The accuracy of pain and fatigue items across different reporting periods

Abstract

The length of the reporting period specified for items assessing pain and fatigue varies among instruments. How the length of recall impacts the accuracy of symptom reporting is largely unknown. This study investigated the accuracy of ratings for reporting periods ranging from 1 day to 28 days for several items from widely used pain and fatigue measures (SF36v2, Brief Pain Inventory, McGill Pain Questionnaire, Brief Fatigue Inventory). Patients from a community rheumatology practice (N=83) completed momentary pain and fatigue items on average of 5.4 times per day for a month using an electronic diary. Averaged momentary ratings formed the basis for comparison with recall ratings interspersed throughout the month referencing 1-day, 3-day, 7-day, and 28-day periods. As found in previous research, recall ratings were consistently inflated relative to averaged momentary ratings. Across most items, 1-day recall corresponded well to the averaged momentary assessments for the day. Several, but not all, items demonstrated substantial correlations across the different reporting periods. An additional 7 day-by-day recall task suggested that patients have increasing difficulty actually remembering symptom levels beyond the past several days. These data were collected while patients were receiving usual care and may not generalize to conditions where new interventions are being introduced and outcomes evaluated. Reporting periods can influence the accuracy of retrospective symptom reports and should be a consideration in study design.

Figure 1

Study CONSORT statement ^aInsufficient compliance with ratings for primary analyses: IVR (N=15), EMA (N=3), both (N=3).

Figure 2

Figure 2a. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for pain intensity (BPI) bodily pain (SF36v2) and usual fatigue (BFI). Figure 2b. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for McGill pain adjectives. Figure 2c. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for SF36v2 Vitality scale items.

Figure 2

Figure 2a. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for pain intensity (BPI) bodily pain (SF36v2) and usual fatigue (BFI). Figure 2b. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for McGill pain adjectives. Figure 2c. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for SF36v2 Vitality scale items.

Figure 2

Figure 2a. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for pain intensity (BPI) bodily pain (SF36v2) and usual fatigue (BFI). Figure 2b. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for McGill pain adjectives. Figure 2c. Reliability-adjusted correlations of IVR recall with the average of momentary assessments for SF36v2 Vitality scale items.

Figure 3

Mean ratings for momentary (EMA) and IVR recall ratings of BPI average pain (2a) and SF36v2 bodily pain (2b) items.

Figure 4

Correlations of 7 day-by-day recall pain ratings with averaged momentary ratings (EMA) for that day and for the mean of non-corresponding days (N=52).