Using low-frequency oscillations to detect temporal lobe epilepsy with machine learning.

The NIH-sponsored Epilepsy Connectome Project aims to characterize connectivity changes in temporal lobe epilepsy (TLE) patients. The MRI protocol follows that used in the Human Connectome Project, and includes 20 minutes of resting-state fMRI acquired at 3T using 8-band multiband imaging. Glasser parcellation atlas was combined with the FreeSurfer subcortical regions to generate resting state functional connectivity (RSFC), amplitude of low frequency fluctuations (ALFF), and fractional ALFF (fALFF) measures. Seven different frequency ranges such as Slow-5 (0.01-0.027Hz) and Slow-4 (0.027-0.073Hz) were selected to compute these measures. The goal was to train machine learning classification models to discriminate TLE patients from healthy controls, and to determine which combination of the resting state measure and frequency range produced the best classification model. The samples included age- and gender-matched groups of 60 TLE patients and 59 healthy controls. Three traditional machine learning models were trained: support vector machine (SVM), linear discriminant analysis (LDA), and naïve Bayes classifier (NB). The highest classification accuracy was obtained using RSFC measures in the Slow-4+5 band (0.01-0.073Hz) as features. Leave-one-out cross-validation accuracies were approximately 83%, with receiver operating characteristic area-under-the-curve reaching close to 90%. Increased connectivity from right area posterior 9-46v in TLE patients contributed to the high accuracies. With increased sample sizes in the near future, better machine learning models will be trained not only to aid the diagnosis of TLE, but also as a tool to understand this brain disorder.