-y
Zaręba N, Kepinska M (2020) The function of transthyretin complexes with metallothionein in Alzheimer’s disease. Int J Mol Sci 21(23):9003. https://doi.org/10.3390/ijms21239003
Daneshjou R et al (2017) Working toward precision medicine: predicting phenotypes from exomes in the critical assessment of genome interpretation (CAGI) challenges. Hum Mutat 38(9):1182–1192. https://doi.org/10.1002/humu.23280
Ben-David A (2008) Comparison of classification accuracy using Cohen’s weighted kappa. Expert Syst Appl 34(2):825–832
Seigel DG, Podgo MJ, Remaley NA (1992) Acceptable values of kappa for comparison of two groups. Am J Epidemiol 135(5):571–578
Rasmussen AH, Olofsson I, Chalmer MA, Olesen J, Hansen TF (2020) Higher burden of rare frameshift indels in genes related to synaptic transmission separate familial hemiplegic migraine from common types of migraine. J Med Genet 57(9):610–616. https://doi.org/10.1136/jmedgenet-2019-106640
Funding
This work was supported by The Assistant Secretary of Defence for Health Affairs endorsed by the Department of Defence, through FY 2018 Peer Reviewed Medical Research Program Discovery Award, under Award No. W81XWH1910098. Opinions, interpretations, conclusions and recommendations are those of the author and are not necessarily endorsed by the Department of Defense. This work was supported by the National Health and Medical Research Council through grant GNT1122387—Identifying novel gene mutations for molecular diagnosis of familial hemiplegic migraine.
Author information
Authors and Affiliations
Contributions
Conceptualization: Omar Ibrahim, Lyn R. Griffiths; methodology: Omar Ibrahim, Neven Maksemous, Rodney A. Lea, Heidi G. Sutherland; formal analysis and investigation: Omar Ibrahim, Rod A Lea; writing—original draft preparation: Omar Ibrahim; writing—review and editing: Omar Ibrahim, Heidi G. Sutherland, Rodney A. Lea, Fatima Nasrallah, Neven Maksemous, Robert A. Smith, Larisa M. Haupt, Lyn R. Griffiths; funding acquisition: Lyn R. Griffiths; resources: Larisa M. Haupt, Fatima Nasrallah; supervision: Lyn R. Griffiths, Larisa M. Haupt, Heidi G. Sutherland.
Corresponding author
Ethics declarations
Ethics approval
Ethical approval for this project was provided by the Queensland University of Technology Human Research Ethics Committee (project approvals 1700000811 and 1800000611).
Consent to participate
All the participants provided appropriate consent for participation in the research under the terms of the ethical approval for this study.
Conflict of interest
The authors declare no competing interests.
Disclaimer
Opinions, interpretations, conclusions and recommendations are those of the author and are not necessarily endorsed by the Department of Defence.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ibrahim, O., Sutherland, H.G., Lea, R.A. et al. Discriminating head trauma outcomes using machine learning and genomics. J Mol Med 100, 303–312 (2022). https://doi.org/10.1007/s00109-021-02158-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00109-021-02158-z