Search

Abstract To address challenges in screening for chronic kidney disease (CKD), we devised a deep learning-based CKD screening model named UWF-CKDS. It utilizes ultra-wide-field (UWF) fundus images to predict the presence of CKD. We validated the model with data from 23 tertiary hospitals across China. Retinal vessels and retinal microvascular parameters (RMPs) were extracted to enhance model interpretability, which revealed a significant correlation between renal function and RMPs. UWF-CKDS, utilizing UWF images, RMPs, and relevant medical history, can accurately determine CKD status. Importantly, UWF-CKDS exhibited superior performance compared to CTR-CKDS, a model developed using the central region (CTR) cropped from UWF images, underscoring the contribution of the peripheral retina in predicting renal function. The study presents UWF-CKDS as a highly implementable method for large-scale and accurate CKD screening at the population level.

Abstract Central vision loss (CVL) is a major form of low vision that remains inadequately managed worldwide. This study evaluated the clinical efficacy of a novel head-mounted device (HMD), Onyx, designed to enhance visual function and vision-related quality of life for CVL patients. It employs a projection system that enables patients to leverage their residual peripheral vision for environmental awareness. It also integrates artificial intelligence to augment the automatic recognition of text, faces, and objects. In this single-center, prospective cohort study, 41 binocularly low vision patients with CVL were instructed to use Onyx for 4 to 6 h daily over a one-month period. Various metrics were assessed, including near and distance visual acuity (VA), recognition abilities for faces and objects, and the low vision quality-of-life (LVQOL) questionnaire scores, at the start and end of the study. The results showed significant improvements in near VA for 60.98% of the participants, distance VA for 80.49%, and recognition ability for 90.24%. 68.29% of the participants showed significant improvements in the LVQOL scores. Improvement in recognition ability was negatively correlated with baseline recognition ability. Additionally, improvement in the LVQOL scores was correlated with age and the baseline LVQOL score. Overall, the study found that the novel HMD significantly improved visual function and vision-related quality of life for low vision patients with CVL, highlighting the potential benefits and the need for further evaluation of such devices.

Background Polypoidal choroidal vasculopathy (PCV) is a hemorrhagic fundus disease that can lead to permanent vision loss. Predicting the treatment response to anti-VEGF monotherapy in PCV is consistently challenging. We aimed to conduct a prospective multicenter study to explore and identify the imaging biomarkers for predicting the anti-VEGF treatment response in PCV patients, establish predictive model, and undergo multicenter validation.Methods This prospective multicenter study utilized clinical characteristics and images of treatment naïve PCV patients from 15 ophthalmic centers nationwide to screen biomarkers, develop model, and validate its performance. Patients from Peking Union Medical College Hospital were randomly divided into a training set and an internal validation set. A nomogram was established by univariate, LASSO regression, and multivariate regression analysis. Patients from the other 14 centers served as an external test set. Area under the curve (AUC), sensitivity, specificity, and accuracy were calculated. Decision curve analysis (DCA) and clinical impact curve (CIC) were utilized to evaluate the practical utility in clinical decision-making.Findings The eye distribution for the training set, internal validation set, and external test set were 66, 31, and 71, respectively. The ‘Good responder’ exhibited a thinner subfoveal choroidal thickness (SFCT) (230.67 ± 61.96 vs. 314.42 ± 88.00 μm, p

BackgroundAlthough ophthalmic ambulatory surgeries are less costly and may enhance the more efficient utilization of hospital resources, inpatient surgeries were preferable alternatives for patients with complicated eye diseases or poor general health. However, the incidence, causes, and related factors of ophthalmic inpatient surgery cancellation remained largely unknown.MethodsThe electronic medical records of ophthalmic inpatient surgeries between January 2012 and December 2022 was retrospectively reviewed. Cancellation-related factors were explored using multivariate logistic regression analysis and the reasons of cancellation were also evaluated.ResultsIn total, 820 cancelled surgeries and 42,073 performed surgeries were included, with a cancellation rate of 1.9%. Any other ocular comorbidities were risk factors for cancellation (odds ratio (OR) 1.872, 95% confidence intervals (CI) 1.504–2.331; p

PurposeTo investigate the causal relationship between gut microbiota (GM) and chalazion through Mendelian randomization (MR) analysis.MethodsGM-related genome-wide association studies (GWAS) were obtained from the International Consortium MiBioGen. Genetic data for chalazion were sourced from the MRC Integrative Epidemiology Unit (IEU) Open GWAS database. Five MR methods, including inverse variance weighted (IVW), were employed to estimate causal relationships. Cochran’s Q test was used to detect heterogeneity, the MR-Egger intercept test and MR-PRESSO regression were utilized to detect horizontal pleiotropy, and the leave-one-out method was employed to validate data stability.ResultsWe identified 1,509 single nucleotide polymorphisms (SNPs) across 119 genera as instrumental variables (IVs) (p

Polypoidal choroidal vasculopathy (PCV) is a disease characterized by subretinal pigment epithelium (RPE) orange-red polypoidal lesions and abnormal branching neovascular networks (BNNs). In recent years, various non-invasive imaging technologies have rapidly developed, especially the emergence of optical coherence tomography angiography (OCTA), multi-spectral imaging, and other technologies, which enable the observation of more features of PCV. In addition, these technologies are faster and less invasive compared to indocyanine green angiography (ICGA). Multi-modal imaging, which combined multiple imaging techniques, provides important references for the diagnosis and treatment of PCV with the assistance of regression models, deep learning, and other algorithms. In this study, we reviewed the non-invasive imaging techniques, multi-modal imaging diagnosis, and multi-scene therapeutic applications of PCV, with the aim of providing a reference for non-invasive multi-modal diagnosis and treatment of PCV.

BackgroundTo explore the central and peripheral retinal and choroidal changes in diabetic patients without clinical diabetic retinopathy (DM-NoDR) using ultra-wide-field swept-source optical coherence tomography angiography (UWF-SS-OCTA).Methods67 DM-NoDR eyes and 32 age-matched healthy eyes were recruited. Retinal and choroidal parameters, including qualitative retinal microangiopathy, vessel flow (VFD) and linear density (VLD), thickness, and volume, were measured in the central and peripheral areas of the 24 × 20 mm2 UWF-SS-OCTA images.ResultsDM-NoDR eyes had significantly more nonperfusion area and capillary tortuosity than controls in the central and peripheral areas (p

The gold standard for polypoidal choroidal vasculopathy (PCV) diagnosis is indocyanine green angiography (ICGA), but optical coherence tomography angiography (OCTA) has shown promise for PCV imaging in recent years. However, earlier generations of OCTA technology lacked the diagnostic efficacy to replace ICGA. Swept-source optical coherence tomography angiography (SS-OCTA), the latest generation of OCTA technology, has significantly improved penetrating ability, scanning speed, scanning range, and overall image quality compared with earlier generations of OCTA. SS-OCTA reveals a “tangled vasculature” pattern of polypoidal lesions (PLs), providing evidence that they are neovascular rather than aneurysmal structures. New choroidal biomarkers, such as the choriocapillaris flow void (FV), have been identified to explain the development of PCV lesions. Although no direct comparison between SS-OCTA and previous OCTA generations in terms of diagnostic capability has been performed, SS-OCTA has shown several advantages in differential diagnosis and monitoring early reactivation for PCV. These improvements make SS-OCTA a valuable tool for PCV diagnosis and follow-up, and it may become more important for this disease in the future. This review summarized recent advances in PCV morphology and structure, as well as the possible pathogenesis based on SS-OCTA findings. The value of SS-OCTA for PCV management is discussed, along with remaining issues, to provide an updated understanding of PCV and OCTA-guided management.

ObjectivesIn order to evaluate the operational effectiveness of surface warships more reasonably, this article proposes improving the existing evaluation methods to better suit complex battlefield environments. Methods First, according to operational test items and test scenarios planning, the content of the warship platform test items are analyzed, and classification standards for complex battlefield environments' operational intensity and electromagnetic environment are designed. An improved method for evaluating combat effectiveness based on the influence factors of complex battlefield environments is then proposed, and the operational effectiveness of a certain type of surface warship in an anti-air warfare environment is evaluated. ResultsThe results show that the proposed method is effective. Conclusions The proposed method fully considers the influence of complex battlefield environments on the combat capability of different operational units, and solves the problem of existing operational effectiveness evaluation methods failing to fit the actual situation of complex battlefield environments. As such, this study can provide valuable references for the operational testing of naval vessels.

In the production process of aerospace structural parts, there coexist batch production tasks and research and development (R&D) tasks. Personalized small-batch R&D and production tasks lead to frequent emergency insertion orders. In order to ensure that the task is completed on schedule and to solve the flexible job shop dynamic scheduling problem, this paper takes minimization of equipment average load and total completion time as optimization goals, and proposes a dual-loop deep Q network (DL-DQN) method driven by a perception-cognition dual system. Based on the knowledge graph, the perception system realizes the representation of workshop knowledge and the generation of multi-dimensional information matrix. The cognitive system abstracts the scheduling process into two stages: resource allocation agent and process sequencing agent, corresponding to two optimization goals respectively. The workshop status matrix is designed to describe the problems and constraints. In scheduling decision, action instructions are introduced step by step. Finally, the reward function is designed to realize the evaluation of resource allocation decision and process sequence decision. Application of the proposed method in the aerospace shell processing of an aerospace institute and comparative analysis of different algorithms verify the superiority of the proposed method.