Jennifer E Lutomski, Sarah Meaney, Richard A Greene, Anthony C Ryan, Declan Devane

Cardiotocography (CTG) records the fetal heart rate in relation to maternal uterine contractions and is one of the most common forms of fetal assessment during labour. Despite guidelines for CTG interpretation, substantial inter- and intra-observer variation in interpretation has been reported among maternity care providers. Misinterpretation of CTG readings can lead to poor decisions, which can result in unnecessary intervention or delay or withholding of necessary intervention. Expert systems (ESs) represent a type of applied artificial intelligence, which can assist in complex clinical decision-making and potentially serve as a mechanism to improve interpretation of fetal heart rate tracings. To evaluate the effectiveness of continuous or intermittent CTG monitoring during labour with an ES compared with (1) continuous or intermittent CTG monitoring during labour without an ES or (2) intermittent auscultation with a Pinard stethoscope or hand-held Doppler ultrasound device. Outcomes of interest included incidence of perinatal mortality, caesarean delivery, operative vaginal birth, fetal blood sampling, artificial rupture of amniotic membranes, oxytocin augmentation of labour, maternal satisfaction with labour, neonatal seizures, fetal acidaemia, hypoxic ischaemic encephalopathy, admission to neonatal special care and/or neonatal intensive care unit and an Apgar score less than seven at five minutes. We searched the Cochrane Pregnancy and Childbirth Group's Trials Register (27 October 2014), Open Grey (6 October 2014) ProQuest Dissertation & Theses Database (6 October 2014) and reference lists of retrieved studies. Randomised and quasi-randomised controlled trials comparing continuous or intermittent CTG monitoring during labour with an ES with continuous or intermittent CTG monitoring without an ES were eligible for this review. Trials comparing continuous or intermittent CTG monitoring during labour with an ES with intermittent auscultation with a Pinard or hand-held Doppler were also eligible. Two review authors independently assessed the eligibility and quality of the trials as well as extracted data to ensure accuracy. The authors of included trials were contacted to clarify aspects of the study design that were not clearly reported in the original trial publications. No studies comparing CTG monitoring during labour with an ES to intermittent auscultation were identified.Two randomised controlled trials comparing CTG monitoring during labour with an ES versus CTG without an ES were identified and included in the qualitative synthesis of results, but only one trial (n = 220) provided data for quantitative analysis. Both trials were classified as low risk of bias.There was no strong evidence that CTG with an ES has an effect on the incidence of caesarean delivery (risk ratio (RR) 0.61; 95% confidence interval (CI) 0.35 to 1.04) when compared with CTG with fetal blood sampling.There was no strong evidence supporting a reduction in the incidence of neonatal seizures (RR 0.33; 95% CI 0.01 to 8.09) or fetal acidaemia (RR 0.50; 95% CI 0.09 to 2.67) in women monitored using a CTG with an ES versus a CTG without an ES. Overall perinatal mortality could not be ascertained for this trial since data on early neonatal deaths were unavailable. Although fetal deaths were recorded, no fetal deaths occurred in either arm of the trial, and thus no risk estimates could be derived.There was no strong evidence supporting a reduction in the incidence of forceps-assisted vaginal birth (RR 0.50; 95% CI 0.05 to 5.43), hypoxic ischaemic encephalopathy (RR 0.33; 95% CI 0.01 to 8.09), admission to the neonatal intensive care unit (RR 0.40; 95% CI 0.08 to 2.02) or an Apgar less than seven at five minutes (RR 0.50; 95% CI 0.13 to 1.95).The trial did not report on artificial rupture of amniotic membranes,oxytocin augmentation of labour ormaternal satisfaction with labour. Two trials met the inclusion criteria for this review but one trial did not provide data for any of this review's outcomes. The single trial that did contribute data was underpowered to evaluate the association between CTG monitoring with an ES and the primary outcomes of interest. No recommendations for clinical practice can be made at this time. Adequately powered trials are necessary before the impact of ESs for fetal assessment in labour can be determined.