Clostridium difficile infection in Europe: a hospital-based survey

Abstract

Background: Little is known about the extent of Clostridium difficile infection in Europe. Our aim was to obtain a more complete overview of C difficile infection in Europe and build capacity for diagnosis and surveillance.

Methods: We set up a network of 106 laboratories in 34 European countries. In November, 2008, one to six hospitals per country, relative to population size, tested stool samples of patients with suspected C difficile infection or diarrhoea that developed 3 or more days after hospital admission. A case was defined when, subsequently, toxins were identified in stool samples. Detailed clinical data and stool isolates were collected for the first ten cases per hospital. After 3 months, clinical data were followed up.

Findings: The incidence of C difficile infection varied across hospitals (weighted mean 4·1 per 10,000 patient-days per hospital, range 0·0-36·3). Detailed information was obtained for 509 patients. For 389 of these patients, isolates were available for characterisation. 65 different PCR ribotypes were identified, of which 014/020 (61 patients [16%]), 001 (37 [9%]), and 078 (31 [8%]) were the most prevalent. The prevalence of PCR-ribotype 027 was 5%. Most patients had a previously identified risk profile of old age, comorbidity, and recent antibiotic use. At follow up, 101 (22%) of 455 patients had died, and C difficile infection played a part in 40 (40%) of deaths. After adjustment for potential confounders, an age of 65 years or older (adjusted odds ratio 3·26, 95% CI 1·08-9·78; p=0·026), and infection by PCR-ribotypes 018 (6·19, 1·28-29·81; p=0·023) and 056 (13·01; 1·14-148·26; p=0·039) were significantly associated with complicated disease outcome.

Interpretation: PCR ribotypes other than 027 are prevalent in European hospitals. The data emphasise the importance of multicountry surveillance to detect and control C difficile infection in Europe.

Funding: European Centre for Disease Prevention and Control.