Search

Background: Hypertensive disorders of pregnancy (HDP) are significant drivers of maternal and neonatal morbidity and mortality. Current management strategies include early identification and initiation of risk mitigating interventions facilitated by a rules-based checklist. Advanced analytic techniques, such as machine learning, can potentially offer improved and refined predictive capabilities. Objective: To develop and internally validate a machine learning prediction model for hypertensive disorders of pregnancy (HDP) when initiating prenatal care. Study Design: We developed a prediction model using data from the prospective multisite cohort Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b) among low-risk individuals without a prior history of aspirin utilization for preeclampsia prevention. The primary outcome was the development of HDP. Random forest modeling was utilized to develop predictive models. Recursive feature elimination (RFE) was employed to create a reduced model for each outcome. Area under the curve (AUC), 95% confidence intervals (CI), and calibration curves were utilized to assess discrimination and accuracy. Sensitivity analyses were conducted to compare the sensitivity and specificity of the reduced model compared to existing risk factor-based algorithms. Results: Of 9,124 assessed low risk nulliparous individuals, 21% (n=1,927) developed HDP. The prediction model for HDP had satisfactory discrimination with an AUC of 0.73 (95% CI: 0.70, 0.75). After RFE, a parsimonious reduced model with 30 features was created with an AUC of 0.71 (95% CI: 0.68, 0.74). Variables included in the model after RFE included body mass index at the first study visit, pre-pregnancy weight, first trimester complete blood count results, and maximum systolic blood pressure at the first visit. Calibration curves for all models revealed relatively stable agreement between predicted and observed probabilities. Sensitivity analysis noted superior sensitivity (AUC 0.80 vs 0.65) and specificity (0.65 vs 0.53) of the model compared to traditional risk factor-based algorithms. Conclusion: In cohort of low-risk nulliparous pregnant individuals, a prediction model may accurately predict HDP diagnosis at the time of initiating prenatal care and aid employment of close interval monitoring and prophylactic measures earlier in pregnancy.

Abstract Background Although community health worker (CHW) programs focus on improving access to healthcare, some individuals may not receive the intended quality or quantity of an intervention. The objective of this research was to examine if certain populations of pregnant women differentially experience the implementation of a community health worker-led maternal health intervention in Zanzibar. Methods We included pregnant women enrolled in the Safer Deliveries (Uzazi Salama) program, which operated in 10 of 11 districts in Zanzibar, Tanzania between January 1, 2017, and June 19, 2019 (N = 33,914). The outcomes of interest were receipt of the entire postpartum intervention (three CHW visits) and time to first postpartum CHW visit (days). Visits by CHWs were done at the women’s home, however, a telehealth option existed for women who were unable to be reached in-person. We conducted statistical tests to investigate the bivariate associations between our outcomes and each demographic and health characteristic. We used multivariate logistic regression to estimate the relationships between covariates and the outcomes and multivariate linear regression to estimate the association between covariates and the average time until first postpartum visit. Results Higher parity (OR = 0.85; P = 0.014; 95%CI: 0.75–0.97), unknown or unreported HIV status (OR = 0.64; p