Postpartum hemorrhage prediction method and device, terminal and storage medium

Abstract

The invention is suitable for the technical field of clinical prediction, and provides a postpartum hemorrhage prediction method and device, a terminal and a storage medium, and the method comprises the steps: collecting the clinical data of pregnant and lying-in women according to a preset standard; obtaining a prenatal variable, an intranatal variable and a postnatal variable; constructing a first model based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm in combination with antenatal variables; on the basis of an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm, constructing a second model in combination with the prenatal variable and the intranatal variable; on the basis of an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm, constructing a third model in combination with the prenatal variable and the intranatal variable; and based on the artificial neural network and an extreme gradient propulsion algorithm, constructing a fourth model in combination with the prenatal variable, the intranatal variable and the postnatal variable. The method can accurately and efficiently predict whether postpartum bleeding is caused or not and the severity of bleeding.

Description

technical field [0001] The present application belongs to the technical field of prediction, and in particular relates to a postpartum hemorrhage prediction method, device, terminal and storage medium. Background technique [0002] Postpartum hemorrhage (PPH) can lead to various complications, such as perinatal hysterectomy, multiple organ failure, disseminated intravascular coagulation disorder and Sheehan's syndrome, and even death in severe cases. It can be seen that reducing the rate of postpartum hemorrhage is of great significance for reducing maternal mortality and ensuring the health and safety of mothers and infants. Studies have shown that most deaths related to postpartum hemorrhage can be avoided if appropriate early clinical interventions are taken in a timely manner, including: adequate perinatal preparation, sperm preparation, appropriate timing and method of delivery, timely delivery. rescue, etc. [0003] At the same time, several clinical prediction model...

AI Technical Summary

Problems solved by technology

However, these models were considered to be at high risk of bias due to poor data quality or lack of external validation and insufficient sample size

Furthermore, these models can only individually identify women at high risk for one type of postpartum hemorrhage and cannot accurately predict the severity of postpartum hemorrhage, leading to delays in diagnosis and treatment, and even serious perinatal risks

Images