An algorithm for the automatic detection of seizures in neonatal amplitude‐integrated EEG

Lommen, Cml; Pasman, JW; Kranen, Vhjm Van; Andriessen, Peter; Cluitmans, P.J.M.; Rooij, Lgm van; Oetomo, Sidarto Bambang

doi:10.1111/j.1651-2227.2007.00223.x

Cited by 26 publications

(17 citation statements)

References 29 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, seizure detection algorithms are being tested in some devices to assist nonexperts in quantifying seizure burden, although none of them are approved by the Food and Drug Administration at this time. 10,11 aEEG classification Much similar to cEEG, the basic interpretation of aEEG is primarily based on pattern recognition of background activity. Al Naqeeb et al 12 used simple voltage criteria to characterize the aEEGs of normal and encephalopathic term infants.…”

Section: Introductionmentioning

confidence: 99%

Using amplitude-integrated EEG in neonatal intensive care

Tao

Mathur

2010

J Perinatol

View full text Add to dashboard Cite

The implementation of amplitude-integrated electroencephalography (aEEG) has enhanced the neurological monitoring of critically ill infants. Limited channel leads are applied to the patient and data are displayed in a semilogarithmic, time-compressed scale. Several classifications are currently in use to describe patient tracings, incorporating voltage criteria, pattern recognition, cyclicity, and the presence or absence of seizures. In term neonates, aEEG has been used to determine the prognosis and treatment for those affected by hypoxic-ischemic encephalopathy, seizures, meningitis and even congenital heart disease. Its application as inclusion criteria for therapeutic hypothermia remains controversial. In preterm infants, normative values and patterns corresponding to gestational age are being established. As these standards emerge, the predictive value of aEEG increases, especially in the setting of preterm brain injury and intraventricular hemorrhage. The sensitivity and specificity of aEEG are enhanced by the display of a simultaneous raw EEG, which aids interpretation. Caution must be taken when using and interpreting this tool in conjunction with certain medications and in the setting of less experienced staff. Continuing efforts at developing software that can aid seizure detection and background classification will enhance the bedside utility of this tool.

show abstract

Section: Introductionmentioning

confidence: 99%

Using amplitude-integrated EEG in neonatal intensive care

Tao

Mathur

2010

J Perinatol

View full text Add to dashboard Cite

show abstract

“…The gestational age ranged from 34 to 42 weeks (mean 38 weeks) with birth weights from 1387 to 4405 (mean 3188 grams). The mean postnatal age at admission was 5.3 days (1–17). Fourteen infants had meningitis.…”

Section: Resultsmentioning

confidence: 99%

The prognostic value of amplitude integrated EEG in neonatal sepsis and/or meningitis

et al. 2010

View full text Add to dashboard Cite

show abstract

“…In [ 13 ], a statistical distribution feature of aEEG signal was proposed. In [ 14 ], an algorithm for the automatic detection of seizures in aEEG was proposed, based on a sudden increase of the aEEG lower boundary which is the characteristic change caused by electrographic neonatal seizures.…”

Section: Introductionmentioning

confidence: 99%

A random forest model based classification scheme for neonatal amplitude-integrated EEG

Chen

Wang

Cao

et al. 2014

BioMedical Engineering OnLine

View full text Add to dashboard Cite

BackgroundModern medical advances have greatly increased the survival rate of infants, while they remain in the higher risk group for neurological problems later in life. For the infants with encephalopathy or seizures, identification of the extent of brain injury is clinically challenging. Continuous amplitude-integrated electroencephalography (aEEG) monitoring offers a possibility to directly monitor the brain functional state of the newborns over hours, and has seen an increasing application in neonatal intensive care units (NICUs).MethodsThis paper presents a novel combined feature set of aEEG and applies random forest (RF) method to classify aEEG tracings. To that end, a series of experiments were conducted on 282 aEEG tracing cases (209 normal and 73 abnormal ones). Basic features, statistic features and segmentation features were extracted from both the tracing as a whole and the segmented recordings, and then form a combined feature set. All the features were sent to a classifier afterwards. The significance of feature, the data segmentation, the optimization of RF parameters, and the problem of imbalanced datasets were examined through experiments. Experiments were also done to evaluate the performance of RF on aEEG signal classifying, compared with several other widely used classifiers including SVM-Linear, SVM-RBF, ANN, Decision Tree (DT), Logistic Regression(LR), ML, and LDA.ResultsThe combined feature set can better characterize aEEG signals, compared with basic features, statistic features and segmentation features respectively. With the combined feature set, the proposed RF-based aEEG classification system achieved a correct rate of 92.52% and a high F1-score of 95.26%. Among all of the seven classifiers examined in our work, the RF method got the highest correct rate, sensitivity, specificity, and F1-score, which means that RF outperforms all of the other classifiers considered here. The results show that the proposed RF-based aEEG classification system with the combined feature set is efficient and helpful to better detect the brain disorders in newborns.

show abstract

An algorithm for the automatic detection of seizures in neonatal amplitude‐integrated EEG

Abstract: This study shows the feasibility of automatic ENS screening based on aEEG signals and may facilitate in the bed-side interpretation of aEEG signals in clinical practice.

Cited by 26 publications

References 29 publications

Using amplitude-integrated EEG in neonatal intensive care

Using amplitude-integrated EEG in neonatal intensive care

The prognostic value of amplitude integrated EEG in neonatal sepsis and/or meningitis

A random forest model based classification scheme for neonatal amplitude-integrated EEG

Contact Info

Product

Resources

About