AUTHOR=Hellstrøm Torgeir , Kaufmann Tobias , Andelic Nada , Soberg Helene L. , Sigurdardottir Solrun , Helseth Eirik , Andreassen Ole A. , Westlye Lars T. 

TITLE=Predicting Outcome 12 Months after Mild Traumatic Brain Injury in Patients Admitted to a Neurosurgery Service

JOURNAL=Frontiers in Neurology

VOLUME=8

YEAR=2017

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2017.00125

DOI=10.3389/fneur.2017.00125

ISSN=1664-2295

ABSTRACT=<sec id="ST1"><title>Objective</title><p>Accurate outcome prediction models for patients with mild traumatic brain injury (MTBI) are key for prognostic assessment and clinical decision-making. Using multivariate machine learning, we tested the unique and added predictive value of (1) magnetic resonance imaging (MRI)-based brain morphometric and volumetric characterization at 4-week postinjury and (2) demographic, preinjury, injury-related, and postinjury variables on 12-month outcomes, including global functioning level, postconcussion symptoms, and mental health in patients with MTBI.</p></sec><sec id="ST2"><title>Methods</title><p>A prospective, cohort study of patients (<italic>n</italic> = 147) aged 16–65 years with a 12-month follow-up. T1-weighted 3 T MRI data were processed in FreeSurfer, yielding accurate cortical reconstructions for surface-based analyses of cortical thickness, area, and volume, and brain segmentation for subcortical and global brain volumes. The 12-month outcome was defined as a composite score using a principal component analysis including the Glasgow Outcome Scale Extended, Rivermead Postconcussion Questionnaire, and Patient Health Questionnaire-9. Using leave-one-out cross-validation and permutation testing, we tested and compared three prediction models: (1) MRI model, (2) clinical model, and (3) MRI and clinical combined.</p></sec><sec id="ST3"><title>Results</title><p>We found a strong correlation between observed and predicted outcomes for the clinical model (<italic>r</italic> = 0.55, <italic>p</italic> &lt; 0.001). The MRI model performed at the chance level (<italic>r</italic> = 0.03, <italic>p</italic> = 0.80) and the combined model (<italic>r</italic> = 0.45, <italic>p</italic> &lt; 0.002) were slightly weaker than the clinical model. Univariate correlation analyses revealed the strongest association with outcome for postinjury factors of posttraumatic stress (Posttraumatic Symptom Scale-10, <italic>r</italic> = 0.61), psychological distress (Hospital Anxiety and Depression Scale, <italic>r</italic> = 0.52), and widespread pain (<italic>r</italic> = 0.43) assessed at 8 weeks.</p></sec><sec id="ST4"><title>Conclusion</title><p>We found no added predictive value of MRI-based measures of brain cortical morphometry and subcortical volumes over and above demographic and clinical features.</p></sec>