A new artificial intelligence model that analyzed 30 years of electronic health records could improve screening for primary aldosteronism, a leading cause of high blood pressure, according to research presented on June 14 at ENDO 2026, the Endocrine Society's annual meeting in Chicago.
Primary aldosteronism occurs when the adrenal glands produce too much aldosterone, a hormone that regulates sodium and potassium levels. This condition increases the risk of cardiovascular disease compared to primary hypertension.
Frank Lee, M.D., of Mayo Clinic in Rochester, Minnesota, said the true prevalence of primary aldosteronism is unknown but estimated that up to 20 percent of patients with hypertension may have it. "Because effective treatments exist for primary aldosteronism, early diagnosis can prevent future complications and reduce healthcare costs," Lee said.
The Endocrine Society released its "Primary Aldosteronism: An Endocrine Society Clinical Practice Guideline" in 2025, calling for more widespread screening. Primary aldosteronism raises the risk of complications such as stroke, coronary artery disease, atrial fibrillation, heart failure, and renal disease.
Researchers used de-identified data from over 22,000 patients collected between 1986 and 2025 through the Mayo Clinic Platform to develop their AI model. The system analyzed variables including age, gender, relevant ICD diagnoses related to hypertension and hypokalemia, systolic blood pressure readings, potassium levels, and prescribed medications. They tested this approach on data from nearly 226,000 adults with hypertension using an XGBoost machine learning architecture to predict those at risk for primary aldosteronism up to one year before diagnosis.
Lee said the results show an AI-based approach may be feasible for screening. At a threshold set to identify people at low risk for the condition, "the model correctly flagged more than 90% of primary aldosteronism cases while missing fewer than 10%. At this setting about two-thirds of study participants were identified as candidates for screening."
