Development and Validation of a Bayesian Network for Supporting the Etiological Diagnosis of Uveitis

Abstract

The etiological diagnosis of uveitis is complex. We aimed to implement and validate a Bayesian belief network algorithm for the differential diagnosis of the most relevant causes of uveitis. The training dataset (n = 897) and the test dataset (n = 154) were composed of all incident cases of uveitis admitted to two internal medicine departments, in two independent French centers (Lyon, 2003–2016 and Dijon, 2015–2017). The etiologies of uveitis were classified into eight groups. The algorithm was based on simple epidemiological characteristics (age, gender, and ethnicity) and anatomoclinical features of uveitis. The cross-validated estimate obtained in the training dataset concluded that the etiology of uveitis determined by the experts corresponded to one of the two most probable diagnoses in at least 77% of the cases. In the test dataset, this probability reached at least 83%. For the training and test datasets, when the most likely diagnosis was considered, the highest sensitivity was obtained for spondyloarthritis and HLA-B27-related uveitis (76% and 63%, respectively). The respective specificities were 93% and 54%. This algorithm could help junior and general ophthalmologists in the differential diagnosis of uveitis. It could guide the diagnostic work-up and help in the selection of further diagnostic investigations.

Diagnosis, Classification, and Assessment of the Underlying Etiology of Uveitis by Artificial Intelligence: A Systematic Review

“…Most recently, Jamilloux et al used a Bayesian belief network on a dataset composed of 877 incident uveitis cases to identify the etiology (center node) [11]. Variables included age, gender, ethnicity, and the anatomic and clinical characteristics of the uveitis.…”

“…In medicine, Bayesian belief networks have been proposed as a tool to assist in the differential diagnosis of medical conditions [8,9]. More recently, researchers applied this technique to the diagnosis of uveitis, with promising results [10,11]. Ophthalmological AI algorithms have been applied mainly in diabetic retinopathy screening, age-related macular degeneration, and corneal disease [12].…”

Bus Load Forecasting Method of Power System Based on VMD and Bi-LSTM

“…The hyperparameters of the LSTM neural network used for bus load prediction can be divided into two categories: structural hyperparameters and training hyperparameters. The structural hyperparameters mainly include the number of hidden neurons in the network, etc [21]. The number of hidden layer neurons determines the expressive ability of the network, but also determines whether the network is over-fitting and the network is time-consuming.…”

Optimization of anesthetic decision-making in ERAS using Bayesian network

“…However, the variable relationship in clinical decision-making is complex and uncertain, making it prone to problems such as insufficient fitting and low accuracy. Bayesian Network (BN) is a type of machine learning (ML) that has been applied to the medical field, such as disease diagnosis ( 15 , 16 ), risk prediction ( 17 , 18 ). Its core lies in probabilistic methods ( 19 , 20 ).…”