Patient-reported outcomes: instrument development and selection issues

Abstract

At its most elemental, patient-reported outcomes (PRO) assessment involves asking the patients questions and evaluating their answers. Instrument developers need to be clear about what they want to know, from whom they want to know it and why, whether what they learned is credible, and whether they can interpret what they learned in the context of the research objectives. Because credible instrument development is neither inexpensive nor technically trivial, researchers must first determine that no available measure meets their research objectives. We suggest that the tasks of either reviewing current instruments or developing new ones originate from the same basic premise: PRO assessment requires a well-articulated conceptual framework. Once defined in the context of the research objectives, the conceptual framework needs to be adapted to the population of interest. We discuss how qualitative methods enrich the conceptual framework and facilitate the technical measurement tasks of item development, testing, and reduction. We recognize that PRO assessment stands at a technological crossroads with the increasingly frequent application of "modern" psychometric methods and discuss how innovations such as item banks and computer-adaptive testing will influence PRO instrument development. Although items are the essential building blocks for instruments, scales are the primary unit of analysis for PRO assessment, and we discuss methods for scoring and combining them. Finally, PRO assessment is meaningless if the key figure chooses not to cooperate. We consider how respondent burden influences the quality of PRO assessment.