A new formula for optimized weight estimation in extreme fetal macrosomia (≥ 4500 g)

Boosting distributional copula regression

Capturing complex dependence structures between outcome variables (e.g., study endpoints) is of high relevance in contemporary biomedical data problems and medical research. Distributional copula regression provides a flexible tool to model the joint distribution of multiple outcome variables by disentangling the marginal response distributions and their dependence structure. In a regression setup, each parameter of the copula model, that is, the marginal distribution parameters and the copula dependence parameters, can be related to covariates via structured additive predictors. We propose a framework to fit distributional copula regression via model-based boosting, which is a modern estimation technique that incorporates useful features like an intrinsic variable selection mechanism, parameter shrinkage and the capability to fit regression models in high-dimensional data setting, that is, situations with more covariates than observations. Thus, model-based boosting does not only complement existing Bayesian and maximum-likelihood based estimation frameworks for this model class but rather enables unique intrinsic mechanisms that can be helpful in many applied problems. The performance of our boosting algorithm for copula regression models with continuous margins is evaluated in simulation studies that cover low- and high-dimensional data settings and situations with and without dependence between the responses. Moreover, distributional copula boosting is used to jointly analyze and predict the length and the weight of newborns conditional on sonographic measurements of the fetus before delivery together with other clinical variables.

A New Sonographic Weight Estimation Formula for Small-for-Gestational-Age Fetuses

OBJECTIVES

The purpose of this study was to develop a new specific weight estimation formula for small-for-gestational-age (SGA) fetuses that differentiated between symmetric and asymmetric growth patterns.

METHODS

A statistical estimation technique known as component-wise gradient boosting was applied to a group of 898 SGA fetuses (symmetric, n = 750; asymmetric, n = 148). A new formula was derived from the data obtained and was then compared to other commonly used equations.

RESULTS

The new formula derived is as follows: estimated fetal weight = e^[1.3734627 + 0.0057133 × biparietal diameter + 0.0011282 × head circumference + 0.0201147 × abdominal circumference + 0.0183081 × femur length - 0.0000177 × biparietal diameter(2) - 0.0000018 × head circumference(2) - 0.0000297 × abdominal circumference(2) -0.0001007 × femur length(2) + 0.0397563 × I(sex = male) + 0.0064505 × gestational age (days) + 0.0096528 × I(SGA = asymmetric)], where the function I denotes an indicator function, which is 1 if the expression is fulfilled (sex = male; SGA type = asymmetric) and otherwise 0. In the whole study group and the 2 subgroups, the new formula showed the lowest median absolute percentage error, mean percentage error, and random error and the best distribution of absolute percentage errors within prespecified error bounds.

CONCLUSIONS

The new formula substantially improves weight estimation in SGA fetuses.