Key result
Using Haralick features of the gamma band (30-60 Hz) from EEG data achieved a maximum area under the curve (AUC) of 0.96 for classifying between epileptic seizures and healthy states.
Why the study?
Most previous methods for seizure detection rely on the whole frequency spectrum, prompting investigation into whether using only a high frequency EEG subband can reduce computational load.
Does using Haralick features of the Gamma band (30-60 Hz) from EEG data accurately detect epileptical seizures?
Comparison
Gamma band (30-60 Hz) Haralick features vs whole frequency spectrum
Authors
Loading...
Gamma-band Haralick EEG features may enable accurate seizure detection with lower computational load; leaves open prospective clinical validation.
Does using Haralick features of the Gamma band (30-60 Hz) from EEG data accurately detect epileptical seizures?
Effect estimate: AUC 0.96
Using Haralick features from only the high-frequency gamma band of EEG data provides high accuracy (AUC 0.96) for seizure detection while reducing computational load.
Sameer et al. (2020) studied Epileptical Seizures. Gamma band (30-60 Hz) Haralick features was evaluated on Classification between seizures and healthy states (AUC 0.96). Using Haralick features of the gamma band (30-60 Hz) from EEG data achieved a maximum area under the curve (AUC) of 0.96 for classifying between epileptic seizures and healthy states.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: