Using survival curves for comparison of ordinal qualitative data in clinical studies

Résumé : Background and Objective: The survival-agreement plot was proposed and improved to assess the reliability of a quantitative measure. We propose the use of survival analysis as an alternative non-parametric approach for comparison of ordinal qualitative data. Study Design and Setting: Two case studies were presented. The first one is related to a randomized, double blind, placebo-controlled clinical trial to investigate the safety and efficacy of silymarin/metionin for chronic hepatitis C. The second one is a prospective study to identify gustatory alterations due to chorda tympani nerve involvement in patients with chronic otitis media without prior surgery. Results: No significant difference was detected between the two treatments related to the chronic hepatitis C (p > 0.5). On the other hand, a significant association was observed between the healthy side and the affected side of the face of patients with chronic otitis media related to gustatory alterations (p < 0.05). Conclusion: The proposed method can serve as an alternative procedure to statistical test for comparison of samples from ordinal qualitative variables. This approach has the advantage of being more familiar to clinical researchers.