Prediction of low 5-minute Apgar scores: development and internal validation of parity-stratified clinical prediction models for sub-Saharan Africa.

backgroundLow 5-minute Apgar scores remain an important indicator of compromised neonatal status and may assist in identifying high-risk newborns in resource-constrained or high-volume labour ward settings. Accurate prediction of newborns at risk could guide timely intrapartum and immediate postpartum interventions. Because risk factors vary by maternal parity, prediction models may benefit from a parity-specific approach. This study aimed to develop and internally validate two prognostic models for predicting low 5-minute Apgar scores, stratified by parity.

methodsThe analysis used data from 124,376 singleton births at or beyond 28 weeks of gestation, recorded between July 2021 and December 2023 across 16 hospitals in Benin, Malawi, Tanzania and Uganda. Model predictors were selected using a knowledge-based approach, and multivariable logistic regression was performed. Model performance was assessed through calibration and discrimination with internal validation conducted using bootstrapping. The predicted outcome was the 5-minute Apgar score, categorised as low (< 7) or normal (≥ 7).

resultsIn the overall study population, 6.3% of newborns received a low Apgar score. The final nulliparous and parous models included 14 and 19 predictor parameters, respectively, with country included as an additional fixed effect. The models demonstrated moderate optimism-adjusted performance, with C-statistics of 0.663 for the nulliparous model (95% CI: 0.654–0.675) and 0.732 for the multiparous model (95% CI: 0.724–0.740). Calibration was excellent in both models, with calibration-in-the-large (CITL) values of 0.000–0.001 and calibration slopes of 0.989–0.995. Antepartum haemorrhage and severe anaemia were the strongest contributors in both models.

conclusionsTwo prediction models for low 5-minute Apgar scores, one for nulliparous and one for parous women, demonstrated moderate predictive ability. External validation and further testing are necessary to assess the generalisability and clinical utility of these models.