Effective Macrosomia Prediction Using Random Forest Algorithm

Abstract

(1) Background: Macrosomia is prevalent in China and worldwide. The current method of predicting macrosomia is ultrasonography. We aimed to develop new predictive models for recognizing macrosomia using a random forest model to improve the sensitivity and specificity of macrosomia prediction; (2) Methods: Based on the Shandong Multi-Center Healthcare Big Data Platform, we collected the prenatal examination and delivery data from June 2017 to May 2018 in Jinan, including the macrosomia and normal-weight newborns. We constructed a random forest model and a logistic regression model for predicting macrosomia. We compared the validity and predictive value of these two methods and the traditional method; (3) Results: 405 macrosomia cases and 3855 normal-weight newborns fit the selection criteria and 405 pairs of macrosomia and control cases were brought into the random forest model and logistic regression model. On the basis of the average decrease of the Gini coefficient, the order of influencing factors was: interspinal diameter, transverse outlet, intercristal diameter, sacral external diameter, pre-pregnancy body mass index, age, the number of pregnancies, and the parity. The sensitivity, specificity, and area under curve were 91.7%, 91.7%, and 95.3% for the random forest model, and 56.2%, 82.6%, and 72.0% for logistic regression model, respectively; the sensitivity and specificity were 29.6% and 97.5% for the ultrasound; (4) Conclusions: A random forest model based on the maternal information can be used to predict macrosomia accurately during pregnancy, which provides a scientific basis for developing rapid screening and diagnosis tools for macrosomia.

Keywords: interspinal diameter; macrosomia; random forest; sacral external diameter; transverse outlet.

Figure 1

Change diagram of the number of decision trees and the average out-of-bag estimated error rate when establishing a random forest model.

Figure 2

The figure of variable importance ranking in the macrosomia random forest prediction model.

Figure 3

The histogram of treesize of the random forest model.

Figure 4

The receiver operating characteristic curve of the three methods. (a) shows the ROC curve of the random forest model in predicting macrosomia. (b) shows the ROC curve of the logistic regression in predicting macrosomia.

Figure 5

The cross-validation results.