Objective Automatic diabetic retinopathy screening system based on neural networks has been used to detect diabetic retinopathy (DR). However, there is no quantitative synthesis of performance of these methods. We aimed to estimate the sensitivity and specificity of neural networks in DR grading. Methods Medline, Embase, IEEE Xplore, and Cochrane Library were searched up to 23 July 2019. Studies that evaluated performance of neural networks in detection of moderate or worse DR or diabetic macular edema using retinal fundus images with ophthalmologists’ judgment as reference standard were included. Two reviewers extracted data independently. Risk of bias of eligible studies was assessed using QUDAS-2 tool. Results Twenty-four studies involving 235 235 subjects were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed a pooled sensitivity of 91.9% (95% CI: 89.6% to 94.3%) and specificity of 91.3% (95% CI: 89.0% to 93.5%). Subgroup analyses and meta-regression did not provide any statistically significant findings for the heterogeneous diagnostic accuracy in studies with different image resolutions, sample sizes of training sets, architecture of convolutional neural networks, or diagnostic criteria. Conclusions State-of-the-art neural networks could effectively detect clinical significant DR. To further improve diagnostic accuracy of neural networks, researchers might need to develop new algorithms rather than simply enlarge sample sizes of training sets or optimize image quality.

Hypereosinophilic syndrome (HES), a rare systemic disease, was first described in 1968. As a subtype of HES, idiopathic hypereosinophilic syndrome (IHES) is defined as hypereosinophilia of unknown cause, excluding tumor, infection, allergy, and immune system disease. In most cases, more than 1 organ is affected in patients with IHES. [1] The first-line drug for the treatment of IHES is glucocorticoid, which is effective for both hypereosinophilia and clinical manifestations. [2] However, when the outcome of hormone treatment is unsatisfactory, immunosuppressive or antineoplastic agents can also be administered. [3] Due to the low incidence of IHES, there is currently a lack of large-scale retrospective studies of the disease. We aimed to identify factors predictive of prognosis and determine the endpoint eosinophil (EOS) count after pharmacological therapy and the time at which a change of therapy should be considered following the failure of hormone treatment.Rui Tang and Shubin Lei contributed equally to this work.