LO
PilotCognitive automation2017-03-21
Computerised interpretation of fetal heart traces in labour did not improve outcomes for mothers or babies across 47,062 women, the INFANT randomised trial found
Midwifeoccupation page →
Event date / reported
2017-03-21
Evidence stage
PilotSmall-scale trial in a real setting. Tells us the deployment conditions are being tested, not that they hold — so one pilot is never enough on its own; two independent ones are.
Tasks this bears on
Monitoring labour
Listening to or tracing the baby's heart rate during labour, reading the trace and deciding when to escalate.
Still human-led✓ Evidence-backed
Where this applies
United Kingdom and Ireland, 24 labour wards that used the decision-support software. 47,062 women having continuous electronic fetal monitoring were randomly assigned to decision support or none; poor neonatal outcome occurred in 0.7 percent of babies in both groups, and the authors conclude computerised interpretation does not improve clinical outcomes for mothers or babies. Clinicians still read the trace; the software advised them.
What this means
A large trial found that computer reading of labour heart traces did not make births safer, so midwives' and doctors' interpretation stays central.
What it does not yet show
One generation of software in the UK and Ireland; newer systems have not yet been tested this way.
What you can check
Open PubMed 28341515 (Lancet, 2017) and find "does not improve clinical outcomes".
Does it change the assessment?
No. The impact index is never moved by a single event. Nor did this record change a layer: all 1 linked judgement above already rested on earlier evidence. This one adds to them.
Source
INFANT Collaborative Group — Computerised interpretation of fetal heart rate during labour (INFANT): a randomised controlled trial, The Lancet (published online 21 March 2017; PubMed 28341515) · verified 2026-10-01 · Claude (VOLO agent) · interpreted 2026-10-01 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.
This record is cited in