Dataset Information

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 the children in low-to-middle income countries (LMICs) and has been correlated with decline in cognitive capacity and vaccine immunogenicity. Early identification of infants at risk is critical for early intervention and prevention of morbidity. The aim of this study was to investigate patterns of growth in infants up through 48?months of age to assess whether the growth of infants with stunting eventually improved as well as the potential predictors of growth. METHODS:Height-for-age z-scores (HAZ) of children from Matiari (rural site, 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 assessment of growth predictors via traditional machine learning random forest models. RESULTS:Of the 107 children who were followed up till 48?months of age, 51% were stunted (HAZ?

SUBMITTER: Harrison E

PROVIDER: S-EPMC7597024 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning model demonstrates stunting at birth and systemic inflammatory biomarkers as predictors of subsequent infant growth - a four-year prospective study.

Harrison Elizabeth E Syed Sana S Ehsan Lubaina L Iqbal Najeeha T NT Sadiq Kamran K Umrani Fayyaz F Ahmed Sheraz S Rahman Najeeb N Jakhro Sadaf S Ma Jennie Z JZ Hughes Molly M Ali S Asad SA

BMC pediatrics 20201030 1

<h4>Background</h4>Stunting affects up to one-third of the children in low-to-middle income countries (LMICs) and has been correlated with decline in cognitive capacity and vaccine immunogenicity. Early identification of infants at risk is critical for early intervention and prevention of morbidity. The aim of this study was to investigate patterns of growth in infants up through 48 months of age to assess whether the growth of infants with stunting eventually improved as well as the potential p ...[more]

PMID: 33126871

Similar Datasets

Project description:BackgroundPredicting birth weight and identifying its risk factors are clinically important. This study aims to use interpretable machine learning to predict birth weight and identity important predictors.MethodsThis prospective cohort study was conducted in Tongzhou Maternal and Child Health Care Hospital of Beijing, China, recruiting pregnant women between June 2018 and February 2019. We used 24 features to predict infant birth weight, including gestational age, mother's age, parity, history of macrosomia delivery, pre-pregnancy body mass index (BMI), height, father's BMI, lifestyle (diet, physical activity, smoking), and biomarker (fasting glucose and lipids) features. Study outcome was birth weight of infant. We used 8 supervised learning models including 4 individual [linear regression, ridge regression, lasso regression, support vector machines regression (SVR)], and 4 ensemble estimators (random forest, AdaBoost, gradient boosted trees, and voting ensemble for regression) to predict birth weight. Model accuracy was measured by root mean squared error (RMSE) of 10-fold cross validation on the training set and RMSE of prediction on the test set. We used permutation importance algorithm to understand the prediction from the models and what affected them.ResultThis study included 4,754 mother-child dyads. RMSEs were lower in voting ensemble for regression, linear regression, and SVR than random forest, AdaBoost, and gradient boosted tree. The 5 most important predictors for infant birth weight were gestational age, fetal sex, preterm birth, mother's height, and pre-pregnancy BMI. After adding ultrasound-measured indicators of fetal growth into predictors, mother's height and pre-pregnancy BMI remained the most important predictors in predicting the outcome.ConclusionMother's height and pre-pregnancy BMI were identified as important predictors for infant birth weight. Interpretable machine learning is a promising tool in the prediction of birth weight.

Project description:BackgroundThe child nutritional status of a country is a potential indicator of socioeconomic development. Child malnutrition is still the leading cause of severe health and welfare problems across Bangladesh. The most prevalent form of child malnutrition, stunting, is a serious public health issue in many low and middle-income countries. This study aimed to investigate the heterogeneous effect of some child, maternal, household, and health-related predictors, along with the quantiles of the conditional distribution of Z-score for height-for-age (HAZ) of under five children in Bangladesh.Methods and materialsIn this study, a sample of 8,321 children under five years of age was studied from BDHS-2017-18. The chi-square test was mainly used to identify the significant predictors of the HAZ score and sequential quantile regression was used to estimate the heterogeneous effect of the significant predictors at different quantiles of the conditional HAZ distribution.ResultsThe findings revealed that female children were significantly shorter than their male counterparts except at the 75th quantile. It was also discovered that children aged 7-47 months were disadvantaged, but children aged 48-59 months were advantaged in terms of height over children aged 6 months or younger. Moreover, children with a higher birth order had significantly lower HAZ scores than 1st birth order children. In addition, home delivery, the duration of breastfeeding, and the BCG vaccine and vitamin A received status were found to have varied significant negative associations with the HAZ score. As well, seven or fewer antenatal care visits was negatively associated with the HAZ score, but more than seven antenatal care visits was positively associated with the HAZ score. Additionally, children who lived in urban areas and whose mothers were over 18 years and either normal weight or overweight had a significant height advantage. Furthermore, parental secondary or higher education had a significant positive but varied effect across the conditional HAZ distribution, except for the mother's education, at the 50th quantile. Children from wealthier families were also around 0.30 standard deviations (SD) taller than those from the poorest families. Religion also had a significant relationship with the conditional HAZ distribution in favor of non-Muslim children.ConclusionsTo enhance children's nutritional levels, intervention measures should be designed considering the estimated heterogeneous effect of the risk factors. This would accelerate the progress towards achieving the targets of Sustainable Development Goals (SDGs) related to child and maternal health in Bangladesh by 2030.

Dataset Information

Machine learning model demonstrates stunting at birth and systemic inflammatory biomarkers as predictors of subsequent infant growth - a four-year prospective study.

Publications

Machine learning model demonstrates stunting at birth and systemic inflammatory biomarkers as predictors of subsequent infant growth - a four-year prospective study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets