A gene combination for predicting preeclampsia risk, a preeclampsia risk prediction model and a construction method thereof belong to the field of biomedicine. The invention uses gene polymorphism detection to screen out 499 susceptibility genes, and combines 46 clinical Detection data, using computer deep learning method to prepare a preeclampsia risk prediction model, can predict the risk of preeclampsia. The model design of the present invention mainly relies on the random forest algorithm in computer machine learning, and the gene polymorphism detection results and clinical detection data are converted into digital feature vectors required for building the model, and the number of decision trees in the random forest is set to 1000 , the training process adopts the random sampling method with replacement to construct the training set, and uses the out-of-bag error rate samples (samples not drawn) as the test set to calculate the error rate of the model.