Patterns of reporting health-related quality of life outcomes in randomized clinical trials: implications for clinicians and quality of life researchers

Abstract

Purpose: To assess the patterns of, and trends over time in, health-related quality of life (HRQL) reporting in randomized controlled trials (RCTs).

Methods: The English-language literature of RCTs published in 2002-2008 was identified using Medline, Embase, and Healthstar databases, in addition to the Cochrane Clinical Trials Registry. Eligible trials were phase III studies that included an HRQL outcome. Data were abstracted on eight outcomes derived from previously recommended quality standards for reporting HRQL, and on four outcomes describing how HRQL data are presented in RCT reports. Two readers examined each article; discrepancies were resolved through discussion and third review if required.

Results: A sample of 794 RCTs was identified. HRQL was a primary outcome in 25.4% (200/794). One hundred and ten RCTs (14%) used "supplementary" reports (separate from the first publication) to report HRQL findings. The proportion of RCTs that met the eight quality indicators ranged from 15% (HRQL used in the calculation of sample size) to 81% (reporting instrument validity). RCTs with HRQL as a primary outcome or with a supplementary report had higher concordance on the quality measures. Reporting improved on many indicators over time. Substantive variation in how HRQL data are presented in RCTs was evident.

Conclusions: Current practice of reporting HRQL outcomes in RCTs remains highly variable, both with regard to quality of reporting and the patterns of data analysis and presentation. This variation presents challenges for clinicians to apply these data in clinical practice. Consistent reporting practices, which are interpretable by clinicians, are required, as are processes to achieve this consistency in future reports.