Acute cardiac care & resuscitation
Mortality Risk Stratification Utilizing Artificial Intelligence Electrocardiogram for Hyperkalemia in Cardiac Intensive Care Unit Patients
Authors' conclusion
AI-ECG-based prediction of hyperkalemia, even with a normal laboratory potassium value, was associated with higher in-hospital mortality and lower 1-year survival in CICU patients.
Study context
- Population
- Mayo Clinic cardiac intensive care unit (CICU) patients with 12-lead electrocardiogram (ECG) and blood K at admission, 2007–2018
- Participants
- 11,234 patients
- Exposure
- AI-ECG prediction of hyperkalemia vs laboratory K
- Outcome
- In-hospital mortality
Methodological detailssingle-centre
- Single-centre
Main finding
As reported in the abstract
- In-hospital mortality increased in false-positive, false-negative and true-positive patients, respectively
- P < 0.001
Observational data: associations, not effects.
Further findings
Survival to 1 year
- Successively lower survival to 1 year in false-positive, false-negative and true-positive patients
Hyperkalemia prevalence · admission
- AI-ECG predicted hyperkalemia
- 33.9% (n = 3,810)
- Laboratory-confirmed hyperkalemia (K ≥5 mEq/L)
- 12.9% (n = 1,451)
- Mean laboratory K
- 4.2 ± 0.3 mEq/L
Original publication
Mortality Risk Stratification Utilizing Artificial Intelligence Electrocardiogram for Hyperkalemia in Cardiac Intensive Care Unit Patients. JACC Adv. Published 21 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →