A game theory based analysis of network connectivity reveals that state transition is crucial for epilepsy surgery outcome prediction
Ivankovic, K.; Principe, A.; Montoya, J.; Manubens-Gil, L.; Dierssen, M.; Rocamora, R.
Show abstract
Seizures recur in half of patients who undergo epilepsy surgery. Presurgical workup mainly focuses on seizures, but only partially helps predicting outcomes, even after invasive electroencephalography. We conceived a generalizable model to detect epileptogenic networks through connectivity changes and identified the crucial role of the transition from pre-seizure to seizure, achieving the highest outcome prediction (93%) to date in a chronological cohort of 21 patients with 3-year follow-up or more.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Synchronizability predicts effective responsive neurostimulation for epilepsy prior to treatment 95%
- Uncovering Spatiotemporal Dynamics of the Corticothalamic Network during Seizures 95%
- Stimulation better targets fast ripple generating networks in super-responders to the responsive neurostimulator system (RNS) 95%
Similar papers in this journal
Similar papers in this journal
- Optimizing Detection and Deep Learning-based Classification of Pathological High-Frequency Oscillations in Epilepsy 95%
- Pro-ictal, rather than pre-ictal, brain state marked by global critical slowing and local gamma power increase 95%
- Visualization of Phase-Amplitude Coupling Using Rhythmic High-Frequency Activity 94%
Similar papers in this journal
"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.