Combining EQ-5D-5L items into a level summary score: demonstrating feasibility using non-parametric item response theory using an international dataset

Background The EQ-5D-5L is a well-established health questionnaire that estimates health utilities by applying preference-based weights. Limited work has been done to examine alternative scoring approaches when utility weights are unavailable or inapplicable. We examined whether the Mokken scaling approach can elucidate 1) if the level summary score is appropriate for the EQ-5D-5L and 2) an interpretation of such a score. Methods The R package "mokken" was used to assess monotonicity (scaling coefficients H, automated item selection procedure) and manifest invariant item ordering (MIIO: paired item response functions [IRF], H-T). We used a rich dataset (the Multiple Instrument Comparison, MIC) which includes EQ-5D-5L data from six Western countries. Results While all EQ-5D-5L items demonstrated monotonicity, the anxiety/depression (AD) item had weak scalability (H-i = 0.377). Without AD, scalability improved from H-s = 0.559 to H-s = 0.714. MIIO revealed that the 5 items can be ordered, and the ordering is moderately accurate in the MIC data (H-T = 0.463). Excluding AD, H-T improves to 0.743. Results were largely consistent across disease and country subgroups. Discussion The 5 items of the EQ-5D-5L form a moderate to strong Mokken scale, enabling persons to be ordered using the level summary score. Item ordering suggests that the lower range of the score represents mainly problems with pain and anxiety/depression, the mid-range indicates additional problems with mobility and usual activities, and middle to higher range of scores reveals additional limitations with self-care. Scalability and item ordering are even stronger when the anxiety/depression item is not included in the scale.