In Clinical endocrinology ; h5-index 50.0
OBJECTIVE : The clinical practice guideline for primary aldosteronism (PA) places a high value on confirmatory tests to sparing patients with false-positive results in case detection from undergoing adrenal venous sampling (AVS). However, it is unclear whether multiple types of confirmatory tests are more useful than a single type. To evaluate whether the machine-learned combination of two confirmatory tests is more useful in predicting subtypes of PA than each test alone.
DESIGN : A retrospective cross-sectional study in referral centers.
PATIENTS : This study included 615 patients with PA randomly assigned to the training and test datasets. The participants underwent saline infusion test (SIT) and captopril challenge test (CCT) and were subtyped by AVS (unilateral, n = 99; bilateral, n = 516).
MEASUREMENTS : The area under the curve (AUC) and clinical usefulness using decision curve analysis for the subtype prediction in the test dataset.
RESULTS : The AUCs for the combination of SIT and CCT, SIT alone, and CCT alone were 0.850, 0.813, and 0.786, respectively, with no significant differences between them. The AUC for the baseline clinical characteristics alone was 0.872, whereas the AUCs for these combined with SIT, combined with CCT, and combined with both SIT and CCT were 0.868, 0.854, and 0.855, respectively, with no significant improvement in AUC. The additional clinical usefulness of the second confirmatory test was unremarkable on decision curve analysis.
CONCLUSIONS : Our data suggest that patients with positive case detection undergo one confirmatory test to determine the indication for AVS. This article is protected by copyright. All rights reserved.
Kaneko Hiroki, Umakoshi Hironobu, Fukumoto Tazuru, Wada Norio, Ichijo Takamasa, Sakamoto Shohei, Watanabe Tetsuhiro, Ishihara Yuki, Tagami Tetsuya, Ogata Masatoshi, Iwahashi Norifusa, Yokomoto-Umakoshi Maki, Matsuda Yayoi, Sakamoto Ryuichi, Ogawa Yoshihiro
2022-Nov-22
adrenal cortex function tests, adrenocortical adenoma, artificial intelligence, hyperaldosteronism, hypertension, machine learning, renin-angiotensin system
