Kraisangka, J., Scott, J., Kanwar, M., Liu, Z., Lin, S., Everett, A., Perer, A., Movahedi, F., Antaki, J., Benza, R. “EKG Parameters In Predicting Survivals In Pulmonary Arterial Hypertension.” Chest, vol. 160, no. 4, Oct. 2021, pp. A2325–26.
PURPOSE: EKG parameters are ones of the predictors for prognosis of the patients with pulmonary arterial hypertension (PAH).
METHODS: We analyzed the imaging and EKG variables obtained at baseline in 4 PAH clinical trials: SERAPHIN, BREATHE-1, CHEST-2, and PATENT-2. The outcome of the analysis was mortality at the time to event of each individual trial. We selected only the significant EKG variables (p-value<0.05) to be aggregated across the clinical trials using Stouffer’s method, weighed by their ‘N’ in the clinical trials.
RESULTS: Collective data from 1,579 patients were available at baseline with 10 EKG variables. Out of the 10, only 4 variables were still significant (p-value<0.05) after the aggregation of p-values: 1) Non-sinus rhythms: HR=6.11 [1.36; 27.33], aggregated p-value=0.0180, N=213; 2) Mean ventricular rate (beat/min): HR=1.04 [1.02; 1.07], aggregated p-value=0.0011, N=393; 3) QRS interval (ms): HR=0.99 [0.95; 1.03], aggregated p-value=0.0242, N=948; and 4) Atrial or ventricular extrasystole: HR=0.35 [0.04; 3.33], aggregated p-value=0.0041, N=231. The most predictive variable to mortality were non-sinus rhythm followed by the mean ventricular rate, while the presence of atrial or ventricular extrasystole is protective.
CONCLUSIONS: To our knowledge, this is the largest aggregated attempt to analyze EKG parameters in predicting survivals. This analysis will be used to select features for the derivation of machine-learned PAH patient risk stratification models
CLINICAL IMPLICATIONS: Our long-term goal is to generate a comprehensive personalized risk assessment tool from the data-driven variable selections to aid clinical decisions.