Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data.

Preeclampsia is a heterogeneous and complex disease associated with rising morbidity and mortality in pregnant women and newborns in the US. Early recognition of patients at risk is a pressing clinical need to reduce the risk of adverse outcomes. We assessed whether information routinely collected in electronic medical records (EMR) could enhance the prediction of preeclampsia risk beyond what is achieved in standard of care assessments. We developed a digital phenotyping algorithm to curate 108,557 pregnancies from EMRs across the Mount Sinai Health System, accurately reconstructing pregnancy journeys and normalizing these journeys across different hospital EMR systems. We then applied machine learning approaches to a training dataset (N = 60,879) to construct predictive models of preeclampsia across three major pregnancy time periods (ante-, intra-, and postpartum). The resulting models predicted preeclampsia with high accuracy across the different pregnancy periods, with areas under the receiver operating characteristic curves (AUC) of 0.92, 0.82, and 0.89 at 37 gestational weeks, intrapartum and postpartum, respectively. We observed comparable performance in two independent patient cohorts. While our machine learning approach identified known risk factors of preeclampsia (such as blood pressure, weight, and maternal age), it also identified other potential risk factors, such as complete blood count related characteristics for the antepartum period. Our model not only has utility for earlier identification of patients at risk for preeclampsia, but given the prediction accuracy exceeds what is currently achieved in clinical practice, our model provides a path for promoting personalized precision therapeutic strategies for patients at risk.

Inpatient Administration of Alpha-1-Adrenergic Receptor Blocking Agents Reduces Mortality in Male COVID-19 Patients.

Apha-1-adrenergic receptor antagonists (α1-blockers) can suppress pro-inflammatory cytokines, thereby potentially improving outcomes among patients with COVID-19. Accordingly, we evaluated the association between α1-blocker exposure (before or during hospitalization) and COVID-19 in-hospital mortality. We identified 2,627 men aged 45 or older who were admitted to Mount Sinai hospitals with COVID-19 between February 24 and May 31, 2020, in New York. Men exposed to α1-blockers (N = 436) were older (median age 73 vs. 64 years, P < 0.001) and more likely to have comorbidities than unexposed men (N = 2,191). Overall, 777 (29.6%) patients died in hospital, and 1,850 (70.4%) were discharged. Notably, we found that α1-blocker exposure was independently associated with improved in-hospital mortality in a multivariable logistic analysis (OR 0.699; 95% CI, 0.498-0.982; P = 0.039) after adjusting for patient demographics, comorbidities, and baseline vitals and labs. The protective effect of α1-blockers was stronger among patients with documented inpatient exposure to α1-blockers (OR 0.624; 95% CI 0.431-0.903; P = 0.012). Finally, age-stratified analyses suggested variable benefit from inpatient α1-blocker across age groups: Age 45-65 OR 0.483, 95% CI 0.216-1.081 (P = 0.077); Age 55-75 OR 0.535, 95% CI 0.323-0.885 (P = 0.015); Age 65-89 OR 0.727, 95% CI 0.484-1.092 (P = 0.124). Taken together, clinical trials to assess the therapeutic value of α1-blockers for COVID-19 complications are warranted.

A comprehensive digital phenotype for postpartum hemorrhage.

OBJECTIVE: We aimed to establish a comprehensive digital phenotype for postpartum hemorrhage (PPH). Current guidelines rely primarily on estimates of blood loss, which can be inaccurate and biased and ignore complementary information readily available in electronic medical records (EMR). Inaccurate and incomplete phenotyping contributes to ongoing challenges in tracking PPH outcomes, developing more accurate risk assessments, and identifying novel interventions. MATERIALS AND METHODS: We constructed a cohort of 71 944 deliveries from the Mount Sinai Health System. Estimates of postpartum blood loss, shifts in hematocrit, administration of uterotonics, surgical interventions, and diagnostic codes were combined to identify PPH, retrospectively. Clinical features were extracted from EMRs and mapped to common data models for maximum interoperability across hospitals. Blinded chart review was done by a physician on a subset of PPH and non-PPH patients and performance was compared to alternate PPH phenotypes. PPH was defined as clinical diagnosis of postpartum hemorrhage documented in the patient's chart upon chart review. RESULTS: We identified 6639 PPH deliveries (9% prevalence) using our phenotype-more than 3 times as many as using blood loss alone (N = 1,747), supporting the need to incorporate other diagnostic and intervention data. Chart review revealed our phenotype had 89% accuracy and an F1-score of 0.92. Alternate phenotypes were less accurate, including a common blood loss-based definition (67%) and a previously published digital phenotype (74%). CONCLUSION: We have developed a scalable, accurate, and valid digital phenotype that may be of significant use for tracking outcomes and ongoing clinical research to deliver better preventative interventions for PPH.

Improving postpartum hemorrhage risk prediction using longitudinal electronic medical records.

OBJECTIVE: Postpartum hemorrhage (PPH) remains a leading cause of preventable maternal mortality in the United States. We sought to develop a novel risk assessment tool and compare its accuracy to tools used in current practice. MATERIALS AND METHODS: We used a PPH digital phenotype that we developed and validated previously to identify 6639 PPH deliveries from our delivery cohort (N = 70 948). Using a vast array of known and potential risk factors extracted from electronic medical records available prior to delivery, we trained a gradient boosting model in a subset of our cohort. In a held-out test sample, we compared performance of our model with 3 clinical risk-assessment tools and 1 previously published model. RESULTS: Our 24-feature model achieved an area under the receiver-operating characteristic curve (AUROC) of 0.71 (95% confidence interval [CI], 0.69-0.72), higher than all other tools (research-based AUROC, 0.67 [95% CI, 0.66-0.69]; clinical AUROCs, 0.55 [95% CI, 0.54-0.56] to 0.61 [95% CI, 0.59-0.62]). Five features were novel, including red blood cell indices and infection markers measured upon admission. Additionally, we identified inflection points for vital signs and labs where risk rose substantially. Most notably, patients with median intrapartum systolic blood pressure above 132 mm Hg had an 11% (95% CI, 8%-13%) median increase in relative risk for PPH. CONCLUSIONS: We developed a novel approach for predicting PPH and identified clinical feature thresholds that can guide intrapartum monitoring for PPH risk. These results suggest that our model is an excellent candidate for prospective evaluation and could ultimately reduce PPH morbidity and mortality through early detection and prevention.

In-hospital use of ACE inhibitors/angiotensin receptor blockers associates with COVID-19 outcomes in African American patients.

BACKGROUNDThe angiotensin-converting enzyme (ACE) D allele is more prevalent among African Americans compared with other races and ethnicities and has previously been associated with severe coronavirus disease 2019 (COVID-19) pathogenesis through excessive ACE1 activity. ACE inhibitors/angiotensin receptor blockers (ACE-I/ARB) may counteract this mechanism, but their association with COVID-19 outcomes has not been specifically tested in the African American population.METHODSWe identified 6218 patients who were admitted into Mount Sinai hospitals with COVID-19 between February 24 and May 31, 2020, in New York City. We evaluated whether the outpatient and in-hospital use of ACE-I/ARB is associated with COVID-19 in-hospital mortality in an African American compared with non-African American population.RESULTSOf the 6218 patients with COVID-19, 1138 (18.3%) were ACE-I/ARB users. In a multivariate logistic regression model, ACE-I/ARB use was independently associated with a reduced risk of in-hospital mortality in the entire population (OR, 0.655; 95% CI, 0.505-0.850; P = 0.001), African American population (OR, 0.44; 95% CI, 0.249-0.779; P = 0.005), and non-African American population (OR, 0.748, 95% CI, 0.553-1.012, P = 0.06). In the African American population, in-hospital use of ACE-I/ARB was associated with improved mortality (OR, 0.378; 95% CI, 0.188-0.766; P = 0.006), whereas outpatient use was not (OR, 0.889; 95% CI, 0.375-2.158; P = 0.812). When analyzing each medication class separately, ARB in-hospital use was significantly associated with reduced in-hospital mortality in the African American population (OR, 0.196; 95% CI, 0.074-0.516; P = 0.001), whereas ACE-I use was not associated with impact on mortality in any population.CONCLUSIONIn-hospital use of ARB was associated with a significant reduction in in-hospital mortality among COVID-19-positive African American patients.FUNDINGNone.