Dynamic functional network connectivity discriminates mild traumatic brain injury through machine learning

Abstract

Mild traumatic brain injury (mTBI) can result in symptoms that affect a person's cognitive and social abilities. Improvements in diagnostic methodologies are necessary given that current clinical techniques have limited accuracy and are solely based on self-reports. Recently, resting state functional network connectivity (FNC) has shown potential as an important imaging modality for the development of mTBI biomarkers. The present work explores the use of dynamic functional network connectivity (dFNC) for mTBI detection. Forty eight mTBI patients (24 males) and age-gender matched healthy controls were recruited. We identified a set of dFNC states and looked at the possibility of using each state to classify subjects in mTBI patients and healthy controls. A linear support vector machine was used for classification and validated using leave-one-out cross validation. One of the dFNC states achieved a high classification performance of 92% using the area under the curve method. A series of t-test analysis revealed significant dFNC increases between cerebellum and sensorimotor networks. This significant increase was detected in the same dFNC state useful for classification. Results suggest that dFNC can be used to identify optimal dFNC states for classification excluding those that does not contain useful features.

Keywords: Dynamic functional network connectivity; Magnetic resonance imaging; Traumatic brain injury.

Graphical abstract

Fig. 1

Centroids obtained for the four dFNC states (a–e). The figure includes the mean static FNC matrix (f), the occupancy rates and the number of subjects in each state (e). State 1 had the largest occupancy rate and State 3 the smallest. The number of mTBI and controls on each state are similar.

Fig. 2

Connectivity difference results for State 2 evaluated using two-sample t-tests. Significance was corrected using false discovery rate (FDR) over the total of 1128 (48 ∗ 47/2) dFNC values on that state. Each displayed vertex represents a dFNC increment in mTBI compared to HC. No t-test survived FDR correction in any of the other three states. The matrix with all t-values for State 2 is displayed and the circles indicate the significant (FDR corrected) t-tests. The mean SVM weight vector is also displayed where similarities with the t-value matrix can be observed.

Fig. 3

Schematic of the nested LOOCV loop used to identify the optimal state and feature selection threshold. Displayed matrices consist of t-values for each state. Features were selected using the t-values from two sample t-tests that were larger than one of the six thresholds [0.0 0.25 0.50 0.75 1.0 2.0]. In total there were 24 classification models (6 t-thresholds times 4 dFNC states). In this figure, the three dots between models indicate the existence of the other models.

Fig. 4

Histogram of classification performance (AUC) obtained using the nested loop of Fig. 3. State 3 and State 4 were never selected to classify the left out sample. State 2 was selected 88 times with the t-threshold of 0.75 as the preferred choice. State 1 was the second choice, which in most cases replaced missing subject data in State 2. The number of features is displayed in parenthesis below the number of times selected.