Background Diffusion Tensor Imaging (DTI) has shown measurable changes in the brains of patients with persistent post-concussive syndrome (PCS). Because of inconsistent results in univariate DTI metrics among patients with mild traumatic brain injury (mTBI), currently, there is no single objective and reliable MRI index for the clinical decision-making for patients with PCS.Objectives The aim of this study was to evaluate the performance of a newly developed post-concussive syndrome index (PCSI) derived from machine learning of multiparametric MRI data, to classify and differentiate subjects with mTBI and PCS history from those without history of mTBI.Methods Data were retrospectively extracted from 139 patients aged between 18 and 60 years with PCS who had MRI examinations obtained 2 weeks to 1-year post-mTBI, as well as MRI data from 333 subjects without a history of head trauma. The performance of the PCSI was assessed by comparing patients with a clinical diagnosis of PCS to control subjects. The PCSI values for patients with PCS were compared based on mechanism of injury, time interval from injury to MRI examination, gender, prior concussion history, loss of consciousness, and reported symptoms.Results Patients with mTBI had a mean PCSI value of 0.57, compared to the control group, which had a mean PCSI value of 0.12 (p = 8.42e− 23) with accuracy of 88%, sensitivity of 64%, and specificity of 95% respectively. No statistically significant differences were found in PCSI values when comparing by mechanism of injury, gender, or loss of consciousness.Conclusion The PCSI for individuals aged between 18 and 60 years was able to accurately identify patients with post-concussive injuries from 2 weeks to 1-year post-mTBI and differentiate them from controls. The study's results suggest that the multiparametric MRI-based PCSI has great potential as an objective clinical tool to support the diagnosis, treatment, and follow-up care of those with post-concussive syndrome. Future research is required to investigate the replicability of this method using other types of clinical MRI scanners.