CHICAGO — A new artificial intelligence (AI) screening model can identify patients at risk for primary aldosteronism 12 months before clinical diagnosis using routine medical record data. Physician and researcher Frank Lee presented these findings at ENDO 2026, the annual meeting of the Endocrine Society, in Chicago.

Primary aldosteronism occurs when the adrenal glands produce excess aldosterone hormone, which helps balance sodium and potassium levels. Patients with this condition face a higher risk of cardiovascular disease than those with primary hypertension. According to Lee, up to 20 percent of patients with hypertension have primary aldosteronism.

The Endocrine Society released a clinical practice guideline in 2025 that recommended more widespread screening for primary aldosteronism. This condition increases the risk of stroke, coronary artery disease, atrial fibrillation, heart failure, and renal disease. Effective treatments for primary aldosteronism exist, and early diagnosis can prevent future complications while reducing healthcare costs.

Researchers developed the AI screening model by utilizing de-identified data from over 22,000 patients collected between 1986 and 2025 within the Mayo Clinic Platform. The model analyzed variables including age, gender, hypertension- and hypokalemia-related ICD diagnoses, systolic blood pressure measurements, potassium blood levels, and prescribed antihypertensive or potassium supplement medications. The team tested the model on data from 225,887 adults with hypertension.

When configured to identify low-risk individuals, the model correctly flagged more than 90 percent of primary aldosteronism cases, missing fewer than 10 percent. At this low-risk threshold configuration, approximately two-thirds of the study participants were identified as candidates for further screening.

Lee stated that the model identified approximately two out of every three patients for further work-up during testing on patients with high blood pressure who had never been screened for primary aldosteronism. He added that the tool could offer a solution that helps clinicians screen for primary aldosteronism effectively, utilizing information already available in a patient's medical records.

No independent assessment of Frank Lee’s claims was available.