External validation of machine learning models including newborn metabolomic markers for postnatal gestational age estimation in East and South-East Asian infants.

Autor: Hawken S; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada.; School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada., Murphy MSQ; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada., Ducharme R; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada., Bota AB; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada., Wilson LA; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada., Cheng W; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada., Tumulak MJ; Newborn Screening Reference Centre, University of the Philippines Manila, Manila, Philippines., Alcausin MML; Newborn Screening Reference Centre, University of the Philippines Manila, Manila, Philippines., Reyes ME; Newborn Screening Reference Centre, University of the Philippines Manila, Manila, Philippines., Qiu W; Pediatric Endocrinology and Genetic Metabolism, XinHua Hospital, Shanghai, Shanghai, China., Potter BK; School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada., Little J; School of Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada., Walker M; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada.; Better Outcomes Registry & Network, Ottawa, Canada., Zhang L; Department of Gynecology and Obsetrics, XinHua Hospital, Shanghai, Shanghai, China.; MOE-Shanghai Key Lab of Children's Environmental Health, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China., Padilla C; Department of Pediatrics, University of the Philippines Manila, Manilla, Philippines.; Institute of Human Genetics, National Institutes of Health, University of Philippines Manila, Manila, Philippines., Chakraborty P; Newborn Screening Ontario, Children's Hospital of Eastern Ontario, Ottawa, ON, Canada.; Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada., Wilson K; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada.; Department of Medicine, University of Ottowa, Ottowa, ON, Canada.; Bruyère Research Institute, Ottowa, ON, Canada.
Jazyk: angličtina
Zdroj: Gates open research [Gates Open Res] 2021 Jun 21; Vol. 4, pp. 164. Date of Electronic Publication: 2021 Jun 21 (Print Publication: 2020).
DOI: 10.12688/gatesopenres.13131.2
Abstrakt: Background:  Postnatal gestational age (GA) algorithms derived from newborn metabolic profiles have emerged as a novel method of acquiring population-level preterm birth estimates in low resource settings. To date, model development and validation have been carried out in North American settings. Validation outside of these settings is warranted.   Methods:  This was a retrospective database study using data from newborn screening programs in Canada, the Philippines and China. ELASTICNET machine learning models were developed to estimate GA in a cohort of infants from Canada using sex, birth weight and metabolomic markers from newborn heel prick blood samples. Final models were internally validated in an independent sample of Canadian infants, and externally validated in infant cohorts from the Philippines and China.  Results:  Cohorts included 39,666 infants from Canada, 82,909 from the Philippines and 4,448 from China.  For the full model including sex, birth weight and metabolomic markers, GA estimates were within ±5 days of ultrasound values in the Canadian internal validation (mean absolute error (MAE) 0.71, 95% CI: 0.71, 0.72), and within ±6 days of ultrasound GA in both the Filipino (0.90 (0.90, 0.91)) and Chinese cohorts (0.89 (0.86, 0.92)). Despite the decreased accuracy in external settings, our models incorporating metabolomic markers performed better than the baseline model, which relied on sex and birth weight alone. In preterm and growth-restricted infants, the accuracy of metabolomic models was markedly higher than the baseline model. Conclusions:  Accuracy of metabolic GA algorithms was attenuated when applied in external settings.  Models including metabolomic markers demonstrated higher accuracy than models using sex and birth weight alone. As innovators look to take this work to scale, further investigation of modeling and data normalization techniques will be needed to improve robustness and generalizability of metabolomic GA estimates in low resource settings, where this could have the most clinical utility.
Competing Interests: No competing interests were disclosed.
(Copyright: © 2021 Hawken S et al.)
Databáze: MEDLINE