Quantitative EEG analysis for automated detection of nonconvulsive seizures in intensive care units

► The use of EEG monitoring to identify nonconvulsive seizures is increasing in intensive care units. ► No clinically validated seizure detection algorithms exist for patients in intensive care units. ► A new seizure detection algorithm was tested on 24 prolonged EEG recordings. ► The new algorithm performed with 90.4% sensitivity and a 0.066/hour false detection rate. ► The results suggest that the algorithm can assist intensive care unit staff in identifying seizures.