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

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.

Cell-Free Blood Cell Secretome (BCS) Counteracts Skin Aging: Multi-Center Prospective Regenerative Aesthetic Medicine Study Using Exokine®

“…Both too good and too bad evaluations are possible. One concept, "Response shift" 46,47 tries to define the possible changes in patient and observer perception over time and applies sophisticated methods. This is one reason why, not only in aesthetics, more objective measurements are sought in addition.…”

Validation of Generalized Anxiety Disorder 6 (GAD-6)—A Modified Structure of Screening for Anxiety in the Adolescent French Population

“…The DIF analysis was performed partly using the ROSALI algorithm [ 33 , 40 ] based on Partial Credit Models. To detect differences in item difficulty parameters, a PCM estimating different item difficulty parameters for all items between the two groups is compared to a PCM assuming no DIF, i.e., equal item difficulty parameters between groups using a likelihood ratio test.…”

Performance of a Rasch-based method for group comparisons of longitudinal change and response shift at the item level in PRO data: A simulation study

“…The RespOnse Shift ALgorithm at Item level (ROSALI) based on models from RMT consists of 2 main parts [16]. In the first part (steps A to C), differences in item difficulties between groups at time 1 are investigated.…”

“…Hence, new developments are needed to account for RS heterogeneity at item-level. ROSALI has thus been extended to explore the heterogeneity of item-level RS between groups in studies comparing two groups of patients [16]. For example, patients from two different treatment groups might experience their illness in a different way and RS may occur differently in each group or even occur in only one treatment group.…”

“…To date, the latest version of ROSALI enables to detect and adjust for DIF and RS in the estimation of PRO change to ensure valid comparisons between groups and over time. These major changes of ROSALI were described elsewhere [16] alongside with an illustrative example of interpretation of the results of the algorithm.…”