RESUMEN
Objective: To examine adverse delivery outcomes from 2018 to 2019 severe maternal morbidity (SMM) cases that were reviewed by facility-level review committees in Illinois (n = 666) and describe the burden of adverse delivery outcomes among demographic subgroups, SMM etiology, and whether the SMM event was potentially preventable. Materials and Methods: This is a descriptive analysis of the SMM review cohort. Consistent with expert recommendations to identify SMM for hospital quality review, SMM was defined as any intensive care or critical care unit admission and/or transfusion of four or more units of packed red blood cells from conception to 42 days postpartum. Adverse delivery outcomes were fetal death, low birthweight, preterm birth, neonatal intensive care unit admission, and 5-minute Apgar score <7. Chi square and Fisher's exact tests compared maternal demographic and delivery characteristics between the SMM sample and 2018-2019 deliveries in Illinois. Logistic regression modeled the associations between primary cause of morbidity, maternal race/ethnicity, adverse delivery outcomes, and opportunities to alter the outcome to assess whether the burden of adverse birth outcomes was distributed evenly across subcategories of the cohort. Results: Overall, 53.9% of women with SMM had at least one adverse delivery outcome. SMM events owing to preeclampsia/eclampsia (adjusted odds ratio [aOR] = 4.41, 95% confidence interval [CI] = 2.37-8.24) and infection/sepsis (aOR = 4.40, 95% CI = 1.79-11.04) were more likely to be accompanied by adverse delivery outcomes compared with hemorrhage-related SMM. Non-Hispanic Black women with SMM were more likely to have an adverse delivery outcome compared with non-Hispanic White women with SMM (aOR = 1.74, 95% CI = 1.01-3.02). Conclusion: A greater proportion of the SMM review cohort experienced adverse delivery outcomes compared with the overall birthing population in the state. Non-Hispanic Black women with SMM were almost twice as likely to have an adverse delivery outcome compared with non-Hispanic White women.
Asunto(s)
Complicaciones del Embarazo , Nacimiento Prematuro , Embarazo , Recién Nacido , Femenino , Humanos , Nacimiento Prematuro/epidemiología , Illinois/epidemiología , Etnicidad , Complicaciones del Embarazo/epidemiología , Morbilidad , Estudios RetrospectivosRESUMEN
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.