Uncovering precision phenotype-biomarker associations in traumatic brain injury using topological data analysis

Background Traumatic brain injury (TBI) is a complex disorder that is traditionally stratified based on clinical signs and symptoms. Recent imaging and molecular biomarker innovations provide unprecedented opportunities for improved TBI precision medicine, incorporating patho-anatomical and molecular mechanisms. Complete integration of these diverse data for TBI diagnosis and patient stratification remains an unmet challenge. Methods and findings The Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) Pilot multicenter study enrolled 586 acute TBI patients and collected diverse common data elements (TBI-CDEs) across the study population, including imaging, genetics, and clinical outcomes. We then applied topology-based data-driven discovery to identify natural subgroups of patients, based on the TBI-CDEs collected. Our hypothesis was two-fold: 1) A machine learning tool known as topological data analysis (TDA) would reveal data-driven patterns in patient outcomes to identify candidate biomarkers of recovery, and 2) TDA-identified biomarkers would significantly predict patient outcome recovery after TBI using more traditional methods of univariate statistical tests. TDA algorithms organized and mapped the data of TBI patients in multidimensional space, identifying a subset of mild TBI patients with a specific multivariate phenotype associated with unfavorable outcome at 3 and 6 months after injury. Further analyses revealed that this patient subset had high rates of post-traumatic stress disorder (PTSD), and enrichment in several distinct genetic polymorphisms associated with cellular responses to stress and DNA damage (PARP1), and in striatal dopamine processing (ANKK1, COMT, DRD2). Conclusions TDA identified a unique diagnostic subgroup of patients with unfavorable outcome after mild TBI that were significantly predicted by the presence of specific genetic polymorphisms. Machine learning methods such as TDA may provide a robust method for patient stratification and treatment planning targeting identified biomarkers in future clinical trials in TBI patients. Trial Registration ClinicalTrials.gov Identifier NCT01565551

[1]  E K Perry,et al.  D2 dopamine receptor gene (DRD2) Taq1 A polymorphism: reduced dopamine D2 receptor binding in the human striatum associated with the A1 allele. , 1997, Pharmacogenetics.

[2]  Adam R Ferguson,et al.  DRD2 C957T polymorphism is associated with improved 6-month verbal learning following traumatic brain injury , 2016, neurogenetics.

[3]  P. Kochanek,et al.  Bench-to-bedside review: Apoptosis/programmed cell death triggered by traumatic brain injury , 2004, Critical care.

[4]  G. Manley,et al.  Clinical trials in traumatic brain injury: Past experience and current developments , 2011, Neurotherapeutics.

[5]  Gunnar E. Carlsson,et al.  Topology and data , 2009 .

[6]  A. Sheet,et al.  Uniformed Services University of the Health Sciences. , 1976, Journal of the National Medical Association.

[7]  Geoffrey T Manley,et al.  Traumatic brain injury: an international knowledge-based approach. , 2013, JAMA.

[8]  Hester F. Lingsma,et al.  GFAP-BDP as an acute diagnostic marker in traumatic brain injury: results from the prospective transforming research and clinical knowledge in traumatic brain injury study. , 2013, Journal of neurotrauma.

[9]  Shruti V. Kabadi,et al.  PARP-1 inhibition attenuates neuronal loss, microglia activation and neurological deficits after traumatic brain injury. , 2014, Journal of neurotrauma.

[10]  V. A. Thurmond,et al.  Advancing integrated research in psychological health and traumatic brain injury: common data elements. , 2010, Archives of physical medicine and rehabilitation.

[11]  M. Egan,et al.  Functional analysis of genetic variation in catechol-O-methyltransferase (COMT): effects on mRNA, protein, and enzyme activity in postmortem human brain. , 2004, American journal of human genetics.

[12]  Adam R Ferguson,et al.  COMT Val158Met polymorphism is associated with nonverbal cognition following mild traumatic brain injury , 2015, neurogenetics.

[13]  Hester F. Lingsma,et al.  Transforming research and clinical knowledge in traumatic brain injury pilot: multicenter implementation of the common data elements for traumatic brain injury. , 2013, Journal of neurotrauma.

[14]  Adam R Ferguson,et al.  Topological data analysis for discovery in preclinical spinal cord injury and traumatic brain injury , 2015, Nature Communications.

[15]  Benjamin S. Glicksberg,et al.  Identification of type 2 diabetes subgroups through topological analysis of patient similarity , 2015, Science Translational Medicine.

[16]  Hester F. Lingsma,et al.  Acute biomarkers of traumatic brain injury: relationship between plasma levels of ubiquitin C-terminal hydrolase-L1 and glial fibrillary acidic protein. , 2014, Journal of neurotrauma.

[17]  Gunnar Carlsson,et al.  Topological methods reveal high and low functioning neuro‐phenotypes within fragile X syndrome , 2014, Human brain mapping.

[18]  Takashi Yamamoto,et al.  The odor of Osmanthus fragrans attenuates food intake , 2013, Scientific Reports.

[19]  Bjoern Peters,et al.  CD8 T-cell reactivity to islet antigens is unique to type 1 while CD4 T-cell reactivity exists in both type 1 and type 2 diabetes. , 2014, Journal of autoimmunity.

[20]  Pratik Mukherjee,et al.  Magnetic resonance imaging improves 3‐month outcome prediction in mild traumatic brain injury , 2012, Annals of neurology.

[21]  Neeraj,et al.  Digital Commons@Becker Digital Commons@Becker Classification of traumatic brain injury for targeted therapies Classification of traumatic brain injury for targeted therapies Classification of Traumatic Brain Injury for Targeted Therapies , 2008 .

[22]  P. Y. Lum,et al.  Extracting insights from the shape of complex data using topology , 2013, Scientific Reports.

[23]  Seonjeong Park,et al.  A New Approach to Investigate the Association between Brain Functional Connectivity and Disease Characteristics of Attention-Deficit/Hyperactivity Disorder: Topological Neuroimaging Data Analysis , 2015, PloS one.

[24]  E. Smeraldi,et al.  The catechol-O-methyltransferase Val(108/158)Met polymorphism affects antidepressant response to paroxetine in a naturalistic setting , 2009, Psychopharmacology.

[25]  L. Noble-Haeusslein,et al.  Traumatic Brain Injury: An Overview of Pathobiology with Emphasis on Military Populations , 2010, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[26]  Anthony Marmarou,et al.  A new classification of head injury based on computerized tomography , 1991 .

[27]  Ewout W Steyerberg,et al.  Prediction of Outcome in Traumatic Brain Injury with Computed Tomographic Characteristics: A Comparison between the Computed Tomographic Classification and Combinations of Computed Tomographic Predictors , 2005, Neurosurgery.

[28]  Taura L. Barr,et al.  Influence of PARP-1 polymorphisms in patients after traumatic brain injury. , 2010, Journal of neurotrauma.

[29]  M. Wintermark,et al.  Common data elements in radiologic imaging of traumatic brain injury. , 2010, Archives of physical medicine and rehabilitation.

[30]  Bjoern Peters,et al.  CD 8 T-cell reactivity to islet antigens is unique to type 1 while CD 4 T-cell reactivity exists in both type 1 and type 2 diabetes , 2014 .

[31]  R. Hurley,et al.  Common data elements in radiologic imaging of traumatic brain injury , 2010, Journal of magnetic resonance imaging : JMRI.

[32]  Jaques Reifman,et al.  Systems biology approaches for discovering biomarkers for traumatic brain injury. , 2013, Journal of neurotrauma.

[33]  R. Straub,et al.  Effect of COMT Val108/158 Met genotype on frontal lobe function and risk for schizophrenia , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[34]  Ewout W Steyerberg,et al.  Early prognosis in traumatic brain injury: from prophecies to predictions , 2010, The Lancet Neurology.

[35]  G. Manley,et al.  Common data elements for traumatic brain injury: recommendations from the biospecimens and biomarkers working group. , 2010, Archives of physical medicine and rehabilitation.

[36]  B. Pitt.  Psychopharmacology , 1968, Mental Health.

[37]  G. Carlsson,et al.  Topology based data analysis identifies a subgroup of breast cancers with a unique mutational profile and excellent survival , 2011, Proceedings of the National Academy of Sciences.

[38]  J. Ghajar,et al.  Clinical policy: neuroimaging and decisionmaking in adult mild traumatic brain injury in the acute setting. , 2008, Annals of emergency medicine.

[39]  G. Carlsson,et al.  Topology of viral evolution , 2013, Proceedings of the National Academy of Sciences.

[40]  J. Giacino,et al.  Recommendations for the use of common outcome measures in traumatic brain injury research. , 2010, Archives of physical medicine and rehabilitation.

[41]  King H. Yang,et al.  Concussion in Professional Football: Brain Responses by Finite Element Analysis: Part 9 , 2005, Neurosurgery.

[42]  Adam R Ferguson,et al.  Association of a common genetic variant within ANKK1 with six-month cognitive performance after traumatic brain injury , 2015, neurogenetics.

[43]  H. Landolt,et al.  Pharmacogenetics of Modafinil After Sleep Loss: Catechol‐O‐Methyltransferase Genotype Modulates Waking Functions But Not Recovery Sleep , 2009, Clinical pharmacology and therapeutics.