A gene combination for predicting preeclampsia risk, preeclampsia risk prediction model and construction method thereof

Abstract

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.

Description

technical field [0001] The invention belongs to the technical field of biomedicine, and particularly relates to a gene combination for predicting the risk of preeclampsia, a preeclampsia risk prediction model and a construction method thereof. Background technique [0002] Preeclampsia refers to increased blood pressure and proteinuria after 20 weeks of pregnancy, and symptoms such as headache, vertigo, nausea, vomiting, and epigastric discomfort may appear. Eclampsia is the progression from preeclampsia to more severe symptoms, causing seizures or coma, which can lead to serious maternal and fetal complications. The incidence of preeclampsia is about 5-10% of pregnant women, and it is more common in primipara, pregnant women with hypertension and vascular disease. Preeclampsia is divided into early-onset and late-onset preeclampsia according to the time of onset. Early-onset preeclampsia refers to the onset of preeclampsia before 34 weeks of gestation. Due to the early on...

AI Technical Summary

Problems solved by technology

The commonly used differentially expressed protein level indicates that the patient has already experienced early pathophysiological changes. In addition, there are many influencing factors on the protein level, and the detection process also has difficulties in preservation and unstable levels.

3. Gene prediction model: Most of the single-gene prediction models in clinical practice are kits developed by foreign gene companies. Due to racial differences in gene loci, they cannot be carried out in my country

4. Comprehensive screening of maternal factors, uterine artery pulsatility index (UtA-PI), mean arterial pressure (MAP) and serum placental growth factor (PlGF) can predict 40% of premature PE and 33% of term PE, which Combined screening is currently the most efficient method recommended by the International Society for the Study of Hypertension in Pregnancy, but the technique of ultrasonic monitoring of uterine arteries requires professional training and is greatly affected by the monitor's operating level, so it has not been widely used

[0006] To sum up, the accuracy of the existing preeclampsia risk prediction models still needs to be improved, and there is a disconnection between all the models and the prevention and treatment of the disease, making it difficult to determine a targeted diagnosis and treatment plan

Images