Feature selection algorithms for predicting preeclampsia: A comparative approach

Preeclampsia is a disease that complicates a large number of pregnancies. In this study, a comparative approach is taken to understand how dimension reduction methods and time-series summary methods can be useful for predicting preeclampsia based on proteomics data. Here, the dimension reduction methods are the Imperialist Competitive Algorithm and the gene clustering method of the Sample Progression Discovery algorithm, the time-series summary methods included a simple overall average and a 3-point summary corresponding to the three trimesters of pregnancy. These approaches achieved similar prediction accuracy around 90% in two independent datasets. Separate analysis of data from each trimester showed an interesting result that it is easier to predict preeclampsia based on proteomics data of the first two trimesters of pregnancy rather than the last trimester.