Predicting recovery in patients with mild traumatic brain injury and a normal CT using serum biomarkers and diffusion tensor imaging (CENTER-TBI): an observational cohort study

Abstract

Background: Even patients with normal computed tomography (CT) head imaging may experience persistent symptoms for months to years after mild traumatic brain injury (mTBI). There is currently no good way to predict recovery and triage patients who may benefit from early follow-up and targeted intervention. We aimed to assess if existing prognostic models can be improved by serum biomarkers or diffusion tensor imaging metrics (DTI) from MRI, and if serum biomarkers can identify patients for DTI.

Methods: We included 1025 patients aged >18 years with a Glasgow Coma Score >12 and normal CT from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study which recruited between December 19,2014 and December 17, 2017 (NCT02210221). Biomarkers (GFAP, NFL, S100B) were obtained at a median of 8.8 h (Q1-Q3 4.2-16.7) and DTI at 13 days (3-19) after injury. DTI metrics were available in 153 patients for 48 white matter tracts (ICBM-DTI-81 atlas). Incomplete recovery at three months was defined as an extended Glasgow Outcome Scale score <8. Existing prognostic models were fitted with and without biomarkers, or with and without DTI, and internally validated using bootstrapping.

Findings: 385 (38%) patients had incomplete recovery. Adding biomarkers did not improve performance beyond the best existing clinical prognostic model [optimism-corrected AUC 0.69 (95% CI 0.65-0.72) and R² 17% (11-22)]. Adding DTI metrics significantly enhanced all models [best optimism-corrected AUC 0.82 (0.79-0.85) and R² 75% (39-100)]. The top three prognostic tracts were the left posterior thalamic radiation, left superior cerebellar peduncle and right uncinate fasciculus. Serum biomarkers could have avoided 1 in 5 DTI scans, with GFAP <12 h and NFL 12-24 h from injury performing best.

Interpretation: DTI substantially improved existing prognostic models for functional outcome in patients with mTBI and a normal CT, and biomarkers could help select patients for MRI. If validated, DTI could allow for targeted follow-up and enrichment of clinical trials of early interventions to improve outcome.

Funding: EU Seventh Framework Programme, Hannelore Kohl Stiftung, One Mind, Integra LifeSciences, NeuroTrauma Sciences.

Keywords: Biomarkers; Concussion; Imaging; Outcome; Prognostication; Traumatic brain injury.

Fig. 1

Receiver operating characteristics curves for models with (yellow line) and without (green line) diffusion tensor imaging (DTI). AUC (95% CI), Area under the curve (95% confidence interval).

Fig. 2

Calibration plots for models with and without diffusion tensor imaging (DTI). Each prognostic model is presented on a new row. Each row shows the calibration plot of the same model without (left-hand panel) and with (right-hand panel) DTI as a predictor. Dots with bars = mean predicted probability of unfavorable outcome with its 95% confidence interval. Solid line = calibration line that should be followed by a perfectly calibrated model. Dashed line = calibration line of the actual model, fitted using linear regression. Coloured line = calibration line of the actual model, fitted using locally estimated scatterplot smoothing.