Predictive models for estimating the duration of labour induction: A systematic review and critical appraisal.
Toni Gouazé, Alexandra Musso, Jérôme Delotte et al.
✦ AI-curated · Sources linked
In 30 seconds
This systematic review evaluated prediction models for estimating the duration of labor induction, focusing on studies from high-income countries. Nine studies were included, with sample sizes from 204 to 8466 women. The highest externally validated model achieved an area under the ROC curve (AUROC) of 0.81 (95% CI 0.78-0.83), indicating moderate predictive performance.
Key findings
- Reported AUROC for models ranged from 0.73 to 0.88.
- The highest externally validated model had an AUROC of 0.81 (95% CI 0.78-0.83).
- All models were assessed at high or unclear risk of bias.
- Logistic regression was the predominant modelling method used.
Why it matters
Understanding the predictive models for labor induction duration can aid clinicians in making individualized decisions and optimizing resource allocation. However, the current models' limitations highlight the need for improved methodologies.
What to keep in mind
All models were judged at high or unclear risk of bias, primarily due to limitations in the analysis domain.