AI-enabled electrocardiogram alert for potassium imbalance treatment: a pragmatic randomized controlled trial

Abstract

Life-threatening dyskalemia, defined as an abnormal serum potassium concentration, is common in emergency settings that requires timely recognition and treatment and can be detected via AI-enabled electrocardiography. We conducted a pragmatic, open-label, randomized controlled trial with physician-level randomization to evaluate whether a real-time AI-enabled electrocardiography alert could improve physicians' management of dyskalemia. Over a six-month period in 2022, 70 emergency physicians were randomized (35 intervention, 35 control) and provided care to 14,989 patients (7506 in the intervention group and 7483 in the control group) at an academic medical center and a community hospital (ClinicalTrials.gov NCT05118022). The trial had two primary outcomes: the rate of hyperkalemia-related treatment and hypokalemia-related treatment within three hours. The intervention consisted of a real-time pop-up alert in the electronic health records that categorized patients at risk of moderate-to-severe hyperkalemia (≥6.0 mmol/L) or hypokalemia (≤3.0 mmol/L). Physicians in the control group did not receive alerts. Overall, the rate of hyperkalemia-related treatment was not significantly greater in the intervention group (8.0%) than in the control group (7.7%) (hazard ratio 1.05; 95% CI 0.94-1.17; p = 0.420). Similarly, the rate of hypokalemia-related treatment did not differ significantly (2.1% vs. 2.4%; hazard ratio 0.91; 95% CI 0.74-1.13; p = 0.392). Among patients identified by AI-enabled electrocardiography as having hyperkalemia, however, hyperkalemia-related treatment occurred more frequently in the intervention group (69.1% vs. 41.6%; hazard ratio 2.23; 95% CI 1.44-3.46; p < 0.001). This trial demonstrates that a real-time AI-enabled electrocardiography alert facilitated earlier treatment among patients identified as high risk for hyperkalemia.

Ähnliche Arbeiten