Challenges with Percent Predicted Maximal V˙O2 in Patients with Heart Failure

Abstract

Purpose: This study aimed to describe the influence of different equations to predict maximal oxygen uptake (MV˙O2) on the percent predicted MV˙O2 (ppMV˙O2) and the resultant categorization of patients with heart failure with reduced ejection fraction into high or low risk.

Methods: In this retrospective cohort study, ppMV˙O2 was calculated using six different equations to predict MV˙O2 among 1168 patients with heart failure with reduced ejection fraction (33% women). Repeated-measures ANOVA was used to compare within-subject differences in mean ppMV˙O2 between the prediction equations. Cochrane's Q test was used to compare the within-subject difference in the proportion of patients with ppMV˙O2 of <50% (high risk) and ≥75% (low risk) between the prediction equations.

Results: The ppMV˙O2 varied significantly (P < 0.001) between the MV˙O2 prediction equations, with mean (10th, 90th percentile) ppMV˙O2 ranging from 39% (25%, 54%) to 60% (39%, 83%) in men and 37% (24%, 49%) to 70% (47%, 94%) in women. Significant variation (P < 0.001) was also observed between prediction equations for the proportion of patients with ppMV˙O2 of <50% and ≥75% in men and women.

Conclusions: Statistically significant and clinically meaningful variations in the ppMV˙O2 are observed on the basis of the reference equation used to predict MV˙O2. Future writing committees should specify the preferred reference equation when identifying a ppMV˙O2 criterion in guideline statements.