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

Automated early detection of acute retinal necrosis from ultra-widefield color fundus photography using deep learning

BACKGROUND

Acute retinal necrosis (ARN) is a relatively rare but highly damaging and potentially sight-threatening type of uveitis caused by infection with the human herpesvirus. Without timely diagnosis and appropriate treatment, ARN can lead to severe vision loss. We aimed to develop a deep learning framework to distinguish ARN from other types of intermediate, posterior, and panuveitis using ultra-widefield color fundus photography (UWFCFP).

METHODS

We conducted a two-center retrospective discovery and validation study to develop and validate a deep learning model called DeepDrARN for automatic uveitis detection and differentiation of ARN from other uveitis types using 11,508 UWFCFPs from 1,112 participants. Model performance was evaluated with the area under the receiver operating characteristic curve (AUROC), the area under the precision and recall curves (AUPR), sensitivity and specificity, and compared with seven ophthalmologists.

RESULTS

DeepDrARN for uveitis screening achieved an AUROC of 0.996 (95% CI: 0.994-0.999) in the internal validation cohort and demonstrated good generalizability with an AUROC of 0.973 (95% CI: 0.956-0.990) in the external validation cohort. DeepDrARN also demonstrated excellent predictive ability in distinguishing ARN from other types of uveitis with AUROCs of 0.960 (95% CI: 0.943-0.977) and 0.971 (95% CI: 0.956-0.986) in the internal and external validation cohorts. DeepDrARN was also tested in the differentiation of ARN, non-ARN uveitis (NAU) and normal subjects, with sensitivities of 88.9% and 78.7% and specificities of 93.8% and 89.1% in the internal and external validation cohorts, respectively. The performance of DeepDrARN is comparable to that of ophthalmologists and even exceeds the average accuracy of seven ophthalmologists, showing an improvement of 6.57% in uveitis screening and 11.14% in ARN identification.

CONCLUSIONS

Our study demonstrates the feasibility of deep learning algorithms in enabling early detection, reducing treatment delays, and improving outcomes for ARN patients.

Managing a patient with uveitis in the era of artificial intelligence: Current approaches, emerging trends, and future perspectives

The integration of artificial intelligence (AI) with healthcare has opened new avenues for diagnosing, treating, and managing medical conditions with remarkable precision. Uveitis, a diverse group of rare eye conditions characterized by inflammation of the uveal tract, exemplifies the complexities in ophthalmology due to its varied causes, clinical presentations, and responses to treatments. Uveitis, if not managed promptly and effectively, can lead to significant visual impairment. However, its management requires specialized knowledge, which is often lacking, particularly in regions with limited access to health services. AI's capabilities in pattern recognition, data analysis, and predictive modelling offer significant potential to revolutionize uveitis management. AI can classify disease etiologies, analyze multimodal imaging data, predict outcomes, and identify new therapeutic targets. However, transforming these AI models into clinical applications and meeting patient expectations involves overcoming challenges like acquiring extensive, annotated datasets, ensuring algorithmic transparency, and validating these models in real-world settings. This review delves into the complexities of uveitis and the current AI landscape, discussing the development, opportunities, and challenges of AI from theoretical models to bedside application. It also examines the epidemiology of uveitis, the global shortage of uveitis specialists, and the disease's socioeconomic impacts, underlining the critical need for AI-driven approaches. Furthermore, it explores the integration of AI in diagnostic imaging and future directions in ophthalmology, aiming to highlight emerging trends that could transform management of a patient with uveitis and suggesting collaborative efforts to enhance AI applications in clinical practice.

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

Recent years have seen the emergence and application of artificial intelligence (AI) in diagnostic decision support systems. There are approximately 80 etiologies that can underly uveitis, some very rare, and AI may lend itself to their detection. This synthesis of the literature selected articles that focused on the use of AI in determining the diagnosis, classification, and underlying etiology of uveitis. The AI-based systems demonstrated relatively good performance, with a classification accuracy of 93-99% and a sensitivity of at least 80% for identifying the two most probable etiologies underlying uveitis. However, there were limitations to the evidence. Firstly, most data were collected retrospectively with missing data. Secondly, ophthalmic, demographic, clinical, and ancillary tests were not reliably integrated into the algorithms' dataset. Thirdly, patient numbers were small, which is problematic when aiming to discriminate rare and complex diagnoses. In conclusion, the data indicate that AI has potential as a diagnostic decision support system, but clinical applicability is not yet established. Future studies and technologies need to incorporate more comprehensive clinical data and larger patient populations. In time, these should improve AI-based diagnostic tools and help clinicians diagnose, classify, and manage patients with uveitis.

Infrared analysis in the aqueous humor of patients with uveitis: Preliminary results

Inflammatory processes affecting the uvea result in a temporary o permanent blurred vision and represent an important cause of visual impairment worldwide. It is often hard to make a precise diagnosis which is dependent on the clinical expertise, diagnostic tests, laboratory investigations in blood and sometimes in the aqueous humor (AH). With the aim of obtaining proof of principle Fourier Transformed Infrared (FT-IR) absorbance spectroscopy was applied to study the molecular composition of 72 AH samples collected in 26 patients with uveitis and in 44 controls. The unsupervised exploration of the internal structure of the dataset by principal component analysis reduced hundreds IR variables to those most representative allowing to obtain the predictive model that distinguished the AH spectra of patients with uveitis from controls. The same result was obtained by unsupervised agglomerative cluster analysis. After labeling the spectra with some clinical information it was observed that most severe uveitis with active processes were grouped separately from chronic and relapsing uveitis and controls. The consistence of prediction models is discussed in the light of supporting etiological diagnosis by machine learning processes. In conclusion, proof of principle has been obtained that the IR spectral pattern of AH may reflect particular uveal diseases.

Management of Non-Infectious Uveitis, a Selection of Topical Items Updating

First of all, we would like to thank all of the authors for their contributions and the editorial staff who enabled the achievement of this «Diagnosis and Management of Non-infectious Uveitis: Old and New Challenges» Special Issue [...]

Optimization of anesthetic decision-making in ERAS using Bayesian network

Enhanced recovery after surgery (ERAS) can accelerate patient recovery. However, little research has been done on optimizing the ERAS-related measures and how the measures interact with each other. The Bayesian network (BN) is a graphical model that describes the dependencies between variables and is also a model for uncertainty reasoning. In this study, we aimed to develop a method for optimizing anesthetic decisions in ERAS and then investigate the relationship between anesthetic decisions and outcomes. First, assuming that the indicators used were independent, the effects of combinations of single indicators were analyzed based on BN. Additionally, the impact indicators for outcomes were selected with statistical tests. Then, based on the previously selected indicators, the Bayesian network was constructed using the proposed structure learning method based on Strongly Connected Components (SCC) Local Structure determination by Hill Climbing Twice (LSHCT) and adjusted according to the expert’s knowledge. Finally, the relationship is analyzed. The proposed method is validated by the real clinical data of patients with benign gynecological tumors from 3 hospitals in China. Postoperative length of stay (LOS) and total cost (TC) were chosen as the outcomes. Experimental results show that the ERAS protocol has some pivotal indicators influencing LOS and TC. Identifying the relationship between these indicators can help anesthesiologists optimize the ERAS protocol and make individualized decisions.