Gene combination for predicting preeclampsia risk, preeclampsia risk prediction model and construction method of same

Abstract

The invention discloses a gene combination for predicting preeclampsia risk, a preeclampsia risk prediction model and a construction method of same, and belongs to the field of biomedicine. Herein, 499 susceptible genes are screened out through gene polymorphism detection, and 46 clinical detection data are combined, the preeclampsia risk prediction model is made through a computer deep learning method, and then the preeclampsia risk prediction can be realized. Herein, the model design mainly depends on a random forest algorithm in computer machine learning, gene polymorphism detection results and clinical detection data are converted into digital feature vectors required for model construction, the number of decision trees in a random forest is set to be 1000, and a training set is constructed by adopting a replacement random sampling method in the training process; and the out-of-bag error rate samples (unextracted samples) is set as a test set to calculate the error rate of the model.

Description

technical field [0001] The invention belongs to the technical field of biomedicine, and in particular 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 the occurrence of elevated blood pressure and proteinuria after 20 weeks of pregnancy, and symptoms such as headache, vertigo, nausea, vomiting, and upper abdominal discomfort. Eclampsia is the progression from preeclampsia to a more serious condition, causing convulsive 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 primiparous women, pregnant women with high blood pressure and vascular diseases. Preeclampsia is divided into early-onset and late-onset preeclampsia according to the time of onset. Early-onset preeclampsia refers to preeclampsia that occurs before ...

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