The clinical utility of anthropometric measures to assess adiposity in a cohort of prematurely born infants: Correlations with MRI fat quantification

Body composition in preterm infants: a systematic review on measurement methods

BACKGROUND

There are several methods to measure body composition in preterm infants. Yet, there is no agreement on which method should be preferred.

METHODS

PubMed, Embase.com, Wiley/Cochrane Library, and Google Scholar were searched for studies that reported on the predictive value or validity of body composition measurements in preterms, up to 6 months corrected age.

RESULTS

Nineteen out of 1884 identified studies were included. Predictive equations based on weight and length indices, body area circumferences, skinfold thickness, bioelectrical impedance, and ultrasound did not show agreement with body composition measured with air displacement plethysmography (ADP), dual-energy x-ray absorptiometry (DXA), magnetic resonance imaging (MRI), or isotope dilution. ADP agreed well with fat mass density measured by isotope dilution (bias -0.002 g/ml, limits of agreement ±0.012 g/ml, n = 14). Fat mass percentage measured with ADP did not agree well with fat mass percentage measured by isotope dilution (limits of agreement up to ±5.8%) and the bias between measurements was up to 2.2%. DXA, MRI, and isotope dilution were not compared to another reference method in preterms.

CONCLUSIONS

DXA, ADP, and isotope dilution methods are considered trustworthy validated techniques. Nevertheless, this review showed that these methods may not yield comparable results.

IMPACT

Based on validation studies that were conducted in a limited number of study subjects, weight and length indices, body area circumferences, skinfold thickness, bioelectrical impedance, and ultrasound seem to be a poor representation of body composition in preterm infants. DXA, ADP, and isotope dilution methods are considered trustworthy and validated techniques. Nevertheless, these methods may not yield comparable results.

Predictors of Newborn's Weight for Height: A Machine Learning Study Using Nationwide Multicenter Ultrasound Data

There has been no machine learning study with a rich collection of clinical, sonographic markers to compare the performance measures for a variety of newborns’ weight-for-height indicators. This study compared the performance measures for a variety of newborns’ weight-for-height indicators based on machine learning, ultrasonographic data and maternal/delivery information. The source of data for this study was a multi-center retrospective study with 2949 mother–newborn pairs. The mean-squared-error-over-variance measures of five machine learning approaches were compared for newborn’s weight, newborn’s weight/height, newborn’s weight/height² and newborn’s weight/hieght³. Random forest variable importance, the influence of a variable over average node impurity, was used to identify major predictors of these newborns’ weight-for-height indicators among ultrasonographic data and maternal/delivery information. Regarding ultrasonographic fetal biometry, newborn’s weight, newborn’s weight/height and newborn’s weight/height² were better indicators with smaller mean-squared-error-over-variance measures than newborn’s weight/height³. Based on random forest variable importance, the top six predictors of newborn’s weight were the same as those of newborn’s weight/height and those of newborn’s weight/height²: gestational age at delivery time, the first estimated fetal weight and abdominal circumference in week 36 or later, maternal weight and body mass index at delivery time, and the first biparietal diameter in week 36 or later. These six predictors also ranked within the top seven for large-for-gestational-age and the top eight for small-for-gestational-age. In conclusion, newborn’s weight, newborn’s weight/height and newborn’s weight/height² are more suitable for ultrasonographic fetal biometry with smaller mean-squared-error-over-variance measures than newborn’s weight/height³. Machine learning with ultrasonographic data would be an effective noninvasive approach for predicting newborn’s weight, weight/height and weight/height².

Prediction of newborn's body mass index using nationwide multicenter ultrasound data: a machine-learning study

BACKGROUND

This study introduced machine learning approaches to predict newborn's body mass index (BMI) based on ultrasound measures and maternal/delivery information.

METHODS

Data came from 3159 obstetric patients and their newborns enrolled in a multi-center retrospective study. Variable importance, the effect of a variable on model performance, was used for identifying major predictors of newborn's BMI among ultrasound measures and maternal/delivery information. The ultrasound measures included biparietal diameter (BPD), abdominal circumference (AC) and estimated fetal weight (EFW) taken three times during the week 21 - week 35 of gestational age and once in the week 36 or later.

RESULTS

Based on variable importance from the random forest, major predictors of newborn's BMI were the first AC and EFW in the week 36 or later, gestational age at delivery, the first AC during the week 21 - the week 35, maternal BMI at delivery, maternal weight at delivery and the first BPD in the week 36 or later. For predicting newborn's BMI, linear regression (2.0744) and the random forest (2.1610) were better than artificial neural networks with one, two and three hidden layers (150.7100, 154.7198 and 152.5843, respectively) in the mean squared error.

CONCLUSIONS

This is the first machine-learning study with 64 clinical and sonographic markers for the prediction of newborns' BMI. The week 36 or later is the most effective period for taking the ultrasound measures and AC and EFW are the best predictors of newborn's BMI alongside gestational age at delivery and maternal BMI at delivery.

BMI Is a Better Body Proportionality Measure than the Ponderal Index and Weight-for-Length for Preterm Infants

BACKGROUND

Clinicians have observed preterm infants in the neonatal intensive care unit growing disproportionally; however, the only growth charts that have been available were from preterm infants born in the 1950s which utilized the ponderal index. Prior to creating the recently published BMI curves, we found only 1 reference justifying the use of the ponderal index.

OBJECTIVES

To determine the best measure of body proportionality for assessing growth in US preterm infants.

METHODS

Using a dataset of 391,681 infants, we determined the body proportionality measure that was most correlated with weight and least correlated with length. We examined the sex-specific overall correlations and then stratified further by gestational age (GA). We then plotted the body proportionality measures versus length to visualize apparent discrepancies in the appropriate measure.

RESULTS

The overall correlations showed weight/length3 (ponderal index) was the best measure but stratification by GA indicated that BMI (weight/length2) was the best measure. This seeming inconsistency was due to negative correlations between ponderal index and length at each GA. BMI, on the other hand, had a correlation with length across GAs, but was uncorrelated with length within GAs. Both ponderal index and BMI were positively correlated with weight.

CONCLUSIONS

BMI is the appropriate measure of body proportionality for preterm infants, contrary to current practice.