Intraocular cetuximab: Safety and effect on axial elongation in young Guinea pigs with lens-induced myopization.

This study aimed to examine the intraocular tolerability of the epidermal growth factor receptor antibody cetuximab, when applied intravitreally, and its effect on axial elongation. Guinea pigs aged 2-3 weeks were subjected to bilateral plano glasses and bilateral lens-induced myopization (LIM) as a single procedure for group I (n = 8) and group II (n = 8), respectively. In the animals of group III (n = 8), group IV (n = 8), and group V (n = 8), the right eyes of the animals, in addition to LIM, received four weekly intravitreal injections of cetuximab (Erbitux®) in doses of 6.25 µg, 12.5 µg, and 25 µg, respectively. As controls, the left eyes, in addition to LIM, received corresponding intraocular injections of phosphate-buffered saline. The animals underwent regular ophthalmoscopic examinations and biometry for axial length measurements. With increasing doses of cetuximab, the inter-eye difference in axial elongation (at study end, left eyes minus right eyes) were significantly the smallest in group I (0.00 ± 0.02 mm) and group II (-0.01 ± 0.02 mm), they were larger in group III (0.04 ± 0.04 mm) and group IV (0.10 ± 0.03 mm), and they were the largest in group V (0.11 ± 0.01 mm). The inter-eye difference in axial elongation enlarged (P < 0.001) with the number of injections applied. Retinal thickness at the posterior pole (right eyes) was significantly thicker in group V than in group II (P < 0.01). The density of apoptotic cells (visualized by TUNEL-staining) did not vary significantly between any of the groups (all P > 0.05). The results suggest that intravitreal injections of cetuximab in young guinea pigs with LIM resulted in a reduction in axial elongation in a dose-dependent and number of treatment-dependent manner. Intraocular toxic effects, such as intraocular inflammation, retinal thinning, or an increased density of apoptotic cells in the retina, were not observed in association with the intravitreally applied cetuximab.

Automatic retinoblastoma screening and surveillance using deep learning.

BACKGROUND: Retinoblastoma is the most common intraocular malignancy in childhood. With the advanced management strategy, the globe salvage and overall survival have significantly improved, which proposes subsequent challenges regarding long-term surveillance and offspring screening. This study aimed to apply a deep learning algorithm to reduce the burden of follow-up and offspring screening. METHODS: This cohort study includes retinoblastoma patients who visited Beijing Tongren Hospital from March 2018 to January 2022 for deep learning algorism development. Clinical-suspected and treated retinoblastoma patients from February 2022 to June 2022 were prospectively collected for prospective validation. Images from the posterior pole and peripheral retina were collected, and reference standards were made according to the consensus of the multidisciplinary management team. A deep learning algorithm was trained to identify "normal fundus", "stable retinoblastoma" in which specific treatment is not required, and "active retinoblastoma" in which specific treatment is required. The performance of each classifier included sensitivity, specificity, accuracy, and cost-utility. RESULTS: A total of 36,623 images were included for developing the Deep Learning Assistant for Retinoblastoma Monitoring (DLA-RB) algorithm. In internal fivefold cross-validation, DLA-RB achieved an area under curve (AUC) of 0.998 (95% confidence interval [CI] 0.986-1.000) in distinguishing normal fundus and active retinoblastoma, and 0.940 (95% CI 0.851-0.996) in distinguishing stable and active retinoblastoma. From February 2022 to June 2022, 139 eyes of 103 patients were prospectively collected. In identifying active retinoblastoma tumours from all clinical-suspected patients and active retinoblastoma from all treated retinoblastoma patients, the AUC of DLA-RB reached 0.991 (95% CI 0.970-1.000), and 0.962 (95% CI 0.915-1.000), respectively. The combination between ophthalmologists and DLA-RB significantly improved the accuracy of competent ophthalmologists and residents regarding both binary tasks. Cost-utility analysis revealed DLA-RB-based diagnosis mode is cost-effective in both retinoblastoma diagnosis and active retinoblastoma identification. CONCLUSIONS: DLA-RB achieved high accuracy and sensitivity in identifying active retinoblastoma from the normal and stable retinoblastoma fundus. It can be used to surveil the activity of retinoblastoma during follow-up and screen high-risk offspring. Compared with referral procedures to ophthalmologic centres, DLA-RB-based screening and surveillance is cost-effective and can be incorporated within telemedicine programs. CLINICAL TRIAL REGISTRATION: This study was registered on ClinicalTrials.gov (NCT05308043).

Electrochemical Reconstruction of NiFe/NiFeOOH Superparamagnetic Core/Catalytic Shell Heterostructure for Magnetic Heating Enhancement of Oxygen Evolution Reaction.

Although (oxy)hydroxides generated by electrochemical reconstruction (EC-reconstruction) of transition-metal catalysts exhibit highly catalytic activities, the amorphous nature fundamentally impedes the electrochemical kinetics due to its poor electrical conductivity. Here, EC-reconstructed NiFe/NiFeOOH core/shell nanoparticles in highly conductive carbon matrix based on the pulsed laser deposition prepared NiFe nanoparticles is successfully confined. Electrochemical characterizations and first-principles calculations demonstrate that the reconstructed NiFe/NiFeOOH core/shell nanoparticles exhibit high oxygen evolution reaction (OER) electrocatalytic activity (a low overpotential of 342.2 mV for 10 mA cm-2 ) and remarkable durability due to the efficient charge transfer in the highly conductive confined heterostructure. More importantly, benefit from the superparamagnetic nature of the reconstructed NiFe/NiFeOOH core/shell nanoparticles, a large OER improvement is achieved (an ultralow overpotential of 209.2 mV for 10 mA cm-2 ) with an alternating magnetic field stimulation. Such OER improvement can be attributed to the Néel relaxation related magnetic heating effect functionalized superparamagnetic NiFe cores, which are generally underutilized in reconstructed core/shell nanoparticles. This work demonstrates that the designed superparamagnetic core/shell nanoparticles, combined with the large improvement by magnetic heating effect, are expected to be highly efficient OER catalysts along with the confined structure guaranteed high conductivity and catalytic stability.

External Fields Assisted Highly Efficient Oxygen Evolution Reaction of Confined 1T-VSe2 Ferromagnetic Nanoparticles.

As a clean and effective approach, the introduction of external magnetic fields to improve the performance of catalysts has attracted extensive attention. Owing to its room-temperature ferromagnetism, chemical stability, and earth abundance, VSe2 is expected to be a promising and cost-effective ferromagnetic electrocatalyst for the accomplishment of high-efficient spin-related OER kinetics. In this work, a facile pulsed laser deposition (PLD) method combined with rapid thermal annealing (RTA) treatment is used to successfully confine monodispersed 1T-VSe2 nanoparticles in amorphous carbon matrix. As expected, with external magnetic fields of 800 mT stimulation, the confined 1T-VSe2 nanoparticles exhibit highly efficient oxygen evolution reaction (OER) catalytic activity with an overpotential of 228 mV for 10 mA cm-2 and remarkable durability without deactivation after >100 h OER operation. The experimental results together with theoretical calculations illustrate that magnetic fields can facilitate the surface charge transfer dynamics of 1T-VSe2 , and modify the adsorption-free energy of *OOH, thus finally improving the intrinsic activity of the catalysts. This work realizes the application of ferromagnetic VSe2 electrocatalyst in highly efficient spin-dependent OER kinetics, which is expected to promote the application of transition metal chalcogenides (TMCs) in external magnetic field-assisted electrocatalysis.

Development and validation of medical record-based logistic regression and machine learning models to diagnose diabetic retinopathy.

PURPOSES: Many factors were reported to be associated with diabetic retinopathy (DR); however, their contributions remained unclear. We aimed to evaluate the prognostic and diagnostic accuracy of logistic regression and three machine learning models based on various medical records. METHODS: This was a cross-sectional study. We investigated the prevalence and associations of DR among 757 participants aged 40 years or older in the 2005-2006 National Health and Nutrition Examination Survey (NHANES). We trained the models to predict if the participants had DR with 15 predictor variables. Area under the receiver operating characteristic (AUROC) and mean squared error (MSE) of each algorithm were compared in the external validation dataset using a replicate cohort from NHANES 2007-2008. RESULTS: Among the 757 participants, 53 (7.00%) subjects had DR, the mean (standard deviation, SD) age was 57.7 (13.04), and 78.0% were male (n = 42). Logistic regression revealed that female gender (OR = 4.130, 95% CI: 1.820-9.380; P < 0.05), HbA1c (OR = 1.665, 95% CI: 1.197-2.317; P < 0.05), serum creatine level (OR = 2.952, 95% CI: 1.274-6.851; P < 0.05), and eGFR level (OR = 1.009, 95% CI: 1.000-1.014, P < 0.05) increased the risk of DR. The average performance obtained from internal validation was similar in all models (AUROC ≥ 0.945), and k-nearest neighbors (KNN) had the highest value with an AUROC of 0.984. In external validation, they remained robust or with modest reductions in discrimination with AUROC still ≥ 0.902, and KNN also performed the best with an AUROC of 0.982. Both logistic regression and machine learning models had good performance in the clinical diagnosis of DR. CONCLUSIONS: This study highlights the utility of comparing traditional logistic regression to machine learning models. We found that logistic regression performed as well as optimized machine learning methods when classifying DR patients.

Boosting the OER Performance of Nitrogen-Doped Ni Nanoclusters Confined in an Amorphous Carbon Matrix.

Nanoclusters are ideal electrocatalysts due to their high surface activity. However, their high activities also lead to serious agglomeration and performance attenuation during the catalytic process. Here, highly dispersed Ni nanoclusters (∼3 nm) confined in an amorphous carbon matrix are successfully fabricated by pulsed laser deposition, followed by rapid temperature annealing treatment. Then, the Ni nanoclusters are further doped with nitrogen element through a clean N2 radio frequency plasma technology. It is found that the nitrogen-doped Ni nanoclusters obtained under optimized conditions showed superior OER performance with a very low overpotential of 240 mV at a current density of 10 mA/cm2, together with good stability. The excellent OER performance of the nanoclusters can be attributed to the unique confined structure and nitrogen doping, which not only provide more active sites but also improve the conductivity. Our work provides a controllable method for the construction of a novel confined structure with controllable nitrogen doping, which can be used as a high-efficiency OER electrocatalyst.

Screening for novel risk factors related to high myopia using machine learning.

BACKGROUND: High myopia-related complications have become a major cause of irreversible vision loss. Evaluating the association between potential factors and high myopia can provide insights into pathophysiologic mechanisms and further intervention targets for myopia progression. METHOD: Participants aged 12-25 years from National Health and Nutrition Examination Survey 2001-2006 were selected for the analysis. Myopia was defined as spherical equivalent (sum of spherical error and half of the cylindrical error) of any eyes ≤-0.5 diopters. High myopia was defined as the spherical equivalent of any eye ≤ - 5.00 diopters. Essential variables were selected by Random Forest algorithm and verified by multivariable logistic regression. RESULTS: A total of 7,033 participants and 74 potential factors, including demographic (4 factors), physical examination (6 factors), nutritional and serological (45 factors), immunological (9 variables), and past medical history factors (10 factors), were included into the analysis. Random Forest algorithm found that several anthropometric, nutritional, and serological factors were associated with high myopia. Combined with multivariable logistic regression, high levels of serum vitamin A was significantly associated with an increased prevalence of high myopia (adjusted odd ratio = 1.46 for 1 µmol/L increment, 95% confidence interval [CI] 1.01-2.10). Furthermore, we found that neither C-reactive protein nor asthma increased the risk and severity of myopia. CONCLUSION: High levels of serum vitamin A was seemingly associated with an increased prevalence of high myopia. This borderline significant association should be interpreted with caution because the potential increased type I error after the multiple testing. It still needs further investigation regarding the mechanism underlying this association. Neither C-reactive protein nor asthma increased the risk and severity of myopia.

Epiregulin, epigen and betacellulin antibodies and axial elongation in young guinea pigs with lens-induced myopization.

BACKGROUND: To examine an effect of intravitreally applied antibodies against epidermal growth factor family members, namely epiregulin, epigen and betacellulin, on ocular axial elongation. METHODS: The experimental study included 30 guinea pigs (age:3-4 weeks) which underwent bilateral lens-induced myopization and received three intraocular injections of 20 µg of epiregulin antibody, epigen antibody and betacellulin antibody in weekly intervals into their right eyes, and of phosphate-buffered saline into their left eyes. Seven days after the last injection, the animals were sacrificed. Axial length was measured by sonographic biometry. RESULTS: At baseline, right eyes and left eyes did not differ (all P > 0.10) in axial length in neither group, nor did the interocular difference in axial length vary between the groups (P = 0.19). During the study period, right and left eyes elongated (P < 0.001) from 8.08 ± 0.07 mm to 8.59 ± 0.06 mm and from 8.08 ± 0.07 mm to 8.66 ± 0.07 mm, respectively. The interocular difference (left eye minus right eye) in axial elongation increased significantly in all three groups (epiregulin-antibody:from 0.03 ± 0.06 mm at one week after baseline to 0.16 ± 0.08 mm at three weeks after baseline;P = 0.001); epigen-antibody group:from -0.01 ± 0.06 mm to 0.06 ± 0.08 mm;P = 0.02; betacellulin antibody group:from -0.05 ± 0.05 mm to 0.02 ± 0.04 mm;P = 0.004). Correspondingly, interocular difference in axial length increased from -0.02 ± 0.04 mm to 0.13 ± 0.06 mm in the epiregulin-antibody group (P < 0.001), and from 0.01 ± 0.05 mm to 0.07 ± 0.05 mm in the epigen-antibody group (P = 0.045). In the betacellulin-antibody group the increase (0.01 ± 0.04 mm to 0.03 ± 0.03 mm) was not significant (P = 0.24). CONCLUSIONS: The EGF family members epiregulin, epigen and betacellulin may be associated with axial elongation in young guinea pigs, with the effect decreasing from epiregulin to epigen and to betacellulin.

Field-Free Improvement of Oxygen Evolution Reaction in Magnetic Two-Dimensional Heterostructures.

Ferromagnetic (FM) electrocatalysts have been demonstrated to reduce the kinetic barrier of oxygen evolution reaction (OER) by spin-dependent kinetics and thus enhance the efficiency fundamentally. Accordingly, FM two-dimensional (2D) materials with unique physicochemical properties are expected to be promising oxygen-evolution catalysts; however, related research is yet to be reported due to their air-instabilities and low Curie temperatures (TC). Here, based on the synthesis of 2D air-stable FM Cr2Te3 nanosheets with a low TC around 200 K, room-temperature ferromagnetism is achieved in Cr2Te3 by proximity to an antiferromagnetic (AFM) CrOOH, demonstrating the accomplishment of long-ranged FM ordering in Cr2Te3 because the magnetic proximity effect stems from paramagnetic (PM)/AFM heterostructure. Therefore, the OER performance can be permanently promoted (without applied magnetic field due to nonvolatile nature of spin) after magnetization. This work demonstrates that a representative PM/AFM 2D heterostructure, Cr2Te3/CrOOH, is expected to be a high-efficient magnetic heterostructure catalysts for oxygen-evolution.

MoS2 Nanoribbons with a Prolonged Photoresponse Lifetime for Enhanced Visible Light Photoelectrocatalytic Hydrogen Evolution.

The high recombination rate of photoinduced electron-hole pairs limits the hydrogen production efficiency of the MoS2 catalyst in photoelectrochemical (PEC) water splitting. The strategy of prolonging the lifetime of photoinduced carriers is of great significance to the promotion of photoelectrocatalytic hydrogen production. An ideal approach is to utilize edge defects, which can capture photoinduced electrons and thus slow down the recombination rate. However, for two-dimensional MoS2, most of the surface areas are inert basal planes. Here, a simple method for preparing one-dimensional MoS2 nanoribbons with abundant inherent edges is proposed. The MoS2 nanoribbon-based device has a good spectral response in the range of 400-500 nm and has a longer lifetime of photoinduced carriers than other MoS2 nanostructure-based photodetectors. An improved PEC catalytic performance of these MoS2 nanoribbons is also experimentally verified under the illumination of 405 nm by using the electrochemical microcell technique. This work provides a new strategy to prolong the lifetime of photoinduced carriers for further improvement of PEC activity, and the evaluation of photoelectric performance provides a feasible way for transition-metal dichalcogenides to be widely used in the energy field.

General synthesis of mixed-dimensional van der Waals heterostructures with hexagonal symmetry.

The combination of two-dimensional (2D) materials with non-2D materials (quantum dots, nanowires and bulk materials), i.e. mixed-dimensional van der Waals (md-vdW) heterostructures endow 2D materials with remarkable electronics properties. However, it remains a big challenge to synthesize md-vdW heterostructures because of the difference of crystal symmetry between 2D and non-2D materials. Meanwhile, it is difficult to initiate the nucleation due to the lack of chemical active sites on chemical inert surfaces of 2D materials. Herein, we design a general chemical vapor deposition method for synthesizing a broad class of md-vdW heterostructures with well-aligned hexagonal symmetry including MoS2/FeS, MoS2/CoS, MoS2/MnS, MoS2/ZnS, Mo(SxSe1-x)2/ZnSxSe1-x, Mo(SxSe1-x)2/CdSxSe1-x. Combining with DFT calculation, we find that the hexagonal symmetry and the centered clusters of MoS2and Mo(SxSe1-x)2nanoflakes are two crucial factors to launch the hexagonally oriented growth and nucleation of non-2D materials on 2D materials. Our discovery opens an opportunity for the versatile hetero-integration of 2D materials and allows systematic investigation of physical properties in a wide variety of md-vdW heterostructures.

Global, regional, and national prevalence, disability adjusted life years, and time trends for refraction disorders, 1990-2019: findings from the global burden of disease study 2019.

BACKGROUND: To evaluate global burden of refraction disorders by year, age, region, gender, socioeconomic status and other national characteristics in terms of disability adjusted life years (DALYs) and prevalence from Global Burden of Disease (GBD) study 2019 and World Bank Open Data 2019. METHODS: Global, regional, and national DALY numbers, crude DALY rates, age-standardized DALY and prevalence rates of refraction disorders were acquired from the GBD study 2019. Mobile cellular subscriptions, urban population, GDP per capita, access to electricity and total fertility rate were obtained from the World Bank to explore the factors that influenced the health burden of refraction disorders. Kruskal-Wallis test, linear regression and multiple linear regression were performed to evaluate the associations between the health burden with socioeconomic levels and other national characteristics. Wilcoxon Signed-Rank Test was used to investigate the gender disparity. RESULTS: Globally, age-standardized DALY rates of refraction disorders decreased from 88.9 (95% UI: 60.5-120.3) in 1990 to 81.5 (95% UI: 55.0-114.8) in 2019, and might fall to 73.16 (95% UI: 67.81-78.51) by 2050. Age-standardized prevalence rates would also reduce to 1830 (95% UI: 1700-1960) by 2050, from 2080 (95% UI: 1870-2310) in 1990 to 1960 (95% UI: 1750-2180) in 2019. In low SDI region, age-standardized DALY rates (equation: Y = 114.05*X + 27.88) and prevalence rates (equation: Y = 3171.1*X + 403.2) were positively correlated with SDI in linear regression respectively. East Asia had the highest blindness rate caused by refraction disorders in terms of age-standardized DALY rates (11.20, 95% UI: 7.38-16.36). Gender inequality was found among different age groups and SDI regions. CONCLUSION: Health burden of refraction disorders decreased in recent years, and may continue to alleviate in the next three decades. Older ages, females and lower socioeconomic status were associated with higher refraction disorders health burden.

Magnetic Enhancement for Hydrogen Evolution Reaction on Ferromagnetic MoS2 Catalyst.

Numerous efforts in improving the hydrogen evolution reaction (HER) performance of transition metal dichalcogenides mostly focus on active sites exposing, vacancy engineering, and phase engineering. However, little room is left for improvement in these approaches. It should be noted that efficient electron transfer also plays a crucial role in catalytic activity. In this work, by employment of an external vertical magnetic field, ferromagnetic bowl-like MoS2 flakes can afford electrons transmitting easily from a glassy carbon electrode to active sites to drive HER, and thus perform magnetic HER enhancement. The ferromagnetic bowl-like MoS2 flakes with an external vertical magnetic field can provide a roughly doubled current density compared to that without an external vertical magnetic field at a constant overpotential of -150 mV. Our work may provide a new pathway to break the bottleneck for further improvement of HER performance and also paves the way to utilize the magnetic enhancement in widely catalytic application.

The challenge of detecting genotype-by-methylation interaction: GAW20.

BACKGROUND: GAW20 working group 5 brought together researchers who contributed 7 papers with the aim of evaluating methods to detect genetic by epigenetic interactions. GAW20 distributed real data from the Genetics of Lipid Lowering Drugs and Diet Network (GOLDN) study, including single-nucleotide polymorphism (SNP) markers, methylation (cytosine-phosphate-guanine [CpG]) markers, and phenotype information on up to 995 individuals. In addition, a simulated data set based on the real data was provided. RESULTS: The 7 contributed papers analyzed these data sets with a number of different statistical methods, including generalized linear mixed models, mediation analysis, machine learning, W-test, and sparsity-inducing regularized regression. These methods generally appeared to perform well. Several papers confirmed a number of causative SNPs in either the large number of simulation sets or the real data on chromosome 11. Findings were also reported for different SNPs, CpG sites, and SNP-CpG site interaction pairs. CONCLUSIONS: In the simulation (200 replications), power appeared generally good for large interaction effects, but smaller effects will require larger studies or consortium collaboration for realizing a sufficient power.

Novel Bioengineered Three-Dimensional Human Intestinal Model for Long-Term Infection of Cryptosporidium parvum.

Cryptosporidium spp. are apicomplexan parasites of global importance that cause human diarrheal disease. In vitro culture models that may be used to study this parasite and that have physiological relevance to in vivo infection remain suboptimal. Thus, the pathogenesis of cryptosporidiosis remains poorly characterized, and interventions for the disease are limited. In this study, we evaluated the potential of a novel bioengineered three-dimensional (3D) human intestinal tissue model (which we developed previously) to support long-term infection by Cryptosporidium parvum Infection was assessed by immunofluorescence assays and confocal and scanning electron microscopy and quantified by quantitative reverse transcription-PCR. We found that C. parvum infected and developed in this tissue model for at least 17 days, the extent of the study time used in the present study. Contents from infected scaffolds could be transferred to fresh scaffolds to establish new infections for at least three rounds. Asexual and sexual stages and the formation of new oocysts were observed during the course of infection. Additionally, we observed ablation, blunting, or distortion of microvilli in infected epithelial cells. Ultimately, a 3D model system capable of supporting continuous Cryptosporidium infection will be a useful tool for the study of host-parasite interactions, identification of putative drug targets, screening of potential interventions, and propagation of genetically modified parasites.

Short-term electrical stimulation to promote nerve repair and functional recovery in a rat model.

PURPOSE: To evaluate the effect of duration of electrical stimulation on peripheral nerve regeneration and functional recovery. Based on previous work, we hypothesized that applying 10 minutes of electrical stimulation to a 10-mm rat sciatic nerve defect would significantly improve nerve regeneration and functional recovery compared with the non-electrical stimulation group. METHODS: A silicone tube filled with a collagen gel was used to bridge a 10-mm nerve defect in rats, and either 10 minutes or 60 minutes of electrical stimulation was applied to the nerve during surgery. Controls consisted of a silicone tube with collagen gel and no electrical stimulation or an isograft. We analyzed recovery over a 12-week period, measuring sciatic functional index and extensor postural thrust scores and concluding with histological examination of the nerve. RESULTS: Functional assessment scores at week 12 increased 24% in the 10-minute group as compared to the no stimulation control group. Electrical stimulation of either 10 or 60 minutes improved the number of nerve fibers over no stimulation. Additionally, the electrical stimulation group's histomorphometric analysis was not different from the isograft group. CONCLUSIONS: Several previous studies have demonstrated the effectiveness of 60-minute stimulations on peripheral nerve regeneration. This study demonstrated that an electrical stimulation of 10 minutes enhanced several functional and histomorphometric outcomes of nerve regeneration and was overall similar to a 60-minute stimulation over 12 weeks. CLINICAL RELEVANCE: Decreasing the electrical stimulation time from 60 minutes to 10 minutes provided a potential clinically feasible and safe method to enhance nerve regeneration and functional recovery.

Predicting systemic diseases in fundus images: systematic review of setting, reporting, bias, and models' clinical availability in deep learning studies.

BACKGROUND: Analyzing fundus images with deep learning techniques is promising for screening systematic diseases. However, the quality of the rapidly increasing number of studies was variable and lacked systematic evaluation. OBJECTIVE: To systematically review all the articles that aimed to predict systemic parameters and conditions using fundus image and deep learning, assessing their performance, and providing suggestions that would enable translation into clinical practice. METHODS: Two major electronic databases (MEDLINE and EMBASE) were searched until August 22, 2023, with keywords 'deep learning' and 'fundus'. Studies using deep learning and fundus images to predict systematic parameters were included, and assessed in four aspects: study characteristics, transparent reporting, risk of bias, and clinical availability. Transparent reporting was assessed by the TRIPOD statement, while the risk of bias was assessed by PROBAST. RESULTS: 4969 articles were identified through systematic research. Thirty-one articles were included in the review. A variety of vascular and non-vascular diseases can be predicted by fundus images, including diabetes and related diseases (19%), sex (22%) and age (19%). Most of the studies focused on developed countries. The models' reporting was insufficient in determining sample size and missing data treatment according to the TRIPOD. Full access to datasets and code was also under-reported. 1/31(3.2%) study was classified as having a low risk of bias overall, whereas 30/31(96.8%) were classified as having a high risk of bias according to the PROBAST. 5/31(16.1%) of studies used prospective external validation cohorts. Only two (6.4%) described the study's calibration. The number of publications by year increased significantly from 2018 to 2023. However, only two models (6.5%) were applied to the device, and no model has been applied in clinical. CONCLUSION: Deep learning fundus images have shown great potential in predicting systematic conditions in clinical situations. Further work needs to be done to improve the methodology and clinical application.

Trends in the Prevalence of Common Retinal and Optic Nerve Diseases in China: An Artificial Intelligence Based National Screening.

Purpose: Retinal and optic nerve diseases have become the primary cause of irreversible vision loss and blindness. However, there is still a lack of thorough evaluation regarding their prevalence in China. Methods: This artificial intelligence-based national screening study applied a previously developed deep learning algorithm, named the Retinal Artificial Intelligence Diagnosis System (RAIDS). De-identified personal medical records from January 2019 to December 2021 were extracted from 65 examination centers in 19 provinces of China. Crude prevalence and age-sex-adjusted prevalence were calculated by mapping to the standard population in the seventh national census. Results: In 2021, adjusted referral possible glaucoma (63.29, 95% confidence interval [CI] = 57.12-68.90 cases per 1000), epiretinal macular membrane (21.84, 95% CI = 15.64-29.22), age-related macular degeneration (13.93, 95% CI = 11.09-17.17), and diabetic retinopathy (11.33, 95% CI = 8.89-13.77) ranked the highest among 10 diseases. Female participants had significantly higher adjusted prevalence of pathologic myopia, yet a lower adjusted prevalence of diabetic retinopathy, referral possible glaucoma, and hypertensive retinopathy than male participants. From 2019 to 2021, the adjusted prevalence of retinal vein occlusion (0.99, 95% CI = 0.73-1.26 to 1.88, 95% CI = 1.42-2.44), macular hole (0.59, 95% CI = 0.41-0.82 to 1.12, 95% CI = 0.76-1.51), and hypertensive retinopathy (0.53, 95% CI = 0.40-0.67 to 0.77, 95% CI = 0.60-0.95) significantly increased. The prevalence of diabetic retinopathy in participants under 50 years old significant increased. Conclusions: Retinal and optic nerve diseases are an important public health concern in China. Further well-conceived epidemiological studies are required to validate the observed increased prevalence of diabetic retinopathy, hypertensive retinopathy, retinal vein occlusion, and macular hole nationwide. Translational Relevance: This artificial intelligence system can be a potential tool to monitor the prevalence of major retinal and optic nerve diseases over a wide geographic area.

Deep learning system for screening AIDS-related cytomegalovirus retinitis with ultra-wide-field fundus images.

Background: Ophthalmological screening for cytomegalovirus retinitis (CMVR) for HIV/AIDS patients is important to prevent lifelong blindness. Previous studies have shown good properties of automated CMVR screening using digital fundus images. However, the application of a deep learning (DL) system to CMVR with ultra-wide-field (UWF) fundus images has not been studied, and the feasibility and efficiency of this method are uncertain. Methods: In this study, we developed, internally validated, externally validated, and prospectively validated a DL system to detect AIDS-related from UWF fundus images from different clinical datasets. We independently used the InceptionResnetV2 network to develop and internally validate a DL system for identifying active CMVR, inactive CMVR, and non-CMVR in 6960 UWF fundus images from 862 AIDS patients and validated the system in a prospective and an external validation data set using the area under the curve (AUC), accuracy, sensitivity, and specificity. A heat map identified the most important area (lesions) used by the DL system for differentiating CMVR. Results: The DL system showed AUCs of 0.945 (95 % confidence interval [CI]: 0.929, 0.962), 0.964 (95 % CI: 0.870, 0.999) and 0.968 (95 % CI: 0.860, 1.000) for detecting active CMVR from non-CMVR and 0.923 (95 % CI: 0.908, 0.938), 0.902 (0.857, 0.948) and 0.884 (0.851, 0.917) for detecting active CMVR from non-CMVR in the internal cross-validation, external validation, and prospective validation, respectively. Deep learning performed promisingly in screening CMVR. It also showed the ability to differentiate active CMVR from non-CMVR and inactive CMVR as well as to identify active CMVR and inactive CMVR from non-CMVR (all AUCs in the three independent data sets >0.900). The heat maps successfully highlighted lesion locations. Conclusions: Our UWF fundus image-based DL system showed reliable performance for screening AIDS-related CMVR showing its potential for screening CMVR in HIV/AIDS patients, especially in the absence of ophthalmic resources.

Visual impairment and major eye diseases in stroke: a national cross-sectional study.

OBJECTIVES: Major ocular diseases share common risk factors and pathogeneses with stroke. This study aimed to evaluate the relation between stroke and ocular diseases including visual impairment (VI). METHODS: The cross-sectional study investigated the prevalence and associations of VI and major eye diseases with stroke among 4570 participants in the 2005-2008 National Health and Nutrition Examination Survey (NHANES). The association of VI and major ocular diseases with stroke were estimated using univariate and multivariate logistic regression crude models and models adjusted for demographics and clinical factors. We also conducted stratified analyses by diabetes and hypertension status. RESULTS: VI was associated with stroke, and the odds ratios (ORs) for mild and moderate and severe visual impairment (MSVI) were 6.79 (95% confidence interval (CI): 2.44-18.88) and 9.46 (95% CI: 2.19-40.94) after adjusting for age and gender (all P < 0.05). Ocular disease was associated with stroke with OR reaching 5.54 (95% CI: 1.83-16.74), and the OR was 9.61 (95% CI: 3.05-30.23) for stroke patients suffering DR after adjusting for age and gender (all P < 0.05). After multivariable adjustment, the associations were limited to mild VI (OR = 10.00, 95% CI: 3.16-30.58), MSVI (OR = 8.57, 95% CI: 1.58-43.36), and any ocular disease (OR = 5.18, 95% CI: 1.46-18.42) (all P < 0.05). Significant associations between stroke and any ocular disease and DR were observed among diabetic participants, and significant relation between stroke and MSVI was found among hypertension patients. CONCLUSIONS: The sample of the US population demonstrates significant associations between VI and major ocular disease with stroke.