Point-of-care artificial intelligence-enabled ECG for dyskalemia: a retrospective cohort analysis for accuracy and outcome prediction

Abstract

Dyskalemias are common electrolyte disorders associated with high cardiovascular risk. Artificial intelligence (AI)-assisted electrocardiography (ECG) has been evaluated as an early-detection approach for dyskalemia. The aims of this study were to determine the clinical accuracy of AI-assisted ECG for dyskalemia and prognostic ability on clinical outcomes such as all-cause mortality, hospitalizations, and ED revisits. This retrospective cohort study was done at two hospitals within a health system from May 2019 to December 2020. In total, 26,499 patients with 34,803 emergency department (ED) visits to an academic medical center and 6492 ED visits from 4747 patients to a community hospital who had a 12-lead ECG to estimate ECG-K⁺ and serum laboratory potassium measurement (Lab-K⁺) within 1 h were included. ECG-K⁺ had mean absolute errors (MAEs) of ≤0.365 mmol/L. Area under receiver operating characteristic curves for ECG-K⁺ to predict moderate-to-severe hypokalemia (Lab-K⁺ ≤3 mmol/L) and moderate-to-severe hyperkalemia (Lab-K⁺ ≥ 6 mmol/L) were >0.85 and >0.95, respectively. The U-shaped relationships between K⁺ concentration and adverse outcomes were more prominent for ECG-K⁺ than for Lab-K⁺. ECG-K⁺ and Lab-K⁺ hyperkalemia were associated with high HRs for 30-day all-cause mortality. Compared to hypokalemic Lab-K⁺, patients with hypokalemic ECG-K⁺ had significantly higher risk for adverse outcomes after full confounder adjustment. In addition, patients with normal Lab-K⁺ but dyskalemic ECG-K⁺ (pseudo-positive) also exhibited more co-morbidities and had worse outcomes. Point-of-care bloodless AI ECG-K⁺ not only rapidly identified potentially severe hypo- and hyperkalemia, but also may serve as a biomarker for medical complexity and an independent predictor for adverse outcomes.

Fig. 1. Study cohorts’ summary.

A Dataset generation based on emergency department visits to an academic medical center and a community hospital; (B) The distributions of ECG-K⁺ and Lab-K⁺ at the academic medical center and community hospital.

Fig. 2. Performance of ECG-K⁺ for detecting mild to severe hypo/hyperkalemia.

The ROC curves for varying degrees of hypo- and hyperkalemia at the academic medical center (A) and community hospital (B). The cut-of-points for each plot were defined previously, which are the same between the two hospitals. Stratified analyses with the most significant differences are shown in (C).

Fig. 3. Distributions of selected patients’ characteristics in each ECG-K⁺ and Lab-K⁺ group.

Bars represent the mean or proportion where appropriate and corresponding 95% conference intervals, which are adjusted by hospital.

Fig. 4. The relationship between ECG-K⁺ and Lab-K⁺ on adverse outcomes in combined analysis from both hospitals.

A The Kaplan–Meier curve analysis of all-cause mortality in hypo- and hyperkalemia as defined by ECG-K⁺ and Lab-K⁺. The hazard ratio (HR) was adjusted by hospital site; (B) Continuous association of ECG-K⁺ and Lab-K⁺ on adverse outcomes. The solid line and dashed line are point estimation and corresponding 95% conference interval, respectively. The baseline model of combined analysis is adjusted to each hospital site and based on Cox proportional hazard model or logistic regression as appropriate for each outcome. The multivariable analyses include significant variables in risk-effect analyses (All-cause mortality: gender, Age, SBP, DBP, HLP, Hb, HCO₃, Blood pH, Na, AST, ALT, Alb, CRP, pBNP, and D-dimer; Hospitalization: gender, age, BMI, DBP, smoke, HLP, STK, HF, WBC, Hb, PLT, HCO₃, PH, Na, Cl, tCa, GLU, AST, CK, Alb, CRP, TnI, and D-dimer; ED revisits in 30 days: gender, DM, CAD, STK, COPD, Hb, and Na).

Fig. 5. Selected patients’ characteristics in different ECG-K⁺ and Lab-K⁺ groups.

Bars represent the mean or proportion where appropriate and corresponding 95% conference intervals, which are adjusted by hospital and Lab-K⁺ via linear or logistic regression (*p < 0.05; **p < 0.01; ***p < 0.001).

Fig. 6. Risk matrices of different ECG-K⁺ and Lab-K⁺ groups on adverse outcomes in combined analysis.

The baseline model of combined analysis is adjusted to each hospital site and based on Cox proportional hazard model or logistic regression as appropriate for each outcome. The color gradient represents the risk of the corresponding group and non-significant results are colored white. Model 1 includes significant demographic data (All-cause mortality: gender, Age, SBP, and DBP; Hospitalization: gender, age, BMI, DBP, and smoke; ED revisit in 30 days: gender). Model 2 includes the variables in model 1 and additional significant disease histories (All-cause mortality: HLP; Hospitalization: HLP, STK, and HF; ED revisit in 30 days: DM, CAD, STK, and COPD). Model 3 includes the variables in model 2 and additional significant laboratory tests (All-cause mortality: Hb, HCO₃, Blood pH, Na, AST, ALT, Alb, CRP, pBNP, and D-dimer; Hospitalization: WBC, Hb, PLT, HCO₃, PH, Na, Cl, tCa, GLU, AST, CK, Alb, CRP, TnI, and D-dimer; ED revisit in 30 days: Hb and Na).

Fig. 7. ECG morphology analysis of combinations of ECG-K⁺ and Lab-K⁺ on adverse outcomes.

A Distributions of ECG morphology in each ECG-K⁺ and Lab-K⁺ group. Bars represent the mean or prevalence where appropriate and corresponding 95% conference intervals, which are adjusted by hospital. B Risk analysis of selected ECG morphologies on adverse outcomes. The hazard ratios and odds ratios were adjusted by hospital. Red, gray, and blue bars denote significantly positive, non-significant, and negative associations, respectively, with the corresponding outcomes.