Evidence · Randomised trial
A machine-learning algorithm for neonatal seizure recognition: a multicentre, randomised, controlled trial.
- Hypoxic-ischaemic encephalopathy and cooling
- Medical
- Neurology
- Nursing
- Seizures
This paper is from 2020, more than five years ago. Newer evidence may have been published since.
Summary
Multicentre randomised controlled trial across eight neonatal centres in Ireland, the Netherlands, Sweden and the UK evaluating ANSeR, a machine-learning seizure detection algorithm used alongside continuous EEG in term and near-term neonates at risk of seizures. It compared clinicians' diagnostic accuracy with and without real-time algorithm support. The algorithm did not improve identification of individual neonates with seizures but improved recognition of seizure hours. The authors suggest benefit may be greater in less experienced centres, though further study is needed.
Summary written for NICUlearn. Always read the original.
- Licence:
- Open (Creative Commons)
The full text of this openly licensed paper is available to NICUlearn members, and Neeky can answer questions from it.
Guidelines are shown for education. Follow your unit's own guidance and senior advice.