Prediction of hyperaldosteronism subtypes when adrenal vein sampling is unilaterally successful

Abstract

Objective – Adrenal venous sampling (AVS) is the gold standard to discriminate patients with unilateral primary aldosteronism (UPA) from bilateral disease (BPA). AVS is technically-demanding and in cases of unsuccessful cannulation of adrenal veins, the results may not be interpreted. The aim of our study was to develop diagnostic models to distinguish UPA from BPA, in cases of unilateral successful AVS and the presence of contralateral suppression of aldosterone secretion. Design – Retrospective evaluation of 158 patients referred to a tertiary hypertension unit who underwent AVS. We randomly assigned 110 patients to a training cohort and 48 patients to a validation cohort to develop and test the diagnostic models. Methods – Supervised machine learning algorithms and regression models were used to develop and validate two prediction models and a 19-point score system to stratify patients according to subtype diagnosis. Results – Aldosterone levels at screening and after confirmatory testing, lowest potassium, ipsilateral and contralateral imaging findings at CT scanning, and contralateral ratio at AVS, were associated with a diagnosis of UPA and were included in the diagnostic models. Machine learning algorithms correctly classified the majority of patients both at training and validation (accuracy 82.9-95.7%). The score system displayed a sensitivity/specificity of 95.2/96.9%, with an AUC of 0.971. A flow-chart integrating our score correctly managed all patients except 3 (98.1% accuracy), avoiding the potential repetition of 77.2% of AVS. Conclusions – Our score could be integrated in clinical practice and guide decision-making in patients with unilateral successful AVS and contralateral suppression.

The Accuracy of Simple and Adjusted Aldosterone Indices for Assessing Selectivity and Lateralization of Adrenal Vein Sampling in the Diagnosis of Primary Aldosteronism Subtypes

“…Without a bilaterally selective procedure, the LI, which is the most widely accepted index in the literature, is not applicable to guide the diagnosis of lateralization of aldosterone hypersecretion and the subsequent opportunity of surgical treatment. Therefore, the introduction of unconventional indices and statistical models ( 25 – 27 , 37 , 38 ) could help in determining the lateralization of aldosterone secretion in case of suboptimal AVS. Our group recently demonstrated the high accuracy of corrected unconventional indices in the prediction of unilateral disease in a large series of patients with PA subtyped with AVS ( 27 ).…”

“…Therefore, during last years, some authors proposed the use of simple unconventional indices with a moderate (19,20), and often not reproducible, accuracy for determining PA lateralization (21)(22)(23)(24). Most recently, Burrello et al developed two scores (25,26) for predicting PA subtypes, using a machine learning approach and reaching a high accuracy; similarly, our group proposed the use of adjusted unconventional AVS indices in order to determine the lateralization of aldosterone secretion when adrenal vein cannulation is not bilaterally selective (27).…”

“…Most recently, Burrello et al. developed two scores ( 25 , 26 ) for predicting PA subtypes, using a machine learning approach and reaching a high accuracy; similarly, our group proposed the use of adjusted unconventional AVS indices in order to determine the lateralization of aldosterone secretion when adrenal vein cannulation is not bilaterally selective ( 27 ).…”

A new machine learning-based prediction model for subtype diagnosis in primary aldosteronism

“…To find an optimal prediction model, five supervised machine learning classifiers were used, including random forest (RF), support vector machines (SVM), gradient boosting decision tree (GBDT), logistic regression (LR), and AdaBoost. First, all possible available variables were used to build models, according to previous research reports ( 7 , 10 , 11 ). Two parameters, urinary PAC and PRA after the furosemide standing test, were removed due to their low importance for the prediction model, relatively poor availability, and absence from the external validation dataset.…”

Best Achievements in Pituitary and Adrenal Diseases in 2020

“…This clinical score can be used to subtype primary aldosteronism when adrenal vein sampling is unavailable or fails. Another study suggested a clinical prediction score to subtype primary aldosteronism when adrenal vein sampling is only unilaterally successful [16]. The contralateral ratio (ratio of aldosterone/cortisol in the contralateral adrenal vein to that in the peripheral vein), in addition to aldosterone levels, potassium levels, and CT imaging, showed a high diagnostic value, with an area under the receiver operating characteristic curve of 0.971.…”