Development and validation of a new algorithm model for differential diagnosis between Crohn's disease and intestinal tuberculosis: a combination of laboratory, imaging and endoscopic characteristics

Abstract

Abstract Background Sometimes in clinical practice, it is a great challenge to distinguish Crohn's disease (CD) and intestinal tuberculosis (ITB), we conducted this study to identify simple and useful algorithm for distinguishing them. Methods We retrospectively reviewed the medical history of the patients who were diagnosed as ITB or CD. We firstly identified ITB patients, and then the patients diagnosed with CD were matched by age, sex, and admission time in a 1:1 ratio. Patients who admitted between May 1, 2013 and April 30, 2019 were regarded as training cohort, and patients admitted between May 1, 2019 and May 1, 2020 were regarded as validation cohort. We used multivariate analysis to identify the potential variables, and then we used R package rpart to build the classification and regression tree (CART), and validated the newly developed model. Results In total, the training cohort included 84 ITB and 84 CD patients, the validation cohort included 22 ITB and 22 CD patients. Multivariate analysis showed that, positive interferon-gamma release assays (IGRAs), ≥ 4 segments involved, longitudinal ulcer, circular ulcer, and aphthous ulcer were confirmed as independent discriminating factors. Using these parameters to build the CART model made an overall accuracy rate was 88.64%, with sensitivity, specificity, NPV, and PPV being 90.91%, 86.36%, 90.48% and 86.96%, respectively. Conclusion We developed a simple and novel algorithm model covering laboratory, imaging, and endoscopy parameters with CART to differentiate ITB and CD with good accuracy. Positive IGRAs and circular ulcer were suggestive of ITB, while ≥ 4 segments involved, longitudinal ulcer, and aphthous ulcer were suggestive of CD.

Keywords

• Crohn's disease
• Intestinal tuberculosis
• Diagnosis
• Algorithm
• CART