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

• Published in: Clinica chimica acta 2021-10, Vol.521, p.206-211
• Main Authors: He, Falin, Lin, Bo, Mou, Kai, Jin, Lizi, Liu, Juntao
• Format: Article
• Language: English
• Subjects: Down syndrome; Machine learning; Prenatal screening; Random forest
• ISSN: 0009-8981; 1873-3492
• DOI: 10.1016/j.cca.2021.07.015

•Currently, Antenatal prenatal risk assessment is based on a logistic regression equation or a log Gaussian model.•Few publications in the scientific literature have developed machine learning methods for the prediction of DS in second trimester antenatal screening.•In this study, 58,972 screening data over 10 years were used to establish a machine model to predict Down syndrome, and the machine prediction model could be applied to other laboratories with robust predictive efficacy.•This machine learning model could function as an alternative tool for DS risk assessment in second trimester maternal serum. Down syndrome (DS) is the most common human chromosomal abnormality. About 1200 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%∼65%. A total of 58,972 pregnant women, including 49 DS cases, who had undergone DS screening in the second trimester were retrospectively included and a machine learning (ML) model based on random forest was built 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. The ML model gave a DS detection rate of 66.7%, with a 5% false positive rate in the model data set. In the external verification data set, the ML model achieved a DS detection rate of 85.2%, with a 5% false positive rate . In comparison with the current laboratory risk model, the ML model improves the DS detection rate with the same false positive rate, while the difference has no significance. The ML model for DS detection described here has a comparable detection rate 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 an alternative tool for DS risk assessment in second trimester maternal serum.