Deep learning distinguishes focal epilepsy groups using connectomes: Feasibility and clinical implications
Maher, C.; Tang, Z.; D'Souza, A.; Cabezas, M.; Cai, W.; Barnett, M.; Kavehei, O.; Wang, C.; Nikpour, A.
Show abstract
The application of deep learning models to evaluate connectome data is gaining interest in epilepsy research. Deep learning may be a useful initial tool to partition connectome data into network subsets for further analysis. Few prior works have used deep learning to examine structural connectomes from patients with focal epilepsy. We evaluated whether a deep learning model applied to whole-brain connectomes could classify 28 participants with focal epilepsy from 20 controls and identify nodal importance for each group. Participants with epilepsy were further grouped based on whether they had focal seizures that evolved into bilateral tonic-clonic seizures (17 with, 11 without). The trained neural network classified patients from controls with an accuracy of 72.92%, while the seizure subtype groups achieved a classification accuracy of 67.86%. In the patient subgroups, the nodes and edges deemed important for accurate classification were also clinically relevant, indicating the models interpretability. The current work expands the evidence for the potential of deep learning to extract relevant markers from clinical datasets. Our findings offer a rationale for further research interrogating structural connectomes to obtain features that can be biomarkers and aid the diagnosis of seizure subtypes.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Individual-specific resting-state networks predict language dominance in drug-resistant epilepsy 94%
- Altered spreading of neuronal avalanches in temporal lobe epilepsy relates to cognitive performance: a resting-state hdEEG study 94%
- Uncovering Spatiotemporal Dynamics of the Corticothalamic Network during Seizures 94%
Similar papers in this journal
- Electrocorticography and Stereo EEG provide distinct measures of brain connectivity: Implications for network models 94%
- Brain network changes after the first seizure: an insight into medication response? 94%
- Effects of spatial sampling on network alterations in idiopathic generalized epilepsy. Can routine EEG be enough? 94%
Similar papers in this journal
- Brain sodium MRI-derived priors support the estimation of epileptogenic zones using personalized model-based methods in Epilepsy 95%
- Multimodal multilayer network centrality relates to executive functioning 94%
- Directionality of neural activity in and out of the seizure onset zone in focal epilepsy 93%
Similar papers in this journal
- Behavioral relevance of category selectivity revealed by human ECoG data 95%
- Velocities of Hippocampal Traveling Waves Proportional to Their Coherence Frequency 94%
- Computational modelling of the long-term effects of brain stimulation on the local and global structural connectivity of epileptic patients 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.