A machine learning model for the prediction of down syndrome in second trimester antenatal screening.

Abstract Background Down syndrome (DS) is the most common human chromosomal abnormality. About 1,200 laboratories carry out antenatal screening for DS in second trimester pregnancies in China. Their prenatal assessment of DS pregnancy risk is based on biometric calculations conducted on maternal serum biochemical markers and ultrasonic markers of fetal growth. However, the performance of this triple test for DS in second trimester pregnancies has a false positive rate of 5%, and a detection rate of about 60%. Method A total of 58,975 pregnant women, including 49 DS cases, who had undergone DS screening in the second trimester were retrospectively included and a machine learning (ML) model was designed to predict DS. In addition, the model was applied to another hospital data set of 27,170 pregnant women, including 27 DS cases, to verify the predictive efficiency of the model. Results The ML model gave a DS detection rate of 66.67%, with a 5% false positive rate and a 1.33% positive prediction value in the model data set. In the external verification data set, the ML model achieved a DS detection rate of 85.19%, with a 5% false positive rate and a 1.61% positive prediction value. In comparison with the current laboratory risk model, the ML model improves the DS detection rate and the positive prediction value with the same false positive rate. Conclusions The ML model for DS detection described here has a higher detection rate and positive prediction value with the same false positive rate as the DS risk screening software currently used in China. Our ML model exhibited robust performance and good extrapolation, and could function as a useful tool for DS risk assessment in second trimester maternal serum.