Abstract
PurposeTo develop and validate a clinical-radiomic nomogram for the preoperative prediction of the aldosterone-producing adenoma (APA) risk in patients with unilateral adrenal adenoma.Patients and MethodsNinety consecutive primary aldosteronism (PA) patients with unilateral adrenal adenoma who underwent adrenal venous sampling (AVS) were randomly separated into training (n = 62) and validation cohorts (n = 28) (7:3 ratio) by a computer algorithm. Data were collected from October 2017 to June 2020. The prediction model was developed in the training cohort. Radiomic features were extracted from unenhanced computed tomography (CT) images of unilateral adrenal adenoma. The least absolute shrinkage and selection operator (LASSO) regression model was used to reduce data dimensions, select features, and establish a radiomic signature. Multivariable logistic regression analysis was used for the predictive model development, the radiomic signature and clinical risk factors integration, and the model was displayed as a clinical-radiomic nomogram. The nomogram performance was evaluated by its calibration, discrimination, and clinical practicability. Internal validation was performed.ResultsSix potential predictors were selected from 358 texture features by using the LASSO regression model. These features were included in the Radscore. The predictors included in the individualized prediction nomogram were the Radscore, age, sex, serum potassium level, and aldosterone-to-renin ratio (ARR). The model showed good discrimination, with an area under the receiver operating characteristic curve (AUC) of 0.900 [95% confidence interval (CI), 0.807 to 0.993], and good calibration. The nomogram still showed good discrimination [AUC, 0.912 (95% CI, 0.761 to 1.000)] and good calibration in the validation cohort. Decision curve analysis presented that the nomogram was useful in clinical practice.ConclusionsA clinical-radiomic nomogram was constructed by integrating a radiomic signature and clinical factors. The nomogram facilitated accurate prediction of the probability of APA in patients with unilateral adrenal nodules and could be helpful for clinical decision making.
Highlights
Primary aldosteronism (PA) is a common cause of secondary hypertension, and the PA prevalence according to hypertension stage is as follows: stage 1, 1.99%; stage 2, 8.02%; and stage 3, 13.2% [1]
Aldosteroneproducing adenoma (APA) was diagnosed in the patients based on the following criteria: 1) a lateralization index (LI) >2.0 at adrenal venous sampling (AVS); 2) a unilateral adrenal nodule on computed tomography (CT) consistent with the LI; and 3) a blood pressure decreases after adrenalectomy or adrenal artery embolization
There were no significant differences in the variables [Radscore, age, sex, serum potassium, estimated glomerular filtration rate, systolic blood pressure (SBP), diastolic blood pressure (DBP), body mass index (BMI), aldosterone-to-renin ratio (ARR) and APA] between the training and validation cohorts (Table 1, P > 0.05), indicating that the use of random seeds to randomly group the total data was reasonable
Summary
Primary aldosteronism (PA) is a common cause of secondary hypertension, and the PA prevalence according to hypertension stage is as follows: stage 1, 1.99%; stage 2, 8.02%; and stage 3, 13.2% [1]. In patients with resistant hypertension, the prevalence rate is higher, nearly 17–23% [2,3,4,5]. In 2008, the Endocrine Society began to recommend the use of adrenal venous sampling (AVS) as a method of localized diagnosis of PA [11]. The process of transforming digital medical images into highdimensional data that can be mined is known as radiomics [14, 15]. Radiomic data contain first-order, second-order, and higher-order statistics. These data, combined with other relevant patient data, can be used as complex bioinformatics mining tools to develop models that may improve the accuracy of diagnosis, prognosis, and prediction [16, 17]. To the best of our knowledge, there are no studies that have determined whether radiomic signatures can predict the risk of APA
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have