Abstract
BACKGROUND: Early-life respiratory infections and asthma are major health burdens during childhood. Markers predicting an increased risk for early-life respiratory diseases are sparse. Here, we identified the predictive value of ultrasound-monitored fetal lung growth for the risk of early-life respiratory infections and asthma. METHODS: Fetal lung size was serially assessed at standardized time points by transabdominal ultrasound in pregnant women participating in a pregnancy cohort. Correlations between fetal lung growth and respiratory infections in infancy or early-onset asthma at five years were examined. Machine-learning models relying on extreme gradient boosting regressor or classifier algorithms were developed to predict respiratory infection or asthma risk based on fetal lung growth. For model development and validation, study participants were randomly divided into a training and a testing group, respectively, by the employed algorithm. RESULTS: Enhanced fetal lung growth throughout pregnancy predicted a lower early-life respiratory infection risk. Male sex was associated with a higher risk for respiratory infections in infancy. Fetal lung growth could also predict the risk of asthma at five years of age. We designed three machine-learning models to predict the risk and number of infections in infancy as well as the risk of early-onset asthma. The models' R(2) values were 0.92, 0.90 and 0.93, respectively, underscoring a high accuracy and agreement between the actual and predicted values. Influential variables included known risk factors and novel predictors, such as ultrasound-monitored fetal lung growth. CONCLUSION: Sonographic monitoring of fetal lung growth allows to predict the risk for early-life respiratory infections and asthma.