Malhamé I, Danilack VA, Raker CA, et al. - Researchers conducted a retrospective cohort study including a total of 89,681 delivery hospitalizations with the aim to generate and internally validate risk prediction models that may aid in detecting women at risk for cardiovascular severe maternal morbidity (CSMM). Two models were developed and examined, one predicting CSMM at delivery (delivery model) and the other predicting CSMM postpartum following discharge from delivery hospitalization (postpartum CSMM). Eleven variables and 3 interaction terms were included in the delivery model. Gestational hypertension, chronic hypertension, multiple gestation, cardiac lesions or valvular heart disease, maternal age ≥ 40 years and history of poor pregnancy outcome were the strongest predictors. Eight variables were included in the postpartum model. Severe preeclampsia, non‐Hispanic black race/ethnicity, chronic hypertension, gestational hypertension, non‐severe pre‐eclampsia and maternal age ≥ 40 years at delivery were noted to be the strongest predictors. Both these models were appropriately calibrated and performed well on internal validation.