Improving the detection of mtbi via complexity analysis in resting - state magnetoencephalography

Diagnosis of mild Traumatic Brain Injury (mTBI) is difficult due to the variability of obvious brain lesions using imaging scans. A promising tool for exploring potential biomarkers for mTBI is magnetoencephalography which has the advantage of high spatial and temporal resolution. By adopting proper analytic tools from the field of symbolic dynamics like Lempel-Ziv complexity, we can objectively characterize neural network alterations compared to healthy control by enumerating the different patterns of a symbolic sequence. This procedure oversimplifies the rich information of brain activity captured via MEG. For that reason, we adopted neural-gas algorithm which can transform a time series into more than two symbols by learning brain dynamics with a small reconstructed error. The proposed analysis was applied to recordings of 30 mTBI patients and 50 normal controls in δ frequency band. Our results demonstrated that mTBI patients could be separated from normal controls with more than 97% classification accuracy based on high complexity regions corresponding to right frontal areas. In addition, a reverse relation between complexity and transition rate was demonstrated for both groups. These findings indicate that symbolic complexity could have a significant predictive value in the development of reliable biomarkers to help with the early detection of mTBI.