Risk factors and true prevalence of bovine tuberculosis in Bangladesh

Abstract

Bovine tuberculosis (bTb) is endemic in Bangladesh but the true prevalence has not yet been reported. Our objectives for this study were to determine the true prevalence and identify risk factors for bTb at the animal- and herd-level in Bangladesh. A total of 510 cows were randomly selected during January 2018 to December 2018. Caudal fold (CFT) and comparative cervical tuberculin tests (CCT) were serially interpreted. Animal- and herd-level risk factor data were collected using a pre-tested questionnaire. The hierarchical true prevalence of bTb was estimated within a Bayesian framework. The herd- and animal-level risk factors were identified using mixed effects logistic regression. The apparent prevalence of bTb was 20.6% [95% Confidence Interval (CI): 17.3; 24.3] based on CFT. The animal-level true prevalence of bTb was 21.9 (13.0; 32.4). The herd-level true prevalence in different regions varied from 41.9% to 88.8%. The region-level true prevalence was 49.9 (13.8; 91.2). There is a 100% certainty that herds from Bhaluka and Mymensingh Sadar upazilas are not free from bTb. The odds of bTb were 3.9 times (1.2; 12.6) higher in herds having more than four cows than those with ≤ 4 cows. On the other hand, the risk of bTb was 3.3 times higher (1.0; 10.5) in non-grazing cows than grazing cows. Crossbred cows were 2.9 times (1.5; 5.9) more likely to be infected with bTb than indigenous cows. The risk of bTb in animals with cough was 2.3 times (1.2; 4.3) higher than those without cough. Crossbred, non-grazing cows with cough should be targeted for bTb surveillance. Herds of the Mymensingh, Sadar and Bhaluka regions should be emphasized for bTb control programs. Estimation of Bayesian hierarchical true prevalence facilitates identification of areas with higher prevalence and can be used to indicate regions that where true prevalence exceeds a pre-specified critical threshold.

Fig 1

Receiver operating characteristic curve of the final multivariable mixed effect logistic regression models, a: at herd level, b: at animal level.