Comparison of machine learning models for seizure prediction in hospitalized patients.

Aaron F StruckAndres A Rodriguez-RuizGamaledin OsmanEmily J GilmoreHiba A HaiderMonica B DhakarMatthew SchrettnerJong W LeeNicolas GaspardLawrence J HirschM Brandon Westovernull null

Published in: Annals of clinical and translational neurology (2019)

For seizure risk stratification of hospitalized patients, the RiskSLIM generated 2HELPS2B model compares favorably to the complex NN and EN generated models. 2HELPS2B is able to accurately and quickly identify low-risk patients with only a 1-h screening EEG.

Keyphrases

machine learning
temporal lobe epilepsy
functional connectivity
working memory
artificial intelligence
resting state
big data
deep learning