Pre-eclampsia (PE) is the main cause of death in maternal and prenatal morbidity. No effective clinical tools could be used for the prediction of PE. A radiomics nomogram based on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) maps was established to predict PE from gestational hypertension (GH).
A total of 138 patients with hypertensive disorders of pregnancy were continuously enrolled in the study prospectively, namely, 58 patients with PE and 80 patients with GH. The patients were randomly divided into a training cohort (
The LASSO analysis finally included 11 radiomics features, which were defined as the radiomics signature. The individualized prediction nomogram was constructed by integrating the radiomics signature, maternal age, and body mass index (BMI). The nomogram exhibited a good performance both in the training cohort [AUC of 0.89 (95% CI, 0.82–0.95)] and test cohort [AUC of 0.85 (95% CI, 0.73–0.97)] for predicting PE from GH. The DCA indicated that clinicians and patients could benefit from the use of radiomics nomogram.
The radiomics nomogram could individually predict PE from GH. The nomogram could be conveniently used to facilitate the treatment decision for clinicians and patients.