Down's syndrome screening method based on machine learning at progestational stage and pregnant metaphase

Abstract

The invention relates to a Down's syndrome screening method based on machine learning at the progestational stage and the pregnant metaphase. The method comprises steps that ns fields of pregnant women's Down's screening result data at the pregnant metaphase are selected as training characteristics; Ns samples are added to a data set A; the samples of the data set A are preprocessed to make the number of samples in a minority class set be balanced with the number of samples in a majority class set to obtain a synthetic data set; samples in the synthetic data set are processed to obtain a prediction model for determining whether a fetus has the Down's syndrome, and the prediction model is utilized to predict a tested sample to obtain the prediction result. The method is advantaged in that the process of artificially dividing the indicator threshold is avoided, human resources are saved, and relatively high accuracy and relatively low false positive rate can be achieved.

Description

technical field [0001] The present invention relates to a screening method for Down's syndrome applied in the field of prenatal diagnosis, more specifically, relates to a screening method for Down's syndrome in the pre-pregnancy and second-trimester pregnancy based on machine learning technology. Background technique [0002] Down syndrome named after John Langdon Down, also known as 21-trisomy syndrome or congenital stupidity, is a common severe chromosomal abnormality disease, the incidence rate in newborns is 1 / 1000, and the elderly pregnant women are more than non-advanced The incidence of pregnant women is more than 5 times higher, and increases with age. However, young pregnant women may also give birth to children with Down syndrome, and they account for the vast majority of the total number of pregnant women who give birth. The clinical manifestations of the children are mental retardation, special facial features, hypotonia, and deformities of fingers and toes. Th...

AI Technical Summary

Problems solved by technology

At present, most of the calculation software used for prenatal screening in my country is based on foreign statistical data. Most hospitals use European and American equipment. These prenatal screening risk assessment software are not set for people of yellow race, so there is a problem of low accuracy, while the machine The learning method can analyze and mine electronic medical records to obtain a screening model that conforms to regional characteristics

Images