Development and validation of a Bayesian network for the differential diagnosis of anterior uveitis

Abstract

Purpose: To develop and validate a Bayesian belief network algorithm for the differential diagnosis of anterior uveitis. Patients and methods: The 11 most common etiologies were included (idiopathic, ankylosing spondylitis, psoriasic arthritis, reactive arthritis, inflammatory bowel diseases, sarcoidosis, tuberculosis, Behçet, Posner-Schlossman syndrome, juvenile idiopathic arthritis (JIA), and Fuchs' heterochromic cyclitis). Frequencies of association between factors and etiologies were retrieved from a systematic review of the literature. Prevalences were calculated using a random sample of 200 patients receiving a diagnosis of anterior uveitis in Moorfields Eye Hospital in 2012. The network was validated in a random sample of 200 patients receiving a diagnosis of anterior uveitis in the same hospital in 2013 plus 10 extra cases of the most rare etiologies (JIA, Behçet, and psoriasic arthritis). Results: In 63.8% of patients the most probable etiology by the algorithm matched the senior clinician diagnosis. In 80.5% of patients the clinician diagnosis matched the first or second most probable results by the algorithm. Taking into account only the most probable diagnosis by the algorithm, sensitivities for each etiology ranged from 100% (7 of 7 patients with reactive arthritis and 5 of 5 with Behçet correctly classified) to 46.7% (7 of 15 patients with tuberculosis-related uveitis). Specificities ranged from 88.8% for sarcoidosis to 99.5% in Posner. Conclusions: This algorithm could help clinicians with the differential diagnosis of anterior uveitis. In addition, it could help with the selection of the diagnostic tests performed.