Multi-modal machine learning detection and tracking of traumatic brain injury neurodegeneration and its differentiation from Alzheimer's disease

SUMMARY The proposed research focuses on the use of neuroimaging and machine learning to detect and understand the progression of neurodegeneration caused by repetitive brain traumaand to differentiate this from that caused by Alzheimer s diseaseADand other dementiasThe deliverables defined in this Phase I stage will support the development of a commercial software product for use in pharmaceutical clinical trials and in clinical diagnosisTraumatic Brain InjuryTBIhas been shown to cause cognitive deterioration and other symptoms that overlap those arising with ADTBI can also lead to the development of Chronic Traumatic EncephalopathyCTEwhich shares similarities in brain atrophy and tau accumulation with ADThere is mixed evidence as to whether TBI increases the risk or rate of developing ADbut regardlessthe likelihoods of co morbidity and misdiagnosis become high as individuals ageThe relevant population includes professional sports athletesindividuals who played head contacting sports during high school or collegemilitary veteransand persons experiencing fallsHoweverthe process by which TBI causes progressive damageand the ways in which it can best be discriminated from ADhave not been determinedThe aims of this grant focus on characterizing the progressive structural and pathology effects of TBI and discriminating these from AD using imaging of structurefunctionand pathologyand machine learningClassifiers will be developed using these information types alone and in combinationInnovations of this work include the use of a uniquecomprehensive data set of imagingcognitiveand other data acquired on more thanfighters by the Cleveland Clinica database of more thanwell characterized scans from persons across the spectrum of pre symptomatic and symptomatic AD and other dementiasand a sophisticated machine learning software platform that addresses issues such as data overfitting and validationSpecific Aimfocuses on characterizing neurodegenerative changes that occur in fighters using volumetricTweighted MRIand white matterDiffusion TensorDTIimagingAimwill characterize tau accumulation in fighters and its relationship to and structural changescomparing the two tracersF AVandF FDDNPSpecific Aimwill determine methods to differentiate TBI related neurodegeneration from AD using structural and tau imagingFollow on work in Phase II will include model refinement and additional validation with additional independent datafurther prediction of cognitive impairmentextension to functional imaging modalities ASL and fMRI BOLDdissociation of co existing TBI and ADcomparisons to other forms of traumaand development of software tools for commercializationThis work can have significant societal benefit through improved detection of TBI effects and precursors to greater damage and impairmentand accurate differentiation of AD and other dementias versus TBI effects to support optimal patient care NARRATIVE This research addresses a critical gap in the understanding of the neurodegenerative effects of Traumatic Brain InjuryTBIand the ability to differentiate effects of TBI from those caused by Alzheimer s diseaseADand other neurodegenerative dementiasAdvances in machine learning will be applied to a unique multi modality data set acquired in overboxers and mixed martial arts fighters who have experienced varying exposure to head trauma and years since trauma was incurredand to a data from a set of more thanscans acquired in persons at varying stages of mild cognitive impairment and dementia due to Alzheimer s disease and other dementiasOutcomes of the research will enable a diagnostic tool to be developed that enables differentiation of TBI effects from those of other dementiasand that increases the understanding of the path by which TBI can cause progressive cognitive impairment