Header
Header
Article

Machine learning for the early prediction of infants with electrographic seizures in neonatal hypoxic-ischaemic encephalopathy



Pavel, Andreea M;

O’Toole, John M;

Proietti, Jacopo;

Livingstone, Vicki;

Mitra, Subhabrata;

Marnane, William P;

Finder, Mikael;

ANSeR Consortium; + view all

Pavel, Andreea M;

O’Toole, John M;

Proietti, Jacopo;

Livingstone, Vicki;

Mitra, Subhabrata;

Marnane, William P;

Finder, Mikael;

Dempsey, Eugene M;

Murray, Deirdre M;

Boylan, Geraldine B;

ANSeR Consortium;

– view fewer

(2022)

Machine learning for the early prediction of infants with electrographic seizures in neonatal hypoxic-ischaemic encephalopathy.

Epilepsia


10.1111/epi.17468.

(In press).


Text

Pressler_Epilepsia – 2022 – Pavel – Machine learning for the early prediction of infants with electrographic seizures in neonatal_extracted.pdf

Access restricted to UCL open access staff until 30 May 2023.

Download (524kB)

Abstract

OBJECTIVE: To assess if early clinical and electroencephalographic(EEG) features predict later seizure development in infants with hypoxic-ischaemic encephalopathy(HIE). METHODS: Clinical and EEG parameters<12 hours of birth from infants with HIE across eight European Neonatal Units were used to develop seizure prediction models. Clinical parameters included: intrapartum complications, foetal distress, gestational age, delivery mode, gender, birth weight, Apgar scores, assisted ventilation, cord pH, blood gases. Earliest EEG hour provided a qualitative analysis (discontinuity, amplitude, asymmetry/asynchrony, sleep-wake cycling-SWC) and a quantitative analysis (power, discontinuity, spectral distribution, inter-hemispheric connectivity) from full montage and 2-channel aEEG. Subgroup analysis, only including infants without anti-seizure medication(ASM) prior to EEG was also performed. Machine-learning(ML) models (random forest and gradient boosting algorithms) were developed to predict infants that would later develop seizures and assessed using Matthews Correlation Coefficient(MCC) and area under the receiver operating curve(AUROC). RESULTS: The study included 162 infants with HIE (53 had seizures). Low Apgar, need for ventilation, high lactate, low base excess, absent SWC, low EEG power, increased EEG discontinuity were associated with seizures. The following predictive models were developed: clinical (MCC 0.368, AUROC 0.681), qualitative-EEG (MCC 0.467, AUROC 0.729), quantitative-EEG (MCC 0.473, AUROC 0.730), clinical and qualitative-EEG (MCC 0.470, AUROC 0.721) and clinical and quantitative-EEG (MCC 0.513, AUROC 0.746). The clinical and qualitative-EEG model significantly outperformed the qualitative-EEG model (MCC 0.470 vs 0.368, p-value 0.037). The clinical and quantitative-EEG model significantly outperformed the clinical model (MCC 0.513 vs 0.368, p-value 0.012). The clinical and quantitative-EEG model for infants without ASM (n=131) had MCC 0.588, AUROC 0.832. Performance for quantitative-aEEG (n=159) was MCC 0.381, AUROC 0.696 and clinical and quantitative-aEEG was MCC 0.384, AUROC 0.720. SIGNIFICANCE: Early EEG background analysis combined with readily available clinical data helped predict infants at highest risk of seizures, hours before they occur. Automated quantitative-EEG analysis was as good as expert analysis for predicting seizures, supporting the use of automated assessment tools for early evaluation of HIE.

Download activity – last month
Download activity – last 12 months
Downloads by country – last 12 months

Archive Staff Only

View Item View Item



Source link

Back to top button