The e-MSWS-12: improving the multiple sclerosis walking scale using item response theory

• Published in: Quality of life research Vol. 25; no. 12; pp. 3221 - 3230
• Main Authors: Engelhard, Matthew M., Schmidt, Karen M., Engel, Casey E., Brenton, J. Nicholas, Patek, Stephen D., Goldman, Myla D.
• Format: Journal Article
• Language: English
• Published: Cham Springer 01.12.2016; Springer International Publishing; Springer Nature B.V
• Subjects: Adult; Aged; Aged, 80 and over; Clinical outcomes; Dimensionality; Disabilities; Disability; Disability Evaluation; Discriminant analysis; Disease models; Female; Humans; INSTRUMENT DEVELOPMENT; Item response theory; Male; Medicine; Medicine & Public Health; Middle Aged; Multiple sclerosis; Multiple Sclerosis - therapy; Neurology; Physical fitness; Psychometrics; Public Health; Quality of life; Quality of Life Research; Sickness Impact Profile; Sociology; Standard error of estimate; Standard error of measurement; Test bias; Three dimensional modeling; Walking; Walking - physiology; Multiple sclerosis; Differential item functioning; Graded response model; 12-Item multiple sclerosis walking scale; Item response theory; Timed 25-foot walk
• ISSN: 0962-9343; 1573-2649; 1573-2649
• DOI: 10.1007/s11136-016-1342-2

Background The Multiple Sclerosis Walking Scale (MSWS-12) is the predominant patient-reported measure of multiple sclerosis (MS) -elated walking ability, yet it had not been analyzed using item response theory (IRT), the emerging standard for patient-reported outcome (PRO) validation. This study aims to reduce MSWS-12 measurement error and facilitate computerized adaptive testing by creating an IRT model of the MSWS-12 and distributing it online. Methods MSWS-12 responses from 284 subjects with MS were collected by mail and used to fit and compare several IRT models. Following model selection and assessment, subpopulations based on age and sex were tested for differential item functioning (DIF). Results Model comparison favored a one-dimensional graded response model (GRM). This model met fit criteria and explained 87 % of response variance. The performance of each MSWS-12 item was characterized using category response curves (CRCs) and item information. IRT-based MSWS-12 scores correlated with traditional MSWS-12 scores (r = 0.99) and timed 25-foot walk (T25FW) speed (r = -0.70). Item 2 showed DIF based on age (X² = 19.02, df=5, p < 0.01), and Item 11 showed DIF based on sex (X² = 13.76, df=5, p = 0.02). Conclusions MSWS-12 measurement error depends on walking ability, but could be lowered by improving or replacing items with low information or DIF. The e-MSWS-12 includes IRT-based scoring, error checking, and an estimated T25FW derived from MSWS-12 responses. It is available at https://ms-irt.shinyapps.io/eMSWS-12.