Noninvasive estimation of blood potassium concentration using ECG and FCM-ANFIS model

Potassium imbalance, often symptomless but potentially fatal, is prevalent in patients with kidney or heart conditions. Traditional laboratory tests for potassium measurement are costly and require skilled technicians. Additionally, phlebotomy is challenging and painful for high-risk patients. To address these issues, this study proposes a noninvasive and bloodless approach that leverages the electrocardiogram (ECG) signal, which may be sensitive to potassium changes. The research introduces a data-driven framework for ECG-based potassium measurement.

The proposed framework comprises five main components: Cohort Selection—Among 461,178 patients in the ECG-ViEW II database, those with simultaneous ECG, Age-adjusted Charlson Comorbidity Index (ACCI), and potassium measurements within a 5-min interval are chosen; Data Labeling—Three labels—hypokalemia, normal, and hyperkalemia—are defined; Feature Extraction—Relevant features such as RR interval, PR interval, QRS duration, QT interval, QTc interval, P axis, QRS axis, T axis, and ACCI are extracted; Feature Selection—The Kruskal–Wallis technique evaluates feature importance and selects discriminative ones; and Model Design—An ANFIS model based on FCM clustering (FCM-ANFIS) is developed using the selected features.

Among the 42 patients selected during cohort filtering, T axis demonstrated significant association with potassium levels (P < 0.01, r = 0.62). The FCM-ANFIS model exhibited an absolute error of 0.4 ± 0.3 mM, a mean absolute percentage error (MAPE) of 9.99%, and an r-squared value of 0.74. Its classification accuracy reached 85.71%. For detecting hypokalemia and hyperkalemia, sensitivities were 100% and 80%, respectively, while specificities were 88.9% and 97.3%, respectively.

This study advances noninvasive potassium measurement, aiding in timely detection and management of dyskalemias, thus reducing cardiac risks.