A machine-learning algorithm for neonatal seizure recognition: a multicentre, randomised, controlled trial

Andreea M Pavel, Janet M Rennie, Linda S de Vries, Mats Blennow, Adrienne Foran, Divyen K Shah, Ronit M Pressler, Olga Kapellou, Eugene M Dempsey, Sean R Mathieson, Elena Pavlidis, Alexander C van Huffelen, Vicki Livingstone, Mona C Toet, Lauren C Weeke, Mikael Finder, Subhabrata Mitra, Deirdre M Murray, William P Marnane, Geraldine B Boylan, Andreea M Pavel, Janet M Rennie, Linda S de Vries, Mats Blennow, Adrienne Foran, Divyen K Shah, Ronit M Pressler, Olga Kapellou, Eugene M Dempsey, Sean R Mathieson, Elena Pavlidis, Alexander C van Huffelen, Vicki Livingstone, Mona C Toet, Lauren C Weeke, Mikael Finder, Subhabrata Mitra, Deirdre M Murray, William P Marnane, Geraldine B Boylan

Abstract

Background: Despite the availability of continuous conventional electroencephalography (cEEG), accurate diagnosis of neonatal seizures is challenging in clinical practice. Algorithms for decision support in the recognition of neonatal seizures could improve detection. We aimed to assess the diagnostic accuracy of an automated seizure detection algorithm called Algorithm for Neonatal Seizure Recognition (ANSeR).

Methods: This multicentre, randomised, two-arm, parallel, controlled trial was done in eight neonatal centres across Ireland, the Netherlands, Sweden, and the UK. Neonates with a corrected gestational age between 36 and 44 weeks with, or at significant risk of, seizures requiring EEG monitoring, received cEEG plus ANSeR linked to the EEG monitor displaying a seizure probability trend in real time (algorithm group) or cEEG monitoring alone (non-algorithm group). The primary outcome was diagnostic accuracy (sensitivity, specificity, and false detection rate) of health-care professionals to identify neonates with electrographic seizures and seizure hours with and without the support of the ANSeR algorithm. Neonates with data on the outcome of interest were included in the analysis. This study is registered with ClinicalTrials.gov, NCT02431780.

Findings: Between Feb 13, 2015, and Feb 7, 2017, 132 neonates were randomly assigned to the algorithm group and 132 to the non-algorithm group. Six neonates were excluded (four from the algorithm group and two from the non-algorithm group). Electrographic seizures were present in 32 (25·0%) of 128 neonates in the algorithm group and 38 (29·2%) of 130 neonates in the non-algorithm group. For recognition of neonates with electrographic seizures, sensitivity was 81·3% (95% CI 66·7-93·3) in the algorithm group and 89·5% (78·4-97·5) in the non-algorithm group; specificity was 84·4% (95% CI 76·9-91·0) in the algorithm group and 89·1% (82·5-94·7) in the non-algorithm group; and the false detection rate was 36·6% (95% CI 22·7-52·1) in the algorithm group and 22·7% (11·6-35·9) in the non-algorithm group. We identified 659 h in which seizures occurred (seizure hours): 268 h in the algorithm versus 391 h in the non-algorithm group. The percentage of seizure hours correctly identified was higher in the algorithm group than in the non-algorithm group (177 [66·0%; 95% CI 53·8-77·3] of 268 h vs 177 [45·3%; 34·5-58·3] of 391 h; difference 20·8% [3·6-37·1]). No significant differences were seen in the percentage of neonates with seizures given at least one inappropriate antiseizure medication (37·5% [95% CI 25·0 to 56·3] vs 31·6% [21·1 to 47·4]; difference 5·9% [-14·0 to 26·3]).

Interpretation: ANSeR, a machine-learning algorithm, is safe and able to accurately detect neonatal seizures. Although the algorithm did not enhance identification of individual neonates with seizures beyond conventional EEG, recognition of seizure hours was improved with use of ANSeR. The benefit might be greater in less experienced centres, but further study is required.

Funding: Wellcome Trust, Science Foundation Ireland, and Nihon Kohden.

Copyright © 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.

Figures

Figure 1
Figure 1
Trial profile EEG=electroencephalography.
Figure 2
Figure 2
Percentage of seizure hours detected, by total seizure burden within the hour
Figure 3
Figure 3
Number of seizure hours in neonates who had seizures in the algorithm group (A) and non-algorithm group (B) Each bar represents a neonate.

References

    1. Mizrahi EM. Clinical and neurophysiologic correlates of neonatal seizures. Cleve Clin J Med. 1989;56(suppl 1):S100–S104.
    1. Vasudevan C, Levene M. Epidemiology and aetiology of neonatal seizures. Semin Fetal Neonatal Med. 2013;18:185–191.
    1. Glass HC, Shellhaas RA, Wusthoff CJ. Contemporary profile of seizures in neonates: a prospective cohort study. J Pediatr. 2016;174:98–103.e1.
    1. Slaughter LA, Patel AD, Slaughter JL. Pharmacological treatment of neonatal seizures: a systematic review. J Child Neurol. 2013;28:351–364.
    1. Murray DM, Boylan GB, Ali I, Ryan CA, Murphy BP, Connolly S. Defining the gap between electrographic seizure burden, clinical expression and staff recognition of neonatal seizures. Arch Dis Child Fetal Neonatal Ed. 2008;93:F187–F191.
    1. Abend NS, Wusthoff CJ, Goldberg EM, Dlugos DJ. Electrographic seizures and status epilepticus in critically ill children and neonates with encephalopathy. Lancet Neurol. 2013;12:1170–1179.
    1. Malone A, Ryan CA, Fitzgerald A, Burgoyne L, Connolly S, Boylan GB. Interobserver agreement in neonatal seizure identification. Epilepsia. 2009;50:2097–2101.
    1. Scher MS, Alvin J, Gaus L, Minnigh B, Painter MJ. Uncoupling of EEG-clinical neonatal seizures after antiepileptic drug use. Pediatr Neurol. 2003;28:277–280.
    1. Weiner SP, Painter MJ, Geva D, Guthrie RD, Scher MS. Neonatal seizures: electroclinical dissociation. Pediatr Neurol. 1991;7:363–368.
    1. Rennie JM, Chorley G, Boylan GB, Pressler R, Nguyen Y, Hooper R. Non-expert use of the cerebral function monitor for neonatal seizure detection. Arch Dis Child Fetal Neonatal Ed. 2004;89:F37–F40.
    1. Shellhaas RA. Continuous long-term electroencephalography: the gold standard for neonatal seizure diagnosis. Semin Fetal Neonatal Med. 2015;20:149–153.
    1. Kharoshankaya L, Stevenson NJ, Livingstone V. Seizure burden and neurodevelopmental outcome in neonates with hypoxic-ischemic encephalopathy. Dev Med Child Neurol. 2016;58:1242–1248.
    1. De Haan TR, Langeslag J, van der Lee JH, van Kaam AH. A systematic review comparing neurodevelopmental outcome in term infants with hypoxic and vascular brain injury with and without seizures. BMC Pediatr. 2018;18:147.
    1. Rennie JM, de Vries LS, Blennow M. Characterisation of neonatal seizures and their treatment using continuous EEG monitoring: a multicentre experience. Arch Dis Child Fetal Neonatal Ed. 2019;104:F493–F501.
    1. Shah DK, Wusthoff CJ, Clarke P. Electrographic seizures are associated with brain injury in newborns undergoing therapeutic hypothermia. Arch Dis Child Fetal Neonatal Ed. 2014;99:F219–F224.
    1. Glass HC, Glidden D, Jeremy RJ, Barkovich AJ, Ferriero DM, Miller SP. Clinical neonatal seizures are independently associated with outcome in infants at risk for hypoxic-ischemic brain injury. J Pediatr. 2009;155:318–323.
    1. Boylan G, Burgoyne L, Moore C, O'Flaherty B, Rennie J. An international survey of EEG use in the neonatal intensive care unit. Acta Paediatr. 2010;99:1150–1155.
    1. Wirrell EC, Armstrong EA, Osman LD, Yager JY. Prolonged seizures exacerbate perinatal hypoxic-ischemic brain damage. Pediatr Res. 2001;50:445–454.
    1. Mulkey SB, Swearingen CJ. Advancing neurologic care in the neonatal intensive care unit with a neonatal neurologist. J Child Neurol. 2014;29:31–35.
    1. Clancy RR. The contribution of EEG to the understanding of neonatal seizures. Epilepsia. 1996;37(suppl 1):S52–S59.
    1. Gotman J, Flanagan D, Rosenblatt B, Bye A, Mizrahi EM. Evaluation of an automatic seizure detection method for the newborn EEG. Electroencephalogr Clin Neurophysiol. 1997;103:363–369.
    1. Lawrence R, Mathur A, Nguyen The Tich S, Zempel J, Inder T. A pilot study of continuous limited-channel aEEG in term infants with encephalopathy. J Pediatr. 2009;154:835. 41.e1.
    1. Liu A, Hahn JS, Heldt GP, Coen RW. Detection of neonatal seizures through computerized EEG analysis. Electroencephalogr Clin Neurophysiol. 1992;82:30–37.
    1. Smit LS, Vermeulen RJ, Fetter WP, Strijers RL, Stam CJ. Neonatal seizure monitoring using non-linear EEG analysis. Neuropediatrics. 2004;35:329–335.
    1. Navakatikyan MA, Colditz PB, Burke CJ, Inder TE, Richmond J, Williams CE. Seizure detection algorithm for neonates based on wave-sequence analysis. Clin Neurophysiol. 2006;117:1190–1203.
    1. Deburchgraeve W, Cherian PJ, De Vos M. Automated neonatal seizure detection mimicking a human observer reading EEG. Clin Neurophysiol. 2008;119:2447–2454.
    1. Mitra J, Glover JR, Ktonas PY. A multistage system for the automated detection of epileptic seizures in neonatal electroencephalography. J Clin Neurophysiol. 2009;26:218–226.
    1. Sharpe C, Davis SL, Reiner GE. Assessing the feasibility of providing a real-time response to seizures detected with continuous long-term neonatal electroencephalography monitoring. J Clin Neurophysiol. 2019;36:9–13.
    1. Temko A, Thomas E, Marnane W, Lightbody G, Boylan GB. Performance assessment for EEG-based neonatal seizure detectors. Clin Neurophysiol. 2011;122:474–482.
    1. Temko A, Boylan G, Marnane W, Lightbody G. Robust neonatal EEG seizure detection through adaptive background modeling. Int J Neural Syst. 2013;23
    1. Mathieson SR, Stevenson NJ, Low E. Validation of an automated seizure detection algorithm for term neonates. Clin Neurophysiol. 2016;127:156–168.
    1. Clancy RR, Legido A. The exact ictal and interictal duration of electroencephalographic neonatal seizures. Epilepsia. 1987;28:537–541.
    1. Stevenson NJ, Clancy RR, Vanhatalo S, Rosén I, Rennie JM, Boylan GB. Interobserver agreement for neonatal seizure detection using multichannel EEG. Ann Clin Transl Neurol. 2015;2:1002–1011.
    1. Cherian PJ, Deburchgraeve W, Swarte RM. Validation of a new automated neonatal seizure detection system: a clinician's perspective. Clin Neurophysiol. 2011;122:1490–1499.
    1. Temko A, Lightbody G. Detecting neonatal seizures with computer algorithms. J Clin Neurophysiol. 2016;33:394–402.
    1. de Cordova PB, Phibbs CS, Schmitt SK, Stone PW. Night and day in the VA: associations between night shift staffing, nurse workforce characteristics, and length of stay. Res Nurs Health. 2014;37:90–97.
    1. Pauls LA, Johnson-Paben R, McGready J, Murphy JD, Pronovost PJ, Wu CL. The weekend effect in hospitalized patients: a meta-analysis. J Hosp Med. 2017;12:760–766.
    1. Ching T, Himmelstein DS, Beaulieu-Jones BK. Opportunities and obstacles for deep learning in biology and medicine. J R Soc Interface. 2018;15
    1. Belle A, Kon MA, Najarian K. Biomedical informatics for computer-aided decision support systems: a survey. ScientificWorldJournal. 2013;2013
    1. Temko A, Thomas E, Marnane W, Lightbody G, Boylan G. EEG-based neonatal seizure detection with Support Vector Machines. Clin Neurophysiol. 2011;122:464–473.

Source: PubMed

Sponsors et collaborateurs

Les conditions médicales

Interventions en matière de drogue

3
S'abonner