Is intestinal biopsy always needed for diagnosis of celiac disease?

OBJECTIVE: Intestinal biopsy is required for a diagnosis of celiac disease (CD). The aim of this study was to assess diagnostic accuracy of transglutaminase antibodies (TGA) in comparison and in association with that of antiemdomysial antibodies (AEA), calculating the post-test odds of having the disease, to verify whether some patients might avoid undergoing intestinal biopsy for a diagnosis of CD. METHODS: A total of 181 consecutive patients (131 < 18 yr), referred to our celiac clinic by primary care physicians for suspect CD. Overall diagnostic accuracy, negative predictive value, and likelihood ratio (LR) were calculated both for each serological test and for serial testing (TGA and after AEA, assuming the post-test probability of TGA as pretest probability of AEA). Both serological determination and histological evaluation were blindly performed. Histology of duodenal mucosa was considered the gold standard. RESULTS: The overall accuracy of TGA and of AEA were 92.8% (89.1-96.6) and 93.4% (89.7-97.0), respectively. The negative predictive value of TGA and AEA were 97.2% (91.9-102.6) and 87.2% (77.7-96.8), respectively. Positive likelihood ratios for TGA and AEA were 3.89 (3.40-4.38) and 7.48 (6.73-8.23), respectively. Serial testing, in groups of patients with prevalence of CD estimated higher than 75%, such as those with classic symptoms of CD, would provide a post-test probability of more than 99%. CONCLUSIONS: Our results suggest that serial testing with TGA and AEA might allow, in some cases, the avoidance of intestinal biopsy to confirm the diagnosis of CD. (C) 2003 by Am. Coll. of Gastroenterology.