A hyperaldosteronism subtypes predictive model using ensemble learning.

This study aimed to develop a machine-learning algorithm to diagnose aldosterone-producing adenoma (APA) for predicting APA probabilities. A retrospective cross-sectional analysis of the Japan Rare/Intractable Adrenal Diseases Study dataset was performed using the nationwide PA registry in Japan comprised of 41 centers. Patients treated between January 2006 and December 2019 were included. Forty-six features at screening and 13 features at confirmatory test were used for model development to calculate APA probability. Seven machine-learning programs were combined to develop the ensemble-learning model (ELM), which was externally validated. The strongest predictive factors for APA were serum potassium (s-K) at first visit, s-K after medication, plasma aldosterone concentration, aldosterone-to-renin ratio, and potassium supplementation dose. The average performance of the screening model had an AUC of 0.899; the confirmatory test model had an AUC of 0.913. In the external validation, the AUC was 0.964 in the screening model using an APA probability of 0.17. The clinical findings at screening predicted the diagnosis of APA with high accuracy. This novel algorithm can support the PA practice in primary care settings and prevent potentially curable APA patients from falling outside the PA diagnostic flowchart.

Impact of mineralocorticoid receptor blockade with direct renin inhibition in angiotensin II-dependent hypertensive mice.

It has been suggested that aldosterone breakthrough during treatment with a type 1 angiotensin II receptor (AT1R) blocker (ARB) may be an important risk factor for the progression of renal and cardiovascular disease. We examined whether the direct renin inhibitor, aliskiren caused aldosterone breakthrough in angiotensin II (Ang II)-dependent hypertensive mice. The effect of combination therapy with aliskiren and eplerenone was compared with that of therapy using renin-angiotensin system (RAS) blockade. Tsukuba hypertensive mice were treated for 12 weeks with aliskiren (30 mg/kg/day, i.p), candesartan (5 mg/kg/day, p.o), eplerenone (100 mg/kg/day, p.o) aliskiren and candesartan, aliskiren and eplerenone or candesartan and eplerenone. Blood pressure, urinary aldosterone and angiotensinogen (AGTN) excretion; plasma endothelin-1 concentration; kidney weight; urinary albumin excretion (UAE); glomerular injury; and renal messenger RNA (mRNA) levels for transforming growth factor (TGF)-ß1, plasminogen activator inhibitor (PAI)-1, angiotensin-converting enzyme (ACE) and AT1R were measured. Combination therapy with aliskiren and candesartan caused a further decrease in blood pressure (p < 0.05) compared with either agent alone. Urinary aldosterone excretion was decreased significantly by 4 weeks of treatment with aliskiren or candesartan (p < 0.05). However, it was increased again by treatment with candesartan or aliskiren for 12 weeks. Combination therapy with aliskiren and eplerenone significantly decreased UAE, the glomerulosclerosis index, and PAI-1 and TGF-ß1 mRNA levels compared with all other therapies (p < 0.05). Treatment with aliskiren decreased urinary aldosterone excretion at 4 weeks and increased it at 12 weeks. Combination therapy with a direct renin inhibitor and a mineralocorticoid receptor blocker may be effective for the prevention of renal injury in Ang II-dependent hypertension.