5156 Circulating MicroRNA-based Biomarker Combinations for Differentiating Uni- and Bilateral Primary Aldosteronism Using a Machine Learning Approach

Abstract

Abstract Disclosure: B. Vekony: None. G. Nyiro: None. Z. Herold: None. J. Fekete: None. F. Ceccato: None. S. Gruber: None. L. Kurzinger: None. M. Parasiliti-Caprino: None. B. Szeredas: None. S.K. Nazri: None. V. Fell: None. M. Bassiony: None. E.A. Azizan: None. I. Bancos: None. F. Beuschlein: None. P. Igaz: None. Background: The differentiation of uni- and bilateral forms of primary aldosteronism (PA) is of pivotal clinical relevance. Whereas unilateral PA warrants surgical treatment, bilateral PA is treated by aldosterone antagonists. The most reliable way to differentiate these two entities is adrenal venous sampling (AVS) that is an invasive method with limited availability and requiring great expertise. Aim: To develop a circulating blood-borne microRNA-based approach using machine learning for the differentiation of uni- and bilateral PA. Methods: Circulating microRNA profiling on an Illumina MiSeq platform was performed on total RNA samples isolated from EDTA-anticoagulated blood specimens taken by AVS from 18 pairs of right and left suprarenal veins (10 uni-, 8 bilateral PA). Significantly differentially expressed microRNAs were analyzed by a neural network (90-10% learner-tester cross-validation simulation). From the top 29 significantly differentially expressed microRNAs, 9 were selected for validation by Taqman RT-qPCR on a separate cohort of 30 AVS-confirmed samples (15-15 uni- and bilateral forms) both on plasma samples from adrenal as well as from peripheral veins. The method was finally tested on another independent cohort of peripheral blood samples from 80 patients (40 uni- and 40 bilateral PA). Results: Regarding the 9 microRNAs selected for validation, microRNA abundance was non-significantly lower in peripheral samples compared to AVS samples. By analyzing peripheral plasma samples, ten combinations of 4-8 microRNAs from the pool of 9 microRNAs turned out to have maximal sensitivity and specificity values over 85 %. The best combination included 6 microRNAs with a sensitivity of 86.3 % and a specificity of 87.91 % (AUC = 0.871). The inclusion of further parameters such as imaging, potassium and renin levels did not improve the model’s performance. Conclusion: The analysis of circulating blood-borne microRNAs represents a minimally invasive and potentially reliable way of differentiating uni- and bilateral PA. If bilateral PA is confirmed by the model, no more localization efforts would be necessary thus simplifying the management of PA patients. This would be relevant both from the patient’s and a public health perspective. Presentation: 6/3/2024