Nyírő, Gábor

BACKGROUND: Distinguishing between unilateral and bilateral primary aldosteronism, a major cause of secondary hypertension, is crucial due to different treatment approaches. While adrenal venous sampling is the gold standard, its invasiveness, limited availability, and often difficult interpretation pose challenges. This study explores the utility of circulating microRNAs (miRNAs) and machine learning in distinguishing between unilateral and bilateral forms of primary aldosteronism. METHODS: MiRNA profiling was conducted on plasma samples from 18 patients with primary aldosteronism taken during adrenal venous sampling on an Illumina MiSeq platform. Bioinformatics and machine learning identified 9 miRNAs for validation by reverse transcription real-time quantitative polymerase chain reaction. Validation was performed on a cohort consisting of 108 patients with known subdifferentiation. A 30-patient subset of the validation cohort involved both adrenal venous sampling and peripheral, the rest only peripheral samples. A neural network model was used for feature selection and comparison between adrenal venous sampling and peripheral samples, while a deep-learning model was used for classification. RESULTS: Our model identified 10 miRNA combinations achieving >85% accuracy in distinguishing unilateral primary aldosteronism and bilateral adrenal hyperplasia on a 30-sample subset, while also confirming the suitability of peripheral samples for analysis. The best model, involving 6 miRNAs, achieved an area under curve of 87.1%. Deep learning resulted in 100% accuracy on the subset and 90.9% sensitivity and 81.8% specificity on all 108 samples, with an area under curve of 86.7%. CONCLUSIONS: Machine learning analysis of circulating miRNAs offers a minimally invasive alternative for primary aldosteronism lateralization. Early identification of bilateral adrenal hyperplasia could expedite treatment initiation without the need for further localization, benefiting both patients and health care providers.

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. Syed Mohammed 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

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