Metrics of brain network architecture capture the impact of disease in children with epilepsy

Abstract

Background and objectiveEpilepsy is associated with alterations in the structural framework of the cerebral network. The aim of this study was to measure the potential of global metrics of network architecture derived from resting state functional MRI to capture the impact of epilepsy on the developing brain.MethodsPediatric patients were retrospectively identified with: 1. Focal epilepsy; 2. Brain MRI at 3 Tesla, including resting state functional MRI; 3. Full scale IQ measured by a pediatric neuropsychologist. The cerebral cortex was parcellated into approximately 700 gray matter network nodes. The strength of a connection between two nodes was defined as the correlation between their resting BOLD signal time series. The following global network metrics were then calculated: clustering coefficient, transitivity, modularity, path length, and global efficiency. Epilepsy duration was used as an index for the cumulative impact of epilepsy on the brain.Results45 patients met criteria (age: 4–19 years). After accounting for age of epilepsy onset, epilepsy duration was inversely related to IQ (p: 0.01). Epilepsy duration predicted by a machine learning algorithm on the basis of the five global network metrics was highly correlated with actual epilepsy duration (r: 0.95; p: 0.0001). Specifically, modularity and to a lesser extent path length and global efficiency were independently associated with epilepsy duration.ConclusionsWe observed that a machine learning algorithm accurately predicted epilepsy duration based on global metrics of network architecture derived from resting state fMRI. These findings suggest that network metrics have the potential to form the basis for statistical models that translate quantitative imaging data into patient-level markers of cognitive deterioration.

Progressive topological disorganization of brain network in focal epilepsy

“…9 The global efficiency is the average nodal efficiency across all nodes within the whole network, which is inversely related to the characteristic path length. Furthermore, the global efficiency in the patients with chronic epilepsy was significantly more decreased than that in the patients with newly diagnosed epilepsy.…”

“…1,2,5 This approach has made a considerable impact on recent studies of brain network, and small-world architectures have been found in the human brain network. 6 Recently, there has also been an emerging role of graph theory in the research of epilepsy, 2 and various modalities have been used to evaluate the topological properties, such as electroencephalography (EEG), 7 magnetoencephalography (MEG), 8 resting state-functional magnetic resonance imaging (rs-fMRI), 9 cortical thickness or volumes, 4,10 and diffusion tensor image (DTI). 6 Recently, there has also been an emerging role of graph theory in the research of epilepsy, 2 and various modalities have been used to evaluate the topological properties, such as electroencephalography (EEG), 7 magnetoencephalography (MEG), 8 resting state-functional magnetic resonance imaging (rs-fMRI), 9 cortical thickness or volumes, 4,10 and diffusion tensor image (DTI).…”

Machine learning applications in epilepsy

“…Paldino et al found that a random forest classifier achieved 100% sensitivity and 95.4% specificity in predicting language impairment using DTI‐based whole‐brain tractography data from 33 pediatric patients with malformations of cortical development . A later study demonstrated that a random forest classifier trained on resting‐state fMRI images from 45 pediatric epilepsy patients was also able to estimate disease duration with high accuracy (correlating with true disease duration with r = .95, P = .0004), which in turn was inversely correlated with full‐scale intelligence quotient . Piña‐Garza et al investigated healthcare utilization in patients with Lennox‐Gastaut syndrome using a multistate Medicaid claims database, utilizing a random forest classifier to identify probable patients based on clinical variables (eg, prescriptions for felbamate or clobazam, vagus nerve stimulator placement, corpus callosotomy, helmet use, or claims for intellectual disability); aside from finding higher lifetime healthcare costs, particularly for home‐based or long‐term care, the authors found lower rates of clobazam or rufinamide use in older patients, raising questions of suboptimal management in this cohort .…”

Thalamic nuclei volumes and network in juvenile myoclonic epilepsy

“…The modularity in the patients with JME was significantly increased over that in healthy controls. This modularity is the degree to which the network tends to segregate into relatively independent modules, or subnetworks, which reflects the capacity of a network to support functional subspecialization . In other words, it reflects the ability of the brain to process specialized functions within highly interconnected functional subnetworks .…”

“…This modularity is the degree to which the network tends to segregate into relatively independent modules, or subnetworks, which reflects the capacity of a network to support functional subspecialization . In other words, it reflects the ability of the brain to process specialized functions within highly interconnected functional subnetworks . Modularity is a critical component of learning, with a more modular structure potentially allowing for more efficient and greater adaptive reorganization in response to changing demands .…”