Development and validation of a Bayesian network for the differential diagnosis of anterior uveitis
Development and validation of a Bayesian network for the differential diagnosis of anterior uveitis
复制标题
DOI：
10.1038/eye.2016.64
复制
发表时间：
2016-06-01
期刊：
影响因子：
3.9
通讯作者：
Westcott, M. C.
中科院分区：
文献类型：
--
作者：
Gonzalez-Lopez, J. J.;Garcia-Aparicio, A. M.;Westcott, M. C.
目的建立并验证一种用于前葡萄膜炎鉴别诊断的贝叶斯信念网络算法。患者和方法包括11种最常见的病因（特发性、强直性脊柱炎、银屑病关节炎、反应性关节炎、炎症性肠病、结节病、结核病、Behcet、Posner-Schlossman综合征、幼年特发性关节炎（JIA）和Fuchs异色循环炎）。从文献的系统回顾中检索了因素和病因之间的关联频率。对2012年在Moorfields眼科医院接受前葡萄膜炎诊断的200名患者进行随机抽样，计算患病率。该网络在2013年同一家医院接受前葡萄膜炎诊断的200例患者和10例最罕见病因（JIA、Behcet和银屑病关节炎）的随机样本中得到验证。结果63.8%的患者最可能病因与资深临床医生诊断相符。在80.5%的患者中，临床医生的诊断与算法的第一或第二最有可能的结果相匹配。仅考虑算法最可能的诊断，每种病因的敏感性范围从100%（7例反应性关节炎患者中有7例，5例Behcet患者中有5例正确分类）到46.7%（15例结核相关性葡萄膜炎患者中有7例）。结节病的特异性从88.8%到波斯纳病的99.5%不等。结论该算法可帮助临床医生鉴别诊断前葡萄膜炎。此外，它还可以帮助选择所执行的诊断测试。
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, Behcet, 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, Behcet, 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 Behcet 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.