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.
Similar content being viewed by others
Log in or create a free account to read this content
Gain free access to this article, as well as selected content from this journal and more on nature.com
or
References
Selmi C . Diagnosis and classification of autoimmune uveitis. Autoimmun Rev 2014; 13 (4-5): 591–594.
Charniak E . Bayesian networks without tears. AI Magazine 1991; 12 (4): 50.
Arias M, Díez FJ, Palacios-Alonso MA, Yebra M, Fernández J 2012. POMDPs in OpenMarkov and ProbModelXML. The Seventh Annual Workshop on Multiagent Sequential Decision-Making Under Uncertainty; June 2012; Valencia, Spain.
Beneyto P, Fernandez MJ, Garcia A, Ibanez M, Garcia-Aparicio A, Morente P . [Fuchs' heterochromic cyclitis without heterochromia: a diagnostic approach]. Archivos de la Sociedad Espanola de Oftalmologia 2007; 82 (6): 355–359.
Bibbo M, Bartels PH, Pfeifer T, Thompson D, Minimo C, Davidson HG . Belief network for grading prostate lesions. Anal Quant Cytol Histol 1993; 15 (2): 124–135.
Montironi R, Bartels PH, Thompson D, Scarpelli M, Hamilton PW . Prostatic intraepithelial neoplasia. Development of a Bayesian belief network for diagnosis and grading. Anal Quant Cytol Histol 1994; 16 (2): 101–112.
Hamilton PW, Anderson N, Bartels PH, Thompson D . Expert system support using Bayesian belief networks in the diagnosis of fine needle aspiration biopsy specimens of the breast. J Clin Pathol 1994; 47 (4): 329–336.
Seixas FL, Zadrozny B, Laks J, Conci A, Muchaluat Saade DC . A Bayesian network decision model for supporting the diagnosis of dementia, Alzheimers disease and mild cognitive impairment. Comput Biol Med 2014; 51: 140–158.
Agrawal R, Gonzalez-Lopez JJ, Nobre-Cardoso J, Gupta B, Grant R, Addison PK et al. Predictive factors for treatment failure in patients with presumed ocular tuberculosis in an area of low endemic prevalence. Br J Ophthalmol 2015; 100: 348–355.
Chang JH, McCluskey PJ, Wakefield D . Acute anterior uveitis and HLA-B27. Surv Ophthalmol 2005; 50 (4): 364–388.
Acknowledgements
The contents of this article were presented at the 2015 ARVO Annual Meeting in Denver, Colorado (abstract number 3123). We thank Dr Maria Pefkianaki for her administrative support.
Author contributions
JJG-L, ÁMG-A, PB, and MCW carried out conception and design of the article; JJG-L and MCW performed the analysis and interpretation of results; JJG-L helped in writing the article; ÁMG-A, PB, and MCW helped in critical revision of the article; JJG-L, ÁMG-A, DS-P, NM-S, NF-L, PB, and MCW helped in final approval of the article; JJG-L, ÁMG-A, DS-P, NM-S, and NF-L helped in data collection; ÁMG-A, PB, and MCW took part in provision of materials, patients, or resources; JJG-L and MCW helped in statistical expertize; JJG-L, ÁMG-A, and PB performed the literature search.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
JJG-L has received study grants from Alcon, Novartis, Thèa and Merck, and has provided consultancy to Bayer. The remaining authors declare no conflict of interest.
Additional information
Supplementary Information accompanies this paper on Eye website
Supplementary information
Rights and permissions
About this article
Cite this article
González-López, J., García-Aparicio, Á., Sánchez-Ponce, D. et al. Development and validation of a Bayesian network for the differential diagnosis of anterior uveitis. Eye 30, 865–872 (2016). https://doi.org/10.1038/eye.2016.64
Received:
Accepted:
Published:
Issue date:
DOI: https://doi.org/10.1038/eye.2016.64
