Method for constructing pre-eclampsia risk assessment prediction model, and application thereof

By combining clinical indicators and mean arterial pressure of pregnant women, a new preeclampsia risk assessment prediction model is developed, which solves the problem of inaccurate preeclampsia risk prediction in the prior art, and achieves a highly accurate preeclampsia risk assessment.

WO2025111763A1 Publication Date: 2025-06-05BGI GENOMICS CO LTD +1
6 Cites 3 Cited by

Patent Information

Application Number
PCT/CN2023/134499
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-11-27
Publication Date
2025-06-05

AI Technical Summary

Technical Problem

The prior art is difficult to accurately predict preeclampsia risks in early pregnancy, and the uterine artery pulsation index measurement that requires professional operation limits the wide application of the method.

Method used

Through in-depth study of preeclampsia-related protein markers such as PLGF and IGFBP1 in serum/plasma of pregnant women, combined with clinical indicators and mean arterial pressure in pregnant women, a new predictive model for preeclampsia risk assessment is developed. The model uses logistic regression, multivariate normal distribution, and Bayesian models for training and validation to construct ROC curves to determine risk thresholds.

Benefits of technology

Accurate prediction of preeclampsia risks in early pregnancy is achieved, and the dependence on uterine arterial pulsation index measurement is avoided, and the accuracy of prediction and clinical application value is improved.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Provided in the present invention are a method for constructing a pre-eclampsia risk assessment prediction model, and a prediction product, a prediction system, and a related application of the method. Specifically, the method of the present invention comprises: constructing a logistic regression analysis model on the basis of acquired clinical indexes of a pregnant woman, and obtaining the prior probability of early-onset pre-eclampsia or late-onset pre-eclampsia in the pregnant woman; performing median-of-multiples calibration on an acquired MAP, IGFBP1 and / or PLGF of the pregnant woman, and respectively constructing a multivariate normal distribution model for a sick pregnant woman and a multivariate normal distribution model for a healthy pregnant woman on the basis of an MAP MoM value and an IGFBP1 MoM value and / or a PLGF MoM value, so as to obtain the conditional probability of early-onset pre-eclampsia or late-onset pre-eclampsia in the pregnant woman; and in view of the prior probability and the conditional probability, calculating the posterior probability of early-onset pre-eclampsia or late-onset pre-eclampsia in the pregnant woman on the basis of a Bayesian model. In the present invention, the detection of related protein markers and the obtaining of maternal clinical information data are relatively easy, the accuracy of predicting early-onset pre-eclampsia and late-onset pre-eclampsia is relatively high, and clinical popularization and application are facilitated; therefore, the present invention is of great value to the prevention and early diagnosis of a disease.
Need to check novelty before this filing date? Find Prior Art