How to Investigate the Effects of Groups on Changes in Longitudinal Patient-Reported Outcomes and Response Shift Using Rasch Models.

Karima Hammas,Priscilla Brisson,Véronique Sébille,Jean-Benoit Hardouin,Myriam Blanchin

doi:10.3389/fpsyg.2020.613482

Abstract

In order to investigate patients’ experience of healthcare, repeated assessments of patient-reported outcomes (PRO) are increasingly performed in observational studies and clinical trials. Changes in PRO can however be difficult to interpret in longitudinal settings as patients’ perception of the concept being measured may change over time, leading to response shift (longitudinal measurement non-invariance) and possibly to erroneous interpretation of the observed changes in PRO. Several statistical methods for response shift analysis have been proposed, but they usually assume that response shift occurs in the same way in all individuals within the sample regardless of their characteristics. Many studies aim at comparing the longitudinal change of PRO into two groups of patients (treatment arm, different pathologies, …). The group variable could have an effect on PRO change but also on response shift effect and the perception of the questionnaire at baseline. In this paper, we propose to enhance the ROSALI algorithm based on Rasch Measurement Theory for the analysis of longitudinal PRO data to simultaneously investigate the effects of group on item functioning at the first measurement occasion, on response shift and on changes in PRO over time. ROSALI is subsequently applied to a longitudinal dataset on change in emotional functioning in patients with breast cancer or melanoma during the year following diagnosis. The use of ROSALI provides new insights in the analysis of longitudinal PRO data.

Highlights

Patient-reported outcomes (PRO) are increasingly used to assess patients’ perception and experience of healthcare with the investigation of health-related quality of life (HRQoL), fatigue, anxiety, and coping (Snyder et al, 2013; Vodicka et al, 2015; LeBlanc and Abernethy, 2017; Lashbrook et al, 2018)
Among the domains assessed by the QLQ-C30, we focused on the emotional functioning scale as we assumed that aspects of quality of life related to mental health were likely to be affected by response shift
The emotional functioning level remained stable for melanoma patients during the first year following diagnosis, whereas it significantly increased for breast cancer patients

Summary

INTRODUCTION

Patient-reported outcomes (PRO) are increasingly used to assess patients’ perception and experience of healthcare with the investigation of health-related quality of life (HRQoL), fatigue, anxiety, and coping (Snyder et al, 2013; Vodicka et al, 2015; LeBlanc and Abernethy, 2017; Lashbrook et al, 2018). ◦ If this test is significant, we assume recalibration on item j in group g and we assess whether this recalibration is uniform (i.e., the differences in item difficulty parameters are the same for all response categories, Figure 2, step 3GU) with the following Wald test: H0: δ(jp2g) − δj(p1g) = jg∀p. Model 3 is updated appropriately by adding constraint of equal differences over time for both groups: δj(p20) − δ(jp10) = δ(jp21) − δ(jp11)∀p The parameters of this updated model are estimated and we test whether this common recalibration can be considered uniform: H0: δj(p2g) − δ(jp1g) = j∀p, g(Figure 2, step 3CU). In step 4, emotional functioning mean change over time was tested using a longitudinal PCM that took into account different item difficulty parameters between groups at time 1 for item 3 and uniform recalibration for items 2 and 3, common to both groups.

DISCUSSION

Findings

ETHICS STATEMENT