Quality of life assessment in patients with heart failure: validity of the German version of the generic EQ-5D-5L™

Abstract

Background: Chronic heart failure patients typically suffer from tremendous strain and are managed mainly in primary care. New care concepts adapted to the severity of heart failure are a challenge and need to consider health-related quality of life aspects. This is the first psychometric validation of the German EQ-5D-5L™ as a generic instrument for assessing health-related quality of life (HRQOL) in a primary care heart failure patient sample.

Methods: Confirmatory factor analysis (CFA) was performed on the baseline EQ-5D-5L™ data from the RECODE-HF study (responses to all items from n = 3225 of 3778 patients). Basic CFA models for HRQOL were calculated based on the EQ-5D-5L™ items using the maximum likelihood (ML) and the asymptotic distribution-free method. In an extended CFA, physical activity and depression were added. The basic CFA ML model was verified for the reduced number of cases of the extended CFA model (n = 3064). In analyses of variance the association of the EQ-5D-5L™ visual analogue scale (VAS) and both the German and the British EQ-5D-5L™ crosswalk index with the SF-36 measure of general health were examined. The discriminant validity was analysed using Pearson's chi-squared tests applying the New York Heart Association classification, for the VAS and indices analyses of variance were calculated.

Results: In the basic CFA models the root mean square error of approximation was 0.095 with the ML method, and 0.081 with the asymptotic distribution-free method (Comparative Fit Index > 0.90 for both). Physical activity and depression were confirmed as influential factors in the extended model. The VAS and indices were strongly associated with the SF-36 measure of general health (partial eta-squared 0.525/0.454/0.481; all p < 0.001; n = 3155/3210/3210, respectively), also for physical activity and depression when included together (partial eta-squared 0.050, 0.200/0.047, 0.213/0.051 and 0.270; all p < 0.001; n = 3015/n = 3064/n = 3064, respectively). The discriminant validity analyses showed p-values < 0.001 and small to moderate effect sizes for all EQ-5D-5L™ items. Analyses of variance demonstrated moderate effect sizes for the VAS and indices (0.067/0.087/0.084; all p < 0.001; n = 3110/3171/3171).

Conclusion: The German EQ-5D-5L™ is a suitable method for assessing HRQOL in heart failure patients.

Keywords: Confirmatory factor analysis; Construct analysis; Discriminant validity; EQ-5D-5L; Heart failure; Quality of life.

Fig. 1

Health-related quality of life (HRQOL) represented by the EQ-5D-5 L™ items. Basic measurement model of the latent construct of HRQOL with model fit and standardised parameter estimates calculated using the maximum likelihood and asymptotic distribution-free methods (in parentheses). E1 - e5 = residual variation

Fig. 2

EQ-5D-5 L™ parameters and general health status. The association of the EQ-5D-5 L™ VAS (a), and the German and the British crosswalk index of the EQ-5D-5 L™ (b) with the SF-36 measure of general health

Fig. 3

Essential influence factors on health-related quality of life (HRQOL) represented by the EQ-5D-5 L™ items. For the variables physical activity and psychosocial distress adjusted model of the latent construct of HRQOL with standardised parameter estimates calculated with the ML method. N = 3064; e1 - e6 = residual variation

Fig. 4

Essential influence factors on health-related quality of life represented by the EQ-5D-5L™ VAS and indices. The association of the EQ-5D-5L™ VAS (a) (c), and the German and the British crosswalk index of the EQ-5D-5L™ (b) (d) with physical activity and psychosocial distress

Fig. 5

Discriminative ability indicated by the severity of heart failure according to the NYHA classes. The discriminative ability of the five EQ-5D-5L™ questions (a) (b) (c) (d) (e), the EQ-5D-5L™ VAS (f), and the German and the British EQ-5D-5L™ crosswalk index (g), respectively