Accuracy of self-report of mammography and Pap smear in a low-income urban population

Abstract

Background: Cancer screening history can often be obtained only by self-report, particularly for disadvantaged populations. We examined the accuracy of self-report of mammography and Pap smear for an urban, low-income population.

Methods: Women attending non-primary care clinics (mostly surgery and orthopedics) at a large public teaching hospital in Minneapolis between July 1992 and May 1993 were queried about their screening history (n = 477). The women were interviewed by a trained peer-recruiter and asked whether they had ever heard of a Pap smear or mammogram, whether they had ever had one, where it was done, and when the last one was. We verified self-report by checking medical records where the test was performed.

Results: The positive and negative predictive value of recall of mammography in the previous year was 72.4% and 90.6%, respectively. The figures for Pap smear recall were somewhat lower, 65.5% and 85.9%, respectively. We found a record of a mammogram in 88% of women able to recall the year. Of these, slightly over two-thirds recalled their mammogram in the same year as their record indicated. Inaccurate recalls were more commonly of the "telescoping" type, i.e., tests were recalled as having occurred more recently than was the case. Recall was substantially better for recent tests. Results for Pap smear recalls were broadly similar.

Conclusions: The accuracy of self-report of mammography and Pap smear is relatively poor for medical practice but is acceptable in population surveys with appropriate correction for overreporting.