Seizure prediction: the long and winding road.

By Florian Mormann, Ralph G. Andrzejak, Christian Erich Elger, Klaus Lehnertz. Brain : a journal of neurology, 2007

1,140 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Psychiatry and Mental health, Signal Processing

View Paper: https://www.semanticscholar.org/paper/afb9ad2b630e5cd4e165ee91f96668afc26cfad3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Psychiatry and Mental health

In Signal Processing

Citations in the corpus

Automatic Seizure Detection Based on Time-Frequency Analysis and Artificial Neural Networks (2007, background): “For the remaining 25% of patients, no su ﬃ cient treatment is currently available [1].”
Artificial Intelligence in Healthcare: Review and Prediction Case Studies (2020, neutral): “Although early seizure-forecasting investigations date back to the 1970s [109], the limited number of seizure events, the paucity of intracranial electroencephalography (iEEG) recordings, and the limited extent of interictal epochs have been major hurdles toward an adequate evaluation of seizure pre”
A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals (2018, background): “The electrical activity of the brain of patients suffering from epilepsy has been considered to change significantly over time while moving towards seizures onset, with various methodologies being proposed to isolate preictal EEG patterns and rhythmic changes that are able to declare an incoming sei”
Focal Onset Seizure Prediction Using Convolutional Networks (2018, methodology): “using intracranial EEG which report a prediction horizon of an hour or longer [14].”
Prediction (2010, neutral): “The “wave” approach consists in viewing the ECoG as a continu ous signal and then apply various signal analysis techniques, for instance derived from the t heory of dynamical systems and chaos [82].”
Learning Robust Features using Deep Learning for Automatic Seizure Detection (2016, background): “Online predictions attempt to predict in advance when seizures will occur, with the possible goal of applying just-in-time treatment or intervention options (Mormann et al., 2007).”
Seizure prediction with spectral power of EEG using cost‐sensitive support vector machines (2011, methodology): “Many previous studies trained and tested their prediction models on the same datasets (Mormann et al., 2007), resulting in overly optimistic prediction rates; their models are not free from the over-fitting problem.”
Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review (2020, methodology): “have provided an overview of the evolution of seizure predicting methods since the 1970 s till 2006 [3] and have covered the major issues related to methodology of ES prediction.”
Classification of patterns of EEG synchronization for seizure prediction. (2009, neutral): “However, and despite decades of research, research in seizure prediction is still qualified as a ‘‘long and winding road” (Mormann et al., 2007).”
Adaptive Control of Epileptic Seizures using Reinforcement Learning (2010, background): “Doing this in a principled way is still an open problem but extensive trial-and-error search, or relying on features found in the seizure detection/prediction literature [15, 46], could reveal features that induce greater policies.”