Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Aug 21;3(9):101169.
doi: 10.1016/j.jacadv.2024.101169. eCollection 2024 Sep.

Mortality Risk Stratification Utilizing Artificial Intelligence Electrocardiogram for Hyperkalemia in Cardiac Intensive Care Unit Patients

David M Harmon  1 , Chris K Heinrich  2 , John J Dillon  3 , Rickey E Carter  4 , Kianoush B Kashani  3   5 , Zachi I Attia  1 , Paul A Friedman  1 , Jacob C Jentzer  1   5
Affiliations

Mortality Risk Stratification Utilizing Artificial Intelligence Electrocardiogram for Hyperkalemia in Cardiac Intensive Care Unit Patients

David M Harmon et al. JACC Adv. .

Abstract

Background: Hyperkalemia has been associated with increased mortality in cardiac intensive care unit (CICU) patients. An artificial intelligence (AI) enhanced electrocardiogram (ECG) can predict hyperkalemia, and other AI-ECG algorithms have demonstrated mortality risk-stratification in CICU patients.

Objectives: The authors hypothesized that the AI-ECG hyperkalemia algorithm could stratify mortality risk beyond laboratory serum potassium measurement alone.

Methods: We included 11,234 unique Mayo Clinic CICU patients admitted from 2007 to 2018 with a 12-lead ECG and blood potassium (K) level obtained at admission with K ≥5 mEq/L defining hyperkalemia. ECGs underwent AI evaluation for the probability of hyperkalemia (probability >0.5 defined as positive). Hospital mortality was analyzed using logistic regression, and survival to 1 year was estimated using Kaplan-Meier and Cox analysis.

Results: In the final cohort (n = 11,234), the mean age was 69.6 ± 10.5 years, 37.8% were females, and 92.4% were White. Chronic kidney disease was present in 20.2%. The mean laboratory potassium value for the cohort was 4.2 ± 0.3 mEq/L. The AI-ECG predicted hyperkalemia in 33.9% (n = 3,810) of CICU patients and 12.9% (n = 1,451) of patients had laboratory-confirmed hyperkalemia (K ≥5 mEq/L). In-hospital mortality increased in false-positive, false-negative, and true-positive patients, respectively (P < 0.001), and each of these patient groups had successively lower survival out to 1 year.

Conclusions: 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. This study demonstrated that AI-ECG probability of hyperkalemia may enable rapid individualized risk stratification in critically ill patients beyond laboratory value alone.

Keywords: artificial intelligence; critical care; electrocardiogram; hyperkalemia; outcomes.

PubMed Disclaimer

Conflict of interest statement

Mayo Clinic has licensed the underlying technology to Anumana, a portable, handheld ECG device maker. Mayo Clinic may receive financial benefits from the use of this technology, but at no point will Mayo Clinic benefit financially from its use for the care of patients at Mayo Clinic. Drs Dillon, Attia, and Friedman may also receive financial benefits from this agreement. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose. Data collection and statistical analysis were performed independently by JCJ, who was not involved in developing or validating the proprietary technology and had no financial stake in the technology.

Figures

None
Graphical abstract
Figure 1
Figure 1
Prevalence and Short-term Outcomes of Hyperkalemia as Predicted by AIECG and Measured by Laboratory Analysis Patient flow diagram (Top). Unadjusted cardiac intensive care unit and hospital mortality as it relates to lab hyperkalemia (K >5.0 mEq/L) and artificial intelligence electrocardiogram predicted hyperkalemia (bottom). P < 0.05 across categories. AI-ECG = artificial intelligence electrocardiogram; CICU = cardiac intensive care unit.
Figure 2
Figure 2
Long-term Outcomes of Hyperkalemia as Predicted by AIECG and Measured by Laboratory Analysis Kaplan-Meier 1-year survival curves based on predicted (by artificial intelligence electrocardiogram) and observed (by laboratory confirmation) hyperkalemia. P < 0.0001 between all groups. FN = false negative; FP = false positive; TP = true positive; TN = true negative.
Central Illustration
Central Illustration
Mortality Risk-Stratification in the Cardiac Intensive Care Unit Utilizing an Artificial Intelligence Enhanced Electrocardiogram to Predict Hyperkalemia CICU = cardiac intensive care unit; ECG = electrocardiogram.
See this image and copyright information in PMC

References

    1. Knaus W.A., Draper E.A., Wagner D.P., Zimmerman J.E. Apache II: a severity of disease classification system. Crit Care Med. 1985;13(10):818–829. - PubMed
    1. Brueske B., Sidhu M.S., Schulman-Marcus J., et al. Hyperkalemia is associated with increased mortality among unselected cardiac intensive care unit patients. J Am Heart Assoc. 2019;8(7) - PMC - PubMed
    1. Jentzer J.C., Anavekar N.S., Bennett C., et al. Derivation and validation of a novel cardiac intensive care unit admission risk score for mortality. J Am Heart Assoc. 2019;8(17) - PMC - PubMed
    1. Breen T.J., Brueske B., Sidhu M.S., et al. Abnormal serum chloride is associated with increased mortality among unselected cardiac intensive care unit patients. PLoS One. 2021;16(4) - PMC - PubMed
    1. Breen T., Brueske B., Sidhu M.S., et al. Abnormal serum sodium is associated with increased mortality among unselected cardiac intensive care unit patients. J Am Heart Assoc. 2020;9(2) - PMC - PubMed

LinkOut - more resources