
A new artificial intelligence (AI) system could help doctors find thousands of people with a hidden hormone disorder that often causes high blood pressure. The research was presented at ENDO 2026, the Endocrine Society’s annual meeting in Chicago.
High blood pressure affects millions of people worldwide. Most people are told they have primary hypertension, which means there is no single known cause. However, some people actually have a condition called primary aldosteronism.
This disorder happens when the adrenal glands, located above the kidneys, make too much of a hormone called aldosterone. The extra hormone causes the body to hold on to too much salt while losing potassium. As a result, blood pressure rises and the risk of serious health problems increases.
People with primary aldosteronism have a greater chance of stroke, heart attack, heart failure, kidney disease and abnormal heart rhythms than people with ordinary high blood pressure.
The condition is thought to affect as many as one in five people with hypertension, yet many patients are never tested. The good news is that effective treatments are available, including medication and, in some cases, surgery.
Researchers at Mayo Clinic wanted to improve screening using information that hospitals already collect. They developed an AI model using anonymous electronic health records from more than 22,000 patients collected between 1986 and 2025.
The system examined routine information such as age, sex, blood pressure, potassium levels, medical diagnoses and blood pressure medicines.
The researchers then tested the model using records from more than 225,000 adults with high blood pressure. The AI system was able to predict which patients were likely to have primary aldosteronism up to 12 months before diagnosis.
When the researchers adjusted the model to identify patients at low risk of being missed, it correctly identified more than 90% of cases while missing fewer than 10%. Around two-thirds of patients were selected for further screening.
These findings suggest AI could help doctors decide who should receive additional testing instead of relying on symptoms alone.
The study has several strengths, including its very large dataset and the use of routine medical records that already exist in healthcare systems. However, it was presented at a scientific meeting and still needs further validation in different hospitals before it becomes part of routine clinical practice.
AI also cannot replace a doctor’s diagnosis. Patients flagged by the model would still need standard hormone tests to confirm the condition.
Overall, this study shows that AI may become a practical tool for finding a common but often overlooked cause of high blood pressure earlier, allowing patients to receive treatment before serious complications develop.
If you care about high blood pressure, please read studies that early time-restricted eating could help improve blood pressure, and coconut sugar could help reduce blood pressure and artery stiffness.
For more information about blood pressure, please see recent studies about added sugar in your diet linked to higher blood pressure, and results showing plant-based foods could benefit people with high blood pressure.
Source: Mayo Clinic.


