TY - JOUR
T1 - A machine-learning algorithm for neonatal seizure recognition
T2 - a multicentre, randomised, controlled trial
AU - Pavel, Andreea M
AU - Rennie, Janet M
AU - de Vries, Linda S
AU - Blennow, Mats
AU - Foran, Adrienne
AU - Shah, Divyen K
AU - Pressler, Ronit M
AU - Kapellou, Olga
AU - Dempsey, Eugene M
AU - Mathieson, Sean R
AU - Pavlidis, Elena
AU - van Huffelen, Alexander C
AU - Livingstone, Vicki
AU - Toet, Mona C
AU - Weeke, Lauren C
AU - Finder, Mikael
AU - Mitra, Subhabrata
AU - Murray, Deirdre M
AU - Marnane, William P
AU - Boylan, Geraldine B
N1 - Funding Information:
This study was funded by a Wellcome Trust Strategic Translational Award (098983) and a Science Foundation Ireland Research Centre Award (12/RC/2272). Nihon Kohden provided EEG monitors for the purpose of this trial. We are extremely grateful for the dedication of our research support team, particularly Jackie O'Leary, Mairead Murray, Jean Conway, Taragh Kiely, and Denis Dwyer (INFANT Research Centre, University College Cork, Cork, Ireland), and Nicola Openshaw-Lawrence (Homerton University Hospital NHS Foundation Trust, London, UK), Jessica Colby-Milley (Rotunda Hospital, Dublin, Ireland), and Ingela Edqvist (Department of Neonatal Medicine, Karolinska University Hospital, Stockholm, Sweden). We thank all of the engineers involved in the development of the algorithm, particularly Andrey Temko and Gordon Lightbody (INFANT Research Centre, University College Cork, Cork, Ireland), and also the clinical teams at all their institutions for supporting the research study. We also thank University College Cork for sponsoring this clinical investigation. We especially thank the families of all neonates included in this trial.
Funding Information:
RMP reports personal fees from UCB Pharma (outside the submitted work). WPM and GBB report grants from the Wellcome Trust and non-financial support from Nihon Kohden (during the conduct of the study), and have a patent A Method of Analysing an Electroencephalogram (EEG) Signal issued. All other authors declare no competing interests.
Publisher Copyright:
© 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license
PY - 2020/10
Y1 - 2020/10
N2 - 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.
AB - 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.
KW - Algorithms
KW - Electroencephalography/methods
KW - Humans
KW - Infant
KW - Intensive Care, Neonatal
KW - Ireland
KW - Machine Learning/statistics & numerical data
KW - Monitoring, Physiologic/methods
KW - Netherlands
KW - Seizures/diagnosis
KW - Sweden
KW - United Kingdom
UR - http://www.scopus.com/inward/record.url?scp=85090487426&partnerID=8YFLogxK
U2 - 10.1016/S2352-4642(20)30239-X
DO - 10.1016/S2352-4642(20)30239-X
M3 - Article
C2 - 32861271
SN - 2352-4642
VL - 4
SP - 740
EP - 749
JO - The Lancet. Child & adolescent health
JF - The Lancet. Child & adolescent health
IS - 10
ER -