A Multicentre Clinical Investigation of a Decision Support Algorithm for Neonatal Seizure Detection

This will be an open, two arm, parallel group, randomised, controlled investigation of the ANSeR Software System as a stand-alone neonatal seizure recognition decision support tool. Term neonates requiring EEG monitoring will be stratified by recruiting site and then randomised to receive either EEG monitoring with the ANSeR Software System or EEG monitoring without the ANSeR Software System. It is proposed that the rate of true detections (sensitivity) of investigation personnel using the ANSeR Software System in clinical practice will be at least 25% higher than that of investigation personnel not using the ANSeR Software System in routine clinical practice. In addition we expect the specificity of investigation personnel using the ANSeR Software System to be no worse than 10% less than that of investigation personnel not using the ANSeR Software System. This should result in more appropriate and timely use of antiepileptic drugs (AED). Randomisation Immediately following enrolment in the investigation, each participant will be randomly assigned to receive either EEG monitoring with the ANSeR Software System or without the ANSeR Software System. Randomisation will be stratified by recruiting site with a 1:1 allocation ratio to each group. Block randomisation with varying block sizes will be used and the randomisation and allocation will be performed centrally using a web-based electronic system. Blinding As this is an investigation of a medical device (software), the investigation personnel will be aware of which group the participant is assigned to. The expert panel who are the diagnostic reference standard will be blinded to group allocation. The biostatistician will also be blinded to group allocation during the analysis of the data.