Obstetric early warning system to predict maternal morbidity of pre-eclampsia, postpartum hemorrhage and infection after birth in high-risk women: a prospective cohort study

Modified Early Obstetric Warning Criteria Predict Maternal Morbidity in the Immediate Postpartum Period: A Case-Control Study

OBJECTIVE

To evaluate the application of Modified Early Obstetric Warning Criteria (MEOWC) in the immediate postpartum period and to generate a preliminary predictive model for postpartum maternal morbidity.

DESIGN

Retrospective case-control study that was conducted from January 2017 to January 2020. A total of 2,762 births occurred during the study period.

SETTING

Obstetrics unit of a general hospital located in the Nakhon Si Thammarat province of Thailand.

PARTICIPANTS

Three hundred charts of complete health records for women in the first 24 hours postbirth were used in the study. Severe maternal morbidity indicators from the Centers for Disease Control and Prevention as well as corresponding International Classification of Diseases, 10th Revision-Clinical Modification codes during birth and postpartum hospitalizations were used to define maternal morbidity. Case and control individuals were matched in an approximate 1:2 fashion based on the year when the birth occurred.

MEASUREMENTS

Outcomes measurement was carried out using three data record forms-personal data, obstetric history, and MEOWC. To estimate the risks, logistic regression was performed, and a receiver operating characteristic curve was derived to evaluate the model's performance.

RESULTS

One hundred cases of maternal morbidity that occurred in the immediate postpartum period were identified and matched with 200 control cases. Women with MEOWC during the immediate postpartum were much more likely to experience subsequent postpartum maternal morbidity than were women without the criteria. MEOWC were a moderate predictor of postpartum maternal morbidity.

CONCLUSION

MEOWC are associated with increased odds of postpartum maternal morbidity. However, these findings should be validated in a prospective cohort to develop a predictive model that is effective for use in immediate postpartum care.

An intelligent adverse delivery outcomes prediction model based on the fusion of multiple obstetric clinical data

Adverse delivery outcomes is a major re-productive health problem that affects the physical and mental health of pregnant women. Obviously, obstetric clinical data has periodically time series characteristics. This paper proposed a three stage adverse delivery outcomes prediction model via the fusion of multiple time series clinical data. The first stage is data aggregation, in which the data set is collected from the obstetric clinical data and divided based on time series features. In the second stage, a multi-channel gated cycle unit is used to solve the calculation error caused by irregular sampling of time series data. The hidden layer feature vector is connected with the fully connected layer, reshaped into a new one-dimensional feature, and fused with the non-time series data into a new data set. The third stage is the prediction stage of adverse delivery outcomes. By connecting the multi-channel gated cycle unit with the extreme gradient lift, the data transmitted in the corresponding channel is used in the feature extraction stage, in which the weighted entropy-based feature extraction is adopted. With the help of the extracted features, a hybrid artificial neural network architecture (MGRU-XGB) was developed to predict adverse delivery outcomes. The experimental results showed that the hybrid model had the best prediction performance for adverse delivery outcomes compared with other single models in terms of sensitivity, specificity, AUC and other evaluation indexes.

Epidemiology and definition of PPH worldwide

Postpartum/peripartum hemorrhage (PPH) is an obstetric emergency complicating 1-10% of all deliveries and is a leading cause of maternal mortality and morbidity worldwide. However, the incidence of PPH differs widely according to the definition and criteria used, the way of measuring postpartum blood loss, and the population being studied with the highest numbers in developing countries. Despite all the significant progress in healthcare, the incidence of PPH is rising due to an incomplete implementation of guidelines, resulting in treatment delays and suboptimal care. A consensus clinical definition of PPH is needed to enable awareness, early recognition, and initiation of appropriate intensive treatment. Unfortunately, the most used definition of PPH based on blood loss ≥500 ml after delivery suffers from inaccuracies in blood loss quantification and is not clinically relevant in most cases, as the amount of blood loss does not fully reflect the severity of bleeding.

Image Analysis Application of Motherwort Total Alkaloid Injection in the Treatment of Postabortion Hemorrhage

In order to reduce the possibility of postabortion hemorrhage leading to maternal death, the author studied the image analysis of postpartum hemorrhage based on Leonurus total alkaloid injection, combining research results, in order to explore the curative effect of Leonurus injection in treating postpartum hemorrhage. After treatment, the time and volume of vaginal bleeding were significantly lower than those in the control group (P < 0.05); it is suggested that the combination of oxytocin and motherwort can effectively reduce the time and volume of vaginal bleeding after medical abortion, conducive to postoperative recovery. The results show that motherwort injection can effectively reduce the amount of bleeding and reduce the risk of postpartum hemorrhage; in addition, adverse reactions have been reduced, and an image analysis consensus has been formed, which is worthy of promotion.