Machine learning guided postnatal gestational age assessment using new-born screening metabolomic data in South Asia and sub-Saharan Africa

• Published in: BMC pregnancy and childbirth 2021-09, Vol.21 (1), p.609-609, Article 609
• Main Authors: Sazawal, Sunil, Ryckman, Kelli K, Das, Sayan, Khanam, Rasheda, Nisar, Imran, Jasper, Elizabeth, Dutta, Arup, Rahman, Sayedur, Mehmood, Usma, Bedell, Bruce, Deb, Saikat, Chowdhury, Nabidul Haque, Barkat, Amina, Mittal, Harshita, Ahmed, Salahuddin, Khalid, Farah, Raqib, Rubhana, Manu, Alexander, Yoshida, Sachiyo, Ilyas, Muhammad, Nizar, Ambreen, Ali, Said Mohammed, Baqui, Abdullah H, Jehan, Fyezah, Dhingra, Usha, Bahl, Rajiv
• Format: Article
• Language: English
• Subjects: Africa South of the Sahara - epidemiology; Algorithms; Asia - epidemiology; Cohort Studies; Datasets; Developing Countries; Female; Gestational Age; Humans; Infant, Newborn; Machine Learning; Male; Metabolites; Metabolomics; Neonatal Screening - methods; New born screening; Pre-term births; Pregnancy; Premature birth; Premature Birth - epidemiology; Prospective Studies; ROC Curve; Ultrasonography, Prenatal; Womens health
• ISSN: 1471-2393; 1471-2393
• DOI: 10.1186/s12884-021-04067-y

Babies born early and/or small for gestational age in Low and Middle-income countries (LMICs) 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 examination is not available in these settings, gestational age (GA) is estimated using new-born assessment, last menstrual period (LMP) recalls and birth weight, which are unreliable. Algorithms in developed settings, using metabolic screen data, provided GA estimates within 1-2 weeks of ultrasonography-based GA. We sought to leverage machine learning algorithms to improve accuracy and applicability of this approach to LMICs settings. This study uses data from AMANHI-ACT, a prospective pregnancy cohorts in Asia and Africa where early pregnancy ultrasonography estimated GA and birth weight are available and metabolite screening data in a subset of 1318 new-borns were also 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 (RMSE) 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. Overall model estimated GA had MAE of 5.2 days (95% CI 4.6-6.8), which was similar to performance in SGA, MAE 5.3 days (95% CI 4.6-6.2). GA was correctly estimated to within 1 week for 85.21% (95% CI 72.31-94.65). For preterm birth classification, AUC in ROC analysis was 98.1% (95% CI 96.0-99.0; p