A comparison of conventional and retrospective measures of change in symptoms after elective surgery

Abstract

Background: Measuring change is fundamental to evaluations, health services research and quality management. To date, the Gold-Standard is the prospective assessment of pre- to postoperative change. However, this is not always possible (e.g. in emergencies). Instead a retrospective approach to the measurement of change is one alternative of potential validity. In this study, the Gold-Standard 'conventional' method was compared with two variations of the retrospective approach: a perceived-change design (model A) and a design that featured observed follow-up minus baseline recall (model B).

Methods: In a prospective longitudinal observational study of 185 hernia patients and 130 laparoscopic cholecystectomy patients (T0: 7-8 days pre-operative; T1: 14 days post-operative and T2: 6 months post-operative) changes in symptoms (Hernia: 9 Items, Cholecystectomy: 8 Items) were assessed at the three time points by patients and the conventional method was compared to the two alternatives. Comparisons were made regarding the percentage of missing values per questionnaire item, correlation between conventional and retrospective measurements, and the degree to which retrospective measures either over- or underestimated changes and time-dependent effects.

Results: Single item missing values in model A were more frequent than in model B (e.g. Hernia repair at T1: model A: 23.5%, model B: 7.9%. In all items and at both postoperative points of measurement, correlation of change between the conventional method and model B was higher than between the conventional method and model A. For both models A and B, correlation with the change calculated with the conventional method was higher at T1 than at T2. Compared to the conventional model both models A and B also overestimated symptom-change (i.e. improvement) with similar frequency, but the overestimation was higher in model A than in model B. In both models, overestimation was lower at T1 than at T2 and lower after hernia repair than after cholecystectomy.

Conclusions: The retrospective method of measuring change was associated with a larger improvement in symptoms than was the conventional method. Retrospective assessment of change results in a more optimistic evaluation of improvement by patients than does the conventional method (at least for hernia repair and laparoscopic cholecystectomy).

Figure 1

Illustration of the models referred to in this article.