Dataset Information

Predicting Undernutrition at Age 2 Years with Early Attained Weight and Length Compared with Weight and Length Velocity.

ABSTRACT: OBJECTIVE:To estimate the abilities of weight and length velocities vs attained growth measures to predict stunting, wasting, and underweight at age 2 years. STUDY DESIGN:We analyzed data from a community-based cohort study (The Etiology, Risk Factors, and Interactions of Enteric Infections and Malnutrition and the Consequences for Child Health and Development study [MAL-ED] study) in Bhaktapur, Nepal. A total of 240 randomly selected children were enrolled at birth and followed up monthly up to age 24 months. Linear and logistic regression models were used to predict malnutrition at 2 years of age with growth velocity z scores at 0-3, 0-6, 3-6, 6-9, 6-12, and 9-12 months (using the World Health Organization Growth Standards) or attained growth at 0, 3, 6, and 12 months as predictors. RESULTS:At age 2 years, 4% of the children were wasted, 13% underweight, and 21% stunted. Children who were malnourished at age 2 years had lower mean growth z scores already at birth and throughout the study period. Anthropometric indicators in infancy were significant predictors for growth at the age of 2 years during most periods and at most ages in infancy. Weight-for-age z score, length-for-age z score, and weight-for-length z score at age 12 months had excellent areas under the curve (91-95) to predict the value of the same indicator at age 24 months. Maximum area under the curve values for weight and length velocity were somewhat lower (70-84). CONCLUSIONS:Growth measured at one time point in infancy was better correlated with undernutrition at age 2 years than growth velocity.

SUBMITTER: Schwinger C

PROVIDER: S-EPMC5323241 | biostudies-literature | 2017 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting Undernutrition at Age 2 Years with Early Attained Weight and Length Compared with Weight and Length Velocity.

Schwinger Catherine C Fadnes Lars T LT Shrestha Sanjaya K SK Shrestha Prakash Sundar PS Chandyo Ram Krishna RK Shrestha Binob B Ulak Manjeswori M Bodhidatta Ladaporn L Mason Carl C Strand Tor A TA

The Journal of pediatrics 20161212

<h4>Objective</h4>To estimate the abilities of weight and length velocities vs attained growth measures to predict stunting, wasting, and underweight at age 2 years.<h4>Study design</h4>We analyzed data from a community-based cohort study (The Etiology, Risk Factors, and Interactions of Enteric Infections and Malnutrition and the Consequences for Child Health and Development study [MAL-ED] study) in Bhaktapur, Nepal. A total of 240 randomly selected children were enrolled at birth and followed u ...[more]

PMID: 27974166

Similar Datasets

Project description:BackgroundOverweight and atopic dermatitis (AD) are major health problems in most industrialised countries, but the relationship between overweight and AD in infants and young children is unclear. We investigated if weight-for-length at birth, in infancy and at two years, as well as early weight-gain velocity, are associated with the development of AD in early life.MethodsCohort study of infants (n = 642), all living in south-east Norway, hospitalized with acute bronchiolitis (n = 404) or recruited from the general population (n = 238), examined at mean age 5.1 months (enrolment) and at a two-year follow-up visit (n = 499; 78%) at mean age 24.6 months. Exposures were weight-for-length (g/cm) at birth, enrolment and two-year follow-up, and early weight-gain velocity (gram/month from birth to enrolment). Excessive weight-for-length was defined as weight-for-length >95th percentile of WHO child-growth standards. Data on weight-for-length at the three time points were obtained for 435, 428 and 473 children. AD was diagnosed according to the Hanifin & Rajka criteria or from a history of physician-diagnosed AD. We performed multivariate analyses with weight-for-length at birth, at enrolment and at the two-year follow-up visit and with early weight gain velocity for the endpoint AD at each visit.ResultsIn adjusted analyses, excessive weight-for-length at enrolment was associated with concurrent AD (OR 3.03; 95% CI 1.23-7.50) and with AD at two years (OR 2.40; 1.11-5.17). In infants without AD, weight-for-length at enrolment increased the risk of AD at two years, with OR being 1.02 (95% CI 1.00-1.04) per increased gram/cm. AD at two years was not associated with concurrent excessive weight-for-length, nor was AD at any time associated with weight-for-length at birth or with early weight-gain velocity.ConclusionsThe results suggest that overweight in infancy may contribute to the development of AD in early life, highlighting the need for child health-care professionals to address potential overweight and atopic disease when advising infants' caregivers.Trial registrationClinicalTrials.gov number, NCT00817466 , EudraCT number, 2009-012667-34.

Project description:BackgroundUndernutrition among children under the age of five is a major public health concern, especially in developing countries. This study aimed to use machine learning (ML) algorithms to predict undernutrition and identify its associated factors.MethodsSecondary data analysis of the 2017 Multiple Indicator Cluster Survey (MICS) was performed using R and Python. The main outcomes of interest were undernutrition (stunting: height-for-age (HAZ) < -2 SD; wasting: weight-for-height (WHZ) < -2 SD; and underweight: weight-for-age (WAZ) < -2 SD). Seven ML algorithms were trained and tested: linear discriminant analysis (LDA), logistic model, support vector machine (SVM), random forest (RF), least absolute shrinkage and selection operator (LASSO), ridge regression, and extreme gradient boosting (XGBoost). The ML models were evaluated using the accuracy, confusion matrix, and area under the curve (AUC) receiver operating characteristics (ROC).ResultsIn total, 8564 children were included in the final analysis. The average age of the children was 926 days, and the majority were females. The weighted prevalence rates of stunting, wasting, and underweight were 17%, 7%, and 12%, respectively. The accuracies of all the ML models for wasting were (LDA: 84%; Logistic: 95%; SVM: 92%; RF: 94%; LASSO: 96%; Ridge: 84%, XGBoost: 98%), stunting (LDA: 86%; Logistic: 86%; SVM: 98%; RF: 88%; LASSO: 86%; Ridge: 86%, XGBoost: 98%), and for underweight were (LDA: 90%; Logistic: 92%; SVM: 98%; RF: 89%; LASSO: 92%; Ridge: 88%, XGBoost: 98%). The AUC values of the wasting models were (LDA: 99%; Logistic: 100%; SVM: 72%; RF: 94%; LASSO: 99%; Ridge: 59%, XGBoost: 100%), for stunting were (LDA: 89%; Logistic: 90%; SVM: 100%; RF: 92%; LASSO: 90%; Ridge: 89%, XGBoost: 100%), and for underweight were (LDA: 95%; Logistic: 96%; SVM: 100%; RF: 94%; LASSO: 96%; Ridge: 82%, XGBoost: 82%). Age, weight, length/height, sex, region of residence and ethnicity were important predictors of wasting, stunting and underweight.ConclusionThe XGBoost model was the best model for predicting wasting, stunting, and underweight. The findings showed that different ML algorithms could be useful for predicting undernutrition and identifying important predictors for targeted interventions among children under five years in Ghana.

Project description:ImportanceThe American Academy of Pediatrics currently recommends weight for length (WFL) for assessment of weight status in children younger than 2 years but body mass index (BMI) for children older than 2 years. However, the clinical implications of using WFL vs BMI in children younger than 2 years as an indicator of future health outcomes remains understudied.ObjectiveTo compare associations of overweight based on WFL vs BMI in children younger than 2 years with cardiometabolic outcomes during early adolescence.Design, setting, and participantsThis prospective study of birth cohorts in the United States (Project Viva) and Belarus (Promotion of Breastfeeding Intervention Trial [PROBIT]) performed from June 1, 1996, to November 31, 2002, included 13 666 children younger than 2 years.Main exposuresOverweight defined as Centers for Disease Control and Prevention (CDC) WFL in the 95th percentile or greater, World Health Organization (WHO) WFL in the 97.7th percentile or greater, or WHO BMI in the 97.7th percentile or greater at 6, 12, 18, or 24 months of age.Main outcomes and measuresPrimary outcomes were fat mass index, insulin resistance, metabolic risk score, and obesity during early adolescence. Secondary outcomes were height and BMI z scores, sum of skinfolds, waist circumference, and systolic blood pressure during early adolescence.ResultsThe study included 919 children (mean [SD] age, 12.9 [0.9] years; 460 [50.1%] male; and 598 [65.1%] white) from Project Viva and 12 747 children (mean [SD] age, 11.5 [0.5] years; 6204 [48.7%] male; and 12 747 [100%] white) from PROBIT. During 6 to 24 months of age, in Project Viva, 206 children (22.4%) were overweight at any of the 4 times points according to the CDC WFL, 160 (17.4%) according to WHO WFL, and 161 (17.5%) according to WHO BMI cut points. In PROBIT, 3715 children (29.1%) were overweight at any of the 4 time points according to the CDC WFL, 3069 (24.1%) according to WHO WFL, and 3125 (24.5%) according to WHO BMI cut points. After maternal and child characteristics were adjusted for, being ever overweight (vs never overweight) during 6 to 24 months of age was associated with higher likelihood of adverse cardiometabolic risk markers during early adolescence, but associations did not differ substantially across WFL and BMI cut points in either cohort. For example, for fat mass index in Project Viva, β = 0.9 (95% CI, 0.5-1.4) for the CDC WFL, β = 1.1 (95% CI, 0.6-1.6) for WHO WFL, and β = 1.4 (95% CI, 0.9-1.9) for WHO BMI. For PROBIT, β = 0.5 (95% CI, 0.4-0.6) for the CDC WFL, β = 0.6 (95% CI, 0.5-0.7) for WHO WFL, and β = 0.6 (95% CI, 0.5-0.6) for WHO BMI. Neither growth metric in infancy was superior over the others based on F statistics (Project Viva: 17.1-17.8; PROBIT: 87.1-88.7). Findings were similar for insulin resistance, metabolic risk score, obesity, and secondary outcomes.Conclusions and relevanceChoice of WFL vs BMI to define overweight during the first 2 years of life may not greatly affect the association with cardiometabolic outcomes during early adolescence. The findings appear to have important implications for investigators seeking to use BMI as a growth metric for epidemiologic research and for practitioners monitoring the weight status of children younger than 2 years.

Dataset Information

Predicting Undernutrition at Age 2 Years with Early Attained Weight and Length Compared with Weight and Length Velocity.

Publications

Predicting Undernutrition at Age 2 Years with Early Attained Weight and Length Compared with Weight and Length Velocity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets