Abstract

METHODS:Between 2019 and 2020, EEG recordings from two institutions that had been recorded with a ninechannel bipolar montage, and included seizure patterns, were collected.The EEG records were classifi ed into those before 37 weeks postmenstrual age (preterm EEGs) and those from 37 weeks onward (term EEGs).EEG records without seizure patterns were also collected.Using the Nihon Kohden seizure-detection program (model QL-162A), these recordings were retrospectively re-analyzed to assess the seizure-detection capability.Experienced investigators evaluated all EEGs for the presence or absence of a seizure pattern.The performance of the program at detecting seizures was investigated. RESULTS:Of the 48 term EEGs, 26 contained 496 seizure episodes.Of the 68 preterm EEGs, 17 included 276 seizure episodes.The average gestational age at recording was 39.6 weeks for the term EEGs and 33.9 weeks for the preterm EEGs.Among the term recordings, hypoxic-ischemic encephalopathy was identifi ed in 16 of the 26 cases, and 3 had neonatal-onset epilepsy.In comparison, 10 of the 17 preterm infants were diagnosed with hypoxic-ischemic encephalopathy.The seizuredetection program accurately identifi ed seizures in 25 of the 26 term infants with seizures, for a sensitivity of 0.96 and specifi city of 0.41.At the individual seizure level, the sensitivity averaged 0.48, with a false-positive rate of 0.33 (/hour).For preterm infants, 14 of 17 were correctly identifi ed with a sensitivity of 0.82 and specifi city of 0.49.The seizure detection sensitivity was 0.33 and the falsepositive rate was 0.33 (/hour).Notable characteristics of undetected seizures in preterm infants included rhythmic delta activity and brief seizure episodes.Events often misclassifi ed as seizures encompassed delta activity specifi c to preterm infants and various artifacts. CONCLUSION:Compared to term infants, the seizuredetection sensitivity was lower in preterm infants.There is a need to develop an artifi cial intelligence algorithm specifi cally trained on the unique background EEG patterns and seizure waveforms of preterm infants.