Abstract: SA-OR44
Monitoring Serum Potassium Concentration in Patients with Severe Hyperkalemia: The Role of Bloodless Artificial Intelligence (AI)-Assisted Electrocardiography
Session Information
- Fluid, Electrolyte, and Acid-Base Disorders: Clinical Research
November 04, 2023 | Location: Room 111, Pennsylvania Convention Center
Abstract Time: 05:24 PM - 05:33 PM
Category: Fluid, Electrolytes, and Acid-Base Disorders
- 1102 Fluid, Electrolyte, and Acid-Base Disorders: Clinical
Authors
- Chen, Chien-Chou, Tri-Service General Hospital Department of Internal Medicine, Taipei, Taiwan
- Sung, Chih-Chien, Tri-Service General Hospital Department of Internal Medicine, Taipei, Taiwan
- Hsu, Yu-Juei, Tri-Service General Hospital Department of Internal Medicine, Taipei, Taiwan
- Lin, Shih-Hua P., Tri-Service General Hospital Department of Internal Medicine, Taipei, Taiwan
Background
Severe hyperkalemia is a potentially life-threatening emergency requiring prompt recognition with rapid management and surveillance. Although bloodless artificial intelligence (AI)-enabled electrocardiography (ECG) provides real-time detection of severe hyperkalemia, its application to monitor blood potassium (K+) levels during management has not been evaluated. This study aimed to determine the value of AI-enabled ECG (AI-ECG) for blood K+ monitoring in patients with severe hyperkalemia.
Methods
This retrospective cohort study was performed at an emergency department (ED) of a single academic medical center over 2.5 years. Patients with true severe hyperkalemia defined as Lab-K+ ≥ 6.5 mmol/L with matched AI-ECG K+ ≥ 5.1 mmol/L were included. AI-ECG K+ was quantified by ECG12Net as developed previously. The following ECG K+ and Lab-K+ were measured almost simultaneously during or after K+-lowering therapy at least 2 times. Clinical characteristics, therapeutic intervention, and pertinent laboratory data were analyzed.
Results
Seventy-eight patients fulfilled the enrolled criteria. Most of them had acute on chronic kidney injury, advanced CKD not yet on dialysis, and dialysis-dependent renal failure. Their initial Lab-K+ and AI-ECG K+ were 7.2 ± 0.7 and 6.6 ± 0.5 mmol/L, respectively. During and after K+-lowering therapy, both Lab-K+ and ECG-K+ were significantly declined in parallel in the patients both treated medically (n=37) and with hemodialysis group (n=41). Of note, six patients showing persistent ECG-K+ hyperkalemia despite the normalized Lab-K+ levels.
Conclusion
Point-of-care AI-ECG K+ may provide an effective monitoring of blood K+ changes for severe hyperkalemia and also reveal the pseudo-positive patients with the underlying cardiac structure changes or disorders.
Funding
- Private Foundation Support