A randomly selected population sample undergoing colonoscopy: prevalence of the irritable bowel syndrome and the impact of selection factors

Abstract

Objective: To analyse the epidemiology of irritable bowel syndrome (IBS) symptoms in a random sample of the general population and in a subsample consenting to a colonoscopy, and to what extent this introduces symptom selection bias.

Materials and methods: Overall, 3347 randomly selected Swedish adults aged 18-70 years were mailed the validated Abdominal Symptom Questionnaire (ASQ). Responders (n=2293; 68.5%) were contacted by phone, and 745 consented to a colonoscopy. All nonresponders were contacted by phone; 265 were reached and asked seven key ASQ questions. Colonoscopy participants also completed the Rome II Modular Questionnaire.

Results: The prevalence of IBS on the basis of the mailed ASQ (troublesome abdominal pain and bowel disturbance in the past 3 months) was 26.2% [95% confidence interval (CI): 24.4-28.0] among the ASQ responders and 36.6% (95% CI: 33.2-40.1) among the colonoscopy participants (P<0.001). Nonresponders had a lower prevalence of IBS (15.8%; 95% CI: 11.4-20.3, P<0.001) than ASQ responders. Colonoscopy participants were slightly older than noncolonoscoped participants completing the ASQ (P<0.001), but men and women were equally represented and no significant socioeconomic differences were identified. The prevalence of IBS was 14.8% (95% CI: 12.2-17.5) on the basis of the Rome II Modular Questionnaire in colonoscopy participants and 14.5% (95% CI: 11.9-17.2) when visible inflammatory disease was excluded. Of the colonoscopy participants, 31.9% (95% CI: 28.5-35.3) were symptom free.

Conclusion: IBS symptoms are common and rarely explained by visible inflammatory disease or cancer. There was a modest selection bias by IBS in participants accepting a screening colonoscopy, but still, one-third were symptom free. Thus, conclusions for the general population can be made from findings in the study cohort.