Objective Classification of mTBI Using Machine Learning on a Combination of Frontopolar Electroencephalography Measurements and Self-reported Symptoms

Abstract

Background The reliable diagnosis of a mild traumatic brain injury (mTBI) is a pervasive problem in sports and in the military. The frequency and severity of each occurrence, while difficult to quantify, may impact long term cognitive function and quality of life. Despite the new revelations concerning brain disfunction from head injuries, individuals still feel pressure to remain on the field despite a debilitating injury. In this study, we evaluated the accuracy of a system that could be employed on the sidelines or in the locker room to provide an immediate objective mTBI assessment. Methods Participants consisted of 38 individuals with a recent mTBI and 47 controls with no history of mTBI within the last 5 years. Participants were administered a simple symptom questionnaire, behavioral tests, and resting state EEG was measured using three frontopolar electrodes. An advanced machine learning algorithm called boosting was utilized to classify subjects into either injured or controls using power spectral densities on 1-min of resting EEG and the symptom questionnaire. Results Results based on leave-one-out cross-validation revealed that the addition of EEG measurements boosted the accuracy to approximately 91 ± 2% compared to 82 ± 4% from the symptom questionnaire alone. Conclusion This study demonstrated the potential benefit of including EEG measurements to diagnose suspected brain injury patients. This is a step toward accurate and objective classification measurements that can be implemented on the field as a future injury assessment tool.

Detection of Moderate Traumatic Brain Injury from Resting-State Eye-Closed Electroencephalography

“…Comparing to other existing methods, the proposed method reaches a high accuracy of 72.46%, which stands out compared to the work by den Brink et al [24], McNerney et al [25], Cao et al [26], and our previous work [27]. By using the same dataset, these approaches achieve the mean cross-validation accuracies of 59.05%, 54.00%, 51.17%, and 49.64%, respectively, as shown in Table 7.…”

“…e parameters are the learning rate and mini batch size. Trained CNN models are then compared with Naive Bayes [24], AdaBoost classifier [25], SVM (MRMR) [26], and SVM (power) [27].…”

“…e second method that is compared was proposed by McNerney et al [25] that uses AdaBoost classifier. e third method that is compared is the work done by Cao et al [26] that uses SVM.…”

“…McNerney et al [25] make use of resting-state EEG and adaptive boosting (AdaBoost) for classification of mild TBI. First, a band-pass filter with cutoff frequency from 0.1 Hz to 100 Hz is applied.…”

“…It carries advantages such as being simple and requiring less tweaking of parameters to achieve high classification result despite being sensitive to noisy data and outliers. us, preprocessing becomes an unavoidable stage in the work of McNerney et al [25] to remove external noises. In the work of Cao et al [26], an automatic classification of athletes with concussion has been proposed by using an EEG-based support vector machine (SVM).…”