ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on X

Kidney Week

Abstract: SA-PO0510

Evaluation of Immediate Potassium-Lowering Treatment on Mortality: Role of Artificial Intelligence-Enabled Electrocardiography for Predicting Hyperkalemia and Mortality Risk

Session Information

Category: Fluid, Electrolytes, and Acid-Base Disorders

  • 1102 Fluid, Electrolyte, and Acid-Base Disorders: Clinical

Authors

  • Lin, Shih-Hua P., Tri-Service General Hospital Department of Medicine, Taipei City, Taiwan
  • Lu, Ang, Tri-Service General Hospital Department of Medicine, Taipei City, Taiwan
  • Lin, Chin, Tri-Service General Hospital Department of Medicine, Taipei City, Taiwan
  • Sung, Chih-Chien, Tri-Service General Hospital Department of Medicine, Taipei City, Taiwan
  • Hsu, Yu-Juei, Tri-Service General Hospital Department of Medicine, Taipei City, Taiwan
Background

Although artificial intelligence-enabled electrocardiography (AI-ECG) has been developed to detect hyperkalemia and predict mortality risk rapidly, its application to evaluate the effect of early potassium (K+)-lowering treatment on mortality in patients with hyperkalemia remained unexplored.

Methods

This retrospective cohort study was performed in the emergency department (ED) of a single academic medical center over 10 years. Patients with hyperkalemia (laboratory confirmed Lab-K+ ≥5.5 mEq/L) receiving at least one paired ECG measured within one hour of each other were included. They were divided into two groups based on whether they received early treatment (defined as within 1 hour of the index ECG) or late treatment, greater than 1 hour and less than 8 hours of index ECG. AI-ECG analysis outputs two primary markers: (1) ECG-hyperkalemia positivity and (2) ECG-mortality risk positivity. Data were extracted from the hospital's electronic health records (EHR) system. The primary outcome of interest was all-cause mortality in 30 days.

Results

A total of 2,746 patients with hyperkalemia met the criteria for analysis. Early treatment group (n=1163) had a significantly higher Lab-K+ (6.2 ± 0.7 vs. 6.0 ± 0.6 mEq/L, p < 0.001) than late treatment group (n=1583). In the overall cohort, the adjusted analysis did not reach significant difference in mortality rate between early and late treatment group. As stratified by AI-ECG markers, early treatment did not achieve a significant survival benefit in patients with either ECG-hyperkalemia or ECG-mortality positivity alone or dual negativity but in patients with dual-positivity for ECG-hyperkalemia and ECG-mortality risk (an adjusted hazard ratio of 0.51 (95% CI: 0.33–0.79, p = 0.003), compared to late treatment. Moreover, tests for interaction showed that the effect of timely treatment differed significantly between these subgroups (p for interaction = 0.041).

Conclusion

AI-ECG may provide early treatment benefit in hyperkalemic patients with dual positivity for ECG-hyperkalemia and ECG-mortality risk and aid in guiding decision support in hyperkalemic patients with higher mortality risk.

Digital Object Identifier (DOI)