Machine Learning Model Demonstrates Stunting at Birth and Systemic Inflammatory Biomarkers as Predictors of Subsequent Infant Growth – A Four-year Prospective Study.

Abstract

Background: Stunting affects up to one-third of children in low-to-middle income countries (LMICs) and has been correlated with cognitive decline and vaccine immunogenicity. Infants with stunting often have growth refractory to nutritional interventions. Early identification of at-risk infants is critical for early intervention and prevention of subsequent morbidity. The aim of this study was to investigate patterns of growth in infants up through 48 months of age, as well as potential predictors of growth.Methods: Height-for-age z-scores (HAZ) of children from Matiari (rural site in Pakistan) at birth, 18 months, and 48 months were obtained. Results of serum-based biomarkers collected at 6 and 9 months were recorded. A descriptive analysis of the population was followed by biomarker prediction assessment via machine learning methods; random forest classification bins of z-scores and random forest regression for continuous z-scores. Results: Of 107 children who were followed up to 48 months, about half were stunted (HAZ < -2) at birth which increased to 54% by 48 months of age. HAZ at 18 months had a positive linear correlation with HAZ at 48 months, while HAZ at birth was less strongly correlated with HAZ at either 18 or 48 months. Stunting status for the majority of children at 48 months was found to be the same as at 18 months. Most children with large gains started off stunted or severely stunted, while all of those with notably large losses were not stunted at birth. Random forest models identified HAZ at birth as the most important feature in predicting HAZ at 18 months. Of the biomarkers, AGP (Alpha- 1-acid Glycoprotein), CRP (C-Reactive Protein), and IL1 (interleukin-1) were assigned the highest importance rankings across both the classification and regressor models.Conclusion: We demonstrated that HAZ at birth is a strong predictor of subsequent growth in infants up through 48 months of age. Biomarkers of systemic inflammation, AGP, CRP, IL1, were also strong predictors of growth outcomes. These findings provide support for continued focus on interventions at birth and early infancy in children at risk for stunting who live in resource-constrained regions of the world.

Neonatal mortality prediction with routinely collected data: a machine learning approach

“…Machine learning models have provided accurate predictions in a variety of settings such as infant growth [ 4 ], differentiation of sepsis and non-infectious systemic inflammatory response syndrome (SIRS) in critically ill children [ 5 ], and mortality risk in critically-ill patients with cancer [ 5 , 6 ]. Mortality risk prediction can be especially impactful in the case of neonatal mortality [ 7 ], as most cases can be prevented with basic adequate care in low and middle-income countries [ 8 ].…”