Application of intelligent algorithms in Down syndrome screening during second trimester pregnancy.

BACKGROUND: Down syndrome (DS) is one of the most common chromosomal aneuploidy diseases. Prenatal screening and diagnostic tests can aid the early diagnosis, appropriate management of these fetuses, and give parents an informed choice about whether or not to terminate a pregnancy. In recent years, investigations have been conducted to achieve a high detection rate (DR) and reduce the false positive rate (FPR). Hospitals have accumulated large numbers of screened cases. However, artificial intelligence methods are rarely used in the risk assessment of prenatal screening for DS. AIM: To use a support vector machine algorithm, classification and regression tree algorithm, and AdaBoost algorithm in machine learning for modeling and analysis of prenatal DS screening. METHODS: The dataset was from the Center for Prenatal Diagnosis at the First Hospital of Jilin University. We designed and developed intelligent algorithms based on the synthetic minority over-sampling technique (SMOTE)-Tomek and adaptive synthetic sampling over-sampling techniques to preprocess the dataset of prenatal screening information. The machine learning model was then established. Finally, the feasibility of artificial intelligence algorithms in DS screening evaluation is discussed. RESULTS: The database contained 31 DS diagnosed cases, accounting for 0.03% of all patients. The dataset showed a large difference between the numbers of DS affected and non-affected cases. A combination of over-sampling and under-sampling techniques can greatly increase the performance of the algorithm at processing non-balanced datasets. As the number of iterations increases, the combination of the classification and regression tree algorithm and the SMOTE-Tomek over-sampling technique can obtain a high DR while keeping the FPR to a minimum. CONCLUSION: The support vector machine algorithm and the classification and regression tree algorithm achieved good results on the DS screening dataset. When the T21 risk cutoff value was set to 270, machine learning methods had a higher DR and a lower FPR than statistical methods.

Indigenization of the median of markers for Down syndrome screening based on statistical analysis of medical big data.

OBJECTIVE: To indigenize the median of Down syndrome (DS) screening markers for first and second trimester, and compare the impact of the indigenized and built-in median data on the efficiency of DS screening. MATERIALS AND METHODS: Data derived from first and Second-trimester screening (FTS and STS) for DS, composed of selected pregnancies deemed to be normal, were examined in a retrospective study. Indigenization regression analysis was calculated by using five models to fit statistical the raw data. Multiple of median (MoM) values estimated by using indigenized medians were compared with those calculated by using built-in. RESULTS: This study established a regression equation which is more suitable for the median of each screening marker in the local pregnant women. The changes of median MoM of screening markers were statistically significant after indigenization. For FTS, the detection rate was 100% when the false positive rate was 5%, and the cut-off value was 1/262. On the other hand, for STS, the detection rate of the model with indigenized parameters was 77.42%, which is 16.13% higher than that of built-in parameters. CONCLUSION: For the individual specific risk of pregnancy, when the indigenized parameters was used to calculate, is more accurately and screening effectiveness has been improved. This is a great reference significance for the current prenatal screening whether indigenized data should be used.