Application value of a nomogram model based on clinical and MRI features in predicting invasive placenta

Abstract

Purpose: This study was aimed at investigating the value of a nomogram model based on clinical and MRI features in predicting the risk of invasive placenta. Methods: Clinical and imaging data for 162 pregnant women with suspected placenta accreta spectrum disorders (PASDs) were retrospectively analyzed; data for 122 cases were used as a derivation cohort, and data from 40 cases were used as a validation cohort. In the derivation cohort, multivariable logistic regression analyses were conducted to develop a model for predicting invasive placenta. The predictive model was validated in 40 pregnant women, the nomogram was constructed, and the predictive efficiency of the model was evaluated through receiver operating characteristic curve analysis. Results: Ten indicators—prior caesarean delivery, loss of the placental-myometrial interface, myometrial interruption, placental/uterine bulge, marked placental heterogeneity, T2-dark intraplacental bands, abnormal vascularization of the placental bed, intraplacental abnormal vascularization, cervical invasion and bladder invasion—significantly differed between invasive and non-invasive placenta (P<0.05). The independent risk factors for invasive placenta were placental/uterine bulge, loss of the placental-myometrial interface, marked placental heterogeneity and abnormal vascularization of the placental bed. The areas under the curve for the derivation cohort and validation cohort were 0.925 and 0.974, respectively, and the diagnostic coincidence rates were 87.7% and 90.0%, respectively. Conclusion: The nomogram model based on clinical and MRI features effectively predicts invasive placenta.