Validity and Inter-Rater Reliability Testing of Quality Assessment Instruments

Book excerpt: The internal validity of a study reflects the extent to which the design and conduct of the study have prevented bias(es). One of the key steps in a systematic review is assessment of a study's internal validity, or potential for bias. This assessment serves to: (1) identify the strengths and limitations of the included studies; (2) investigate, and potentially explain heterogeneity in findings across different studies included in a systematic review; and (3) grade the strength of evidence for a given question. The risk of bias assessment directly informs one of four key domains considered when assessing the strength of evidence. With the increase in the number of published systematic reviews and development of systematic review methodology over the past 15 years, close attention has been paid to the methods for assessing internal validity. Until recently this has been referred to as “quality assessment” or “assessment of methodological quality.” In this context “quality” refers to “the confidence that the trial design, conduct, and analysis has minimized or avoided biases in its treatment comparisons.” To facilitate the assessment of methodological quality, a plethora of tools has emerged. Some of these tools were developed for specific study designs (e.g., randomized controlled trials (RCTs), cohort studies, case-control studies), while others were intended to be applied to a range of designs. The tools often incorporate characteristics that may be associated with bias; however, many tools also contain elements related to reporting (e.g., was the study population described) and design (e.g., was a sample size calculation performed) that are not related to bias. The Cochrane Collaboration recently developed a tool to assess the potential risk of bias in RCTs. The Risk of Bias (ROB) tool was developed to address some of the shortcomings of existing quality assessment instruments, including over-reliance on reporting rather than methods. Several systematic reviews have catalogued and critiqued the numerous tools available to assess methodological quality, or risk of bias of primary studies. In summary, few existing tools have undergone extensive inter-rater reliability or validity testing. Moreover, the focus of much of the tool development or testing that has been done has been on criterion or face validity. Therefore it is unknown whether, or to what extent, the summary assessments based on these tools differentiate between studies with biased and unbiased results (i.e., studies that may over- or underestimate treatment effects). There is a clear need for inter-rater reliability testing of different tools in order to enhance consistency in their application and interpretation across different systematic reviews. Further, validity testing is essential to ensure that the tools being used can identify studies with biased results. Finally, there is a need to determine inter-rater reliability and validity in order to support the uptake and use of individual tools that are recommended by the systematic review community, and specifically the ROB tool within the Evidence-based Practice Center (EPC) Program. In this project we focused on two tools that are commonly used in systematic reviews. The Cochrane ROB tool was designed for RCTs and is the instrument recommended by The Cochrane Collaboration for use in systematic reviews of RCTs. The Newcastle-Ottawa Scale is commonly used for nonrandomized studies, specifically cohort and case-control studies.