LAUSR

The prediction of functional outcome after mild traumatic brain injury (mTBI) is challenging. Conventional magnetic resonance imaging (MRI), does not explain well the variance in outcome as many patients with incomplete recovery will have normal appearing clinical neuroimaging. More advanced quantitative techniques such as diffusion MRI (dMRI), can detect microstructural changes not otherwise visible, and so may offer a way to improve outcome prediction. In this study, we explore the potential of linear support vector classifiers (linearSVCs) to identify dMRI biomarkers that can predict recovery after mTBI. Simultaneously, the harmonization of FA and MD via ComBat was evaluated and compared for the classification performances of the linearSVCs. We included dMRI scans up to 21 days post-injury of 179 mTBI patients and 85 controls from CENTER-TBI, a multi-center prospective cohort study. Patients were dichotomized according to their extended Glasgow outcome scale (GOSE) scores at six months into complete (n=92; GOSE=8) and incomplete (n=87; GOSE<8) recovery. Fractional anisotropy (FA) and mean diffusivity (MD) maps were registered to a common space and harmonized via the ComBat algorithm. LinearSVCs were applied to distinguish: 1) mTBI patients from controls and 2) mTBI patients with complete or incomplete recovery. The linearSVCs were trained on 1) age & sex only, 2) non-harmonized, 3) 2-category harmonized ComBat and 4) 3-category harmonized ComBat FA and MD images combined with age & sex. White matter FA and MD voxels and regions of interest (ROIs) within the John Hopkins University (JHU) atlas were examined. Recursive feature elimination was used to identify the 10% most discriminative voxels or the 10 most discriminative ROIs for each implementation. mTBI patients displayed significantly higher MD and lower FA values than controls for the discriminative voxels and ROIs. For the analysis between mTBI patients and controls, the 3-category harmonized ComBat FA and MD voxel-wise linearSVC provided significantly higher classification scores (81.4% accuracy, 93.3% sensitivity, 80.3% F1-score and 0.88 AUC, p<0.05) compared with the classification based on age & sex only and the ROI approaches (accuracies: 59.8% and 64.8%, respectively). Similar to the previous question, the 3-category harmonized ComBat FA and MD maps voxel-wise approach yields statistically significant prediction scores between mTBI patients with complete or incomplete recovery (71.8% specificity, 66.2% F1-score and 0.71 AUC, p<0.05), which provided a modest increase in the classification score (accuracy: 66.4%) compared to the classification based on age & sex only and ROI-wise approaches(accuracy: 61.4% and 64.7%, respectively). This study showed that ComBat harmonized FA and MD may provide additional information for diagnosis and prognosis of mild traumatic brain injury in a multi-modal machine learning approach. These findings demonstrate that dMRI may assist in the early detection of patients at risk of incomplete recovery from mTBI.