An AI-driven model using 30 years of EHR data enhances screening for primary aldosteronism, a frequently underdiagnosed hypertension cause.
Key Details
- 1Study presented at ENDO 2026 by Mayo Clinic researchers, using Mayo Clinic Platform data from 1986–2025.
- 2AI model analyzed clinical variables: age, gender, ICD codes for hypertension/hypokalemia, blood pressure, potassium levels, and prescriptions.
- 3Model was developed with over 22,000 patients, tested on 225,887 hypertensive adults.
- 4XGBoost architecture predicted primary aldosteronism risk 12 months before diagnosis.
- 5At low-risk threshold, the model flagged >90% of cases while missing <10%, identifying about two-thirds for further screening.
Why It Matters
This AI tool addresses a major gap in early detection of a serious but often-missed hypertension cause, enabling targeted intervention that can lower cardiovascular morbidity and healthcare costs. The study demonstrates powerful potential for machine-learning models in analyzing routine clinical data to guide large-scale, cost-effective diagnosis in at-risk populations.
Source
EurekAlert
Related News
•EurekAlert
AI-Enhanced Imaging Breaks Barriers in Complex Media for Biomedical Use
Researchers developed a physics-based machine learning imaging system that enhances visibility through complex media, holding promise for biomedical imaging.
•EurekAlert
AI Model Accelerates Accurate Dose Prediction for CyberKnife Radiotherapy
A physics- and spatially informed diffusion model accelerates Monte Carlo–level dose estimation for CyberKnife radiotherapy using planning CT and anatomical data.
•EurekAlert
New G-AUDIT Tool Detects Hidden Bias in Medical AI Training Data
Johns Hopkins and FDA researchers unveil G-AUDIT, a tool to identify hidden biases in medical AI datasets before model training.