Machine Learning Guided Postnatal Gestational Age Assessment Using Newborn Screening Metabolomic Data in South Asia and Sub-Saharan Africa

Le résumé fourni par la source

Abstract Background: Babies born early and/or small for gestational age in Low- and Middle-income countries (LMIC) contribute substantially to global neonatal and infant mortality. Tracking this metric is critical at a population level for informed policy, advocacy, resources allocation and program evaluation and at an individual level for targeted care. Early prenatal ultrasound is not available in these settings, gestational age (GA) is estimated using newborn assessment, LMP recalls and birth weight, which are unreliable. Algorithms in developed settings, using metabolic screen data, provided GA estimates within 1-2 weeks of ultrasound-based GA. We sought to leverage machine learning algorithms to improve accuracy and applicability of this approach to LMIC settings.Methods: This study uses data from AMANHI-ACT prospective pregnancy cohorts in Asia and Africa where early pregnancy ultrasound estimated GA and birth weight are available and metabolite screening data in a subset of 1318 newborn are available. We utilized this opportunity to develop machine learning (ML) algorithms. Random Forest Regressor was used where data was randomly split into model-building and model-testing dataset. Mean absolute error (MAE) and root mean square error (RSME) were used to evaluate performance. Bootstrap procedures were used to estimate confidence intervals (CI) for RMSE and MAE. For pre-term birth identification ROC analysis with bootstrap and exact estimation of CI for area under curve (AUC) were performed.Results: Overall model estimated GA, had MAE of 5.8 days (95%CI 5.6-6.3), which was similar to performance in SGA, MAE 6.3 days (95%CI 5.6-7.0). GA was correctly estimated to within 1 week for 70.9% (95%CI 67.9-73.7). For preterm birth classification, AUC in ROC analysis was 92.6% (95%CI 87.5-96.1; p<0.001). This model performed better than Iowa regression, AUC Difference 2.8% (95%CI 0.9-11.8%; p=0.021).Conclusions: Machine learning algorithms and models applied to metabolomic gestational age dating offer a ladder of opportunity for providing accurate population-level gestational age estimates in LMIC settings. These findings also point to an opportunity for investigation of region-specific models, more focused feasible analyte models, and broad untargeted metabolome investigation.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.