Monitoring serum potassium concentration in patients with severe hyperkalemia: the role of bloodless artificial intelligence-enabled electrocardiography

ABSTRACT Background Severe hyperkalemia is a life-threatening emergency requiring prompt management and close surveillance. Although artificial intelligence-enabled electrocardiography (AI-ECG) has been developed to rapidly detect hyperkalemia, its application to monitor potassium (K+) levels remains unassessed. This study aimed to evaluate the effectiveness of AI-ECG for monitoring K+ levels in patients with severe hyperkalemia. Methods This retrospective study was performed at an emergency department of a single medical center over 2.5 years. Patients with severe hyperkalemia defined as Lab-K+ ≥6.5 mmol/l with matched ECG-K+ ≥5.5 mmol/l were included. ECG-K+ was quantified by ECG12Net analysis of the AI-ECG system. The following paired ECG-K+ and Lab-K+ were measured at least twice, almost simultaneously, during and after K+-lowering therapy in 1 day. Clinical characteristics, pertinent intervention, and laboratory data were analyzed. Results Seventy-six patients fulfilling the inclusion criteria exhibited initial Lab-K+ 7.4 ± 0.7 and ECG-K+ 6.8 ± 0.5 mmol/l. Most of them had chronic kidney disease (CKD) or were on chronic hemodialysis (HD). The followed Lab-K+ and ECG-K+ measured with a mean time difference of 11.4 ± 5.6 minutes significantly declined in parallel both in patients treated medically (n = 39) and with HD (n = 37). However, there was greater decrement in Lab-K⁺ (mean 7.3 to 4.1) than ECG-K⁺ (mean 6.6 to 5.0) shortly after HD. Three patients with persistent ECG-K+ hyperkalemia despite normalized Lab-K+ exhibited concomitant acute cardiovascular comorbidities. Conclusions AI-ECG for K+ prediction may help monitor K+ level for severe hyperkalemia and reveal more severe cardiac disorders in the patients with persistent AI-ECG hyperkalemia.