JMIR Publications

ABSTRACT

Background:

Digital decision-support tools for labour care remain limited, with few technologies successfully addressing the complex, time-sensitive decisions required during labour triage. Fit4Labour is a clinician-facing, data-driven research tool, currently under development, that combines computerised cardiotocography interpretation with maternal and fetal risk factors to generate individualised risk scores at labour onset. Its primary aim is to support clinicians in identifying fetuses who may require closer monitoring or expedited delivery, while simultaneously providing reassurance in low-risk cases. By promoting consistent communication and timely escalation of care, Fit4Labour seeks to strengthen clinical decision-making. Understanding and addressing usability and implementation barriers will be critical to its adoption in clinical practice.

Objective:

To assess whether the Fit4Labour tool, developed through intensive co-development at a single hospital, maintains usability and implementation readiness when tested in hospitals with differing clinical contexts.

Methods:

We conducted a convergent parallel mixed-methods study in three UK hospitals (December 2022 to May 2025). Phase 1 involved iterative co-development with midwives and doctors at Oxford University Hospitals NHS Foundation Trust; Phase 2 validated the locked version at Birmingham Women’s and Children’s NHS Foundation Trust and Buckinghamshire Healthcare NHS Trust. Midwives and doctors participated in scenario-based usability sessions evaluated with the System Usability Scale (SUS) and Single Ease Question (SEQ) and task completion time to assess efficiency, followed by focus groups and interviews analysed thematically.

Results:

Twenty-six healthcare professionals participated: 12 in co-development (seven midwives, five doctors) and 14 in validation (eight midwives, six doctors). There was an incremental improvement with validation sites having higher SUS scores (85.8 ± 10.2) for the locked version (v4.0) compared to the initial version (1.0) tested in Oxford (77.5 ± 15.1). Task efficiency improved by 16.9% (from a mean of 11.8 to 8 minutes) with a 28% reduction in performance variability, indicating consistent usability across sites. SEQ scores were consistently high (mean 6.1/7.0). Thematic analysis identified 12 themes within three domains: Clinical Integration and Workflow, Technology Adoption and Implementation, and Patient Safety and Decision-Making. Participants described the Fit4Labour tool as a supportive tool, “like a co-pilot”, improving confidence in their decisions with the potential to aid assessment and triage. Perceived limitations included an incomplete risk factor profile and the need for minor technical adjustments or integration with existing hospital systems to facilitate adoption.

Conclusions:

Through systematic co-development, the Fit4Labour tool demonstrated high usability and consistent performance across multiple hospitals, suggesting potential for integration into existing workflows with minimal local adaptation. Clinicians viewed the tool as a supportive aid that enhanced decision-making while preserving clinical autonomy. While further testing in clinical environments is needed, these findings demonstrate that intensive co-design can produce decision-support tools that transfer effectively across hospitals with differing clinical practices. Clinical Trial: NA