Search

Background/aims: The aim of this study was to develop and evaluate digital ray, based on preoperative and postoperative image pairs using style transfer generative adversarial networks (GANs), to enhance cataractous fundus images for improved retinopathy detection., Methods: For eligible cataract patients, preoperative and postoperative colour fundus photographs (CFP) and ultra-wide field (UWF) images were captured. Then, both the original CycleGAN and a modified CycleGAN (C 2 ycleGAN) framework were adopted for image generation and quantitatively compared using Frechet Inception Distance (FID) and Kernel Inception Distance (KID). Additionally, CFP and UWF images from another cataract cohort were used to test model performances. Different panels of ophthalmologists evaluated the quality, authenticity and diagnostic efficacy of the generated images., Results: A total of 959 CFP and 1009 UWF image pairs were included in model development. FID and KID indicated that images generated by C 2 ycleGAN presented significantly improved quality. Based on ophthalmologists' average ratings, the percentages of inadequate-quality images decreased from 32% to 18.8% for CFP, and from 18.7% to 14.7% for UWF. Only 24.8% and 13.8% of generated CFP and UWF images could be recognised as synthetic. The accuracy of retinopathy detection significantly increased from 78% to 91% for CFP and from 91% to 93% for UWF. For retinopathy subtype diagnosis, the accuracies also increased from 87%-94% to 91%-100% for CFP and from 87%-95% to 93%-97% for UWF., Conclusion: Digital ray could generate realistic postoperative CFP and UWF images with enhanced quality and accuracy for overall detection and subtype diagnosis of retinopathies, especially for CFP.\ TRIAL REGISTRATION NUMBER: This study was registered with ClinicalTrials.gov (NCT05491798)., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Fundus fluorescein angiography (FFA) examinations are widely used in the evaluation of fundus disease conditions to facilitate further treatment suggestions. Here, we present a protocol for performing deep learning-based FFA image analytics with classification and segmentation tasks. We describe steps for data preparation, model implementation, statistical analysis, and heatmap visualization. The protocol is applicable in Python using customized data and can achieve the whole process from diagnosis to treatment suggestion of ischemic retinal diseases. For complete details on the use and execution of this protocol, please refer to Zhao et al. 1 ., Competing Interests: Declaration of interests Z.L., D.L., S.Y., H.L., X.L., and X.Z. reported a valid patent (patent number ZL 2022 1 0715436.3; A fluorescein fundus angiography image processing system and device), which is used for NPA and BRVO area segmentation., (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)

Importance: Although augmenting large language models (LLMs) with knowledge bases may improve medical domain-specific performance, practical methods are needed for local implementation of LLMs that address privacy concerns and enhance accessibility for health care professionals., Objective: To develop an accurate, cost-effective local implementation of an LLM to mitigate privacy concerns and support their practical deployment in health care settings., Design, Setting, and Participants: ChatZOC (Sun Yat-Sen University Zhongshan Ophthalmology Center), a retrieval-augmented LLM framework, was developed by enhancing a baseline LLM with a comprehensive ophthalmic dataset and evaluation framework (CODE), which includes over 30 000 pieces of ophthalmic knowledge. This LLM was benchmarked against 10 representative LLMs, including GPT-4 and GPT-3.5 Turbo (OpenAI), across 300 clinical questions in ophthalmology. The evaluation, involving a panel of medical experts and biomedical researchers, focused on accuracy, utility, and safety. A double-masked approach was used to try to minimize bias assessment across all models. The study used a comprehensive knowledge base derived from ophthalmic clinical practice, without directly involving clinical patients., Exposures: LLM response to clinical questions., Main Outcomes and Measures: Accuracy, utility, and safety of LLMs in responding to clinical questions., Results: The baseline model achieved a human ranking score of 0.48. The retrieval-augmented LLM had a score of 0.60, a difference of 0.12 (95% CI, 0.02-0.22; P = .02) from baseline and not different from GPT-4 with a score of 0.61 (difference = 0.01; 95% CI, -0.11 to 0.13; P = .89). For scientific consensus, the retrieval-augmented LLM was 84.0% compared with the baseline model of 46.5% (difference = 37.5%; 95% CI, 29.0%-46.0%; P < .001) and not different from GPT-4 with a value of 79.2% (difference = 4.8%; 95% CI, -0.3% to 10.0%; P = .06)., Conclusions and Relevance: Results of this quality improvement study suggest that the integration of high-quality knowledge bases improved the LLM's performance in medical domains. This study highlights the transformative potential of augmented LLMs in clinical practice by providing reliable, safe, and practical clinical information. Further research is needed to explore the broader application of such frameworks in the real world.

Aim: To investigate the association of floor area ratio (FAR), an indicator of built environments, and myopia onset., Methods: This prospective cohort study recruited 136 753 children aged 6-10 years from 108 schools in Shenzhen, China at baseline (2016-2017). Refractive power was measured with non-cycloplegic autorefraction over a 2-year follow-up period. FAR was objectively evaluated using geographical information system technology. Mixed-effects logistic regression models were constructed to examine the association of FAR with a 2-year cumulative incidence of myopia among individuals without baseline myopia; multiple linear regression model, with a 2-year cumulative incidence rate of myopia at each school., Results: Of 101 624 non-myopic children (56.3% boys; mean (SE) age, 7.657±1.182 years) included in the study, 26 391 (26.0%) of them developed myopia after 2 years. In the individual-level analysis adjusting for demographic, socioeconomic and greenness factors, an IQR in FAR was associated with a decreased risk of 2-year myopia incidence (OR 0.898, 95% CI 0.866 to 0.932, p<0.001). Similar findings were observed in the analysis additionally adjusted for genetic and behavioural factors (OR 0.821, 95% CI 0.766 to 0.880, p<0.001). In the school-level, an IQR increase in FAR was found to be associated with a 2.0% reduction in the 2-year incidence rate of myopia (95% CI 1.3% to 2.6%, p<0.001)., Conclusions: Exposure to higher FAR was associated with a decreased myopia incidence, providing insights into myopia prevention through school built environments in China., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Purpose: To explore the factors related to the diagnosis yield of syndromic congenital cataracts and describe the phenotype-genotype correlation in congenital cataract patients., Design: Prospective cohort study., Methods: Setting: the participants from underwent clinical examinations between 2021 and 2022. Facial and anterior eye segment photographs, pre- and postoperative ocular parameters, and medical and family histories were recorded. Bioinformatics analysis was performed using whole-exome sequencing data. Statistical and correlation analyses were performed using the basic characteristics, deep phenotype, and genotype data., Participants: 115 patients with unrelated congenital cataract., Interventions: performing clinical examinations, whole-exome sequencing, and bioinformatics analysis for all participants., Main Outcomes and Measures: factors related to the genetic diagnosis yield of syndromic congenital cataracts., Results: Bilaterally asymmetrical cataracts were identified to be associated with syndromic congenital cataracts. The overall genetic diagnostic yield in the cohort was 72.2%. In total, 34.8% of the probands were early diagnosed with various syndromes with the help of genetic information. A phenotype-genotype correlation was detected for some genes and deep phenotypes., Conclusions: We highlight the importance of screening syndromic diseases in the patients with asymmetrical congenital cataracts. Application of whole-exome sequencing helps provide early diagnosis and treatment for the patients with syndromic congenital cataracts. This study also achieved a high genetic diagnostic yield, expanded the genotypic spectrum, and found phenotype-genotype correlations. A comprehensive analysis of cataract symmetricity, family history, and deep phenotypes makes the genotype prediction of some congenital cataract patients possible., (Copyright © 2023 Elsevier Inc. All rights reserved.)

Background: This study aimed to explore the postoperative myopic shift and its relationship to visual acuity rehabilitation in patients with bilateral congenital cataracts (CCs)., Methods: Bilateral CC patients who underwent cataract extraction and primary intraocular lens implantations before 6 years old were included and divided into five groups according to surgical ages (<2, 2-3, 3-4, 4-5, and 5-6 years). The postoperative myopic shift rates, spherical equivalents (SEs), and the best corrected visual acuity (BCVA) were measured and analyzed., Results: A total of 1,137 refractive measurements from 234 patients were included, with a mean follow-up period of 34 months. The postoperative mean SEs at each follow-up in the five groups were linearly fitted with a mean R 2  = 0.93 ± 0.03, which showed a downtrend of SE with age (linear regression). Among patients with a follow-up of 4 years, the mean postoperative myopic shift rate was 0.84, 0.81, 0.68, 0.24, and 0.28 diopters per year (D/y) in the five age groups (from young to old), respectively. The BCVA of those with a surgical age of <2 years at the 4-year visit was 0.26 (LogMAR), and the mean postoperative myopic shift rate was 0.84 D/y. For patients with a surgical age of 2-6 years, a poorer BCVA at the 4-year visit was found in those with higher postoperative myopic shift rates ( r  = 0.974, p  = 0.026, Pearson's correlation test)., Conclusion: Performing cataract surgery for patients before 2 years old and decreasing the postoperative myopic shift rates for those with a surgical age of 2-6 years may benefit visual acuity rehabilitation., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Lin, Zhu, Zhang, Zhou, Zhao, Wang, Chen, Chen, Lin, Feng, Zhong, Chen, Lin, Li, Xiao, Zhou, Wang, Li and Chen.)

Utilization of digital technologies for cataract screening in primary care is a potential solution for addressing the dilemma between the growing aging population and unequally distributed resources. Here, we propose a digital technology-driven hierarchical screening (DH screening) pattern implemented in China to promote the equity and accessibility of healthcare. It consists of home-based mobile artificial intelligence (AI) screening, community-based AI diagnosis, and referral to hospitals. We utilize decision-analytic Markov models to evaluate the cost-effectiveness and cost-utility of different cataract screening strategies (no screening, telescreening, AI screening and DH screening). A simulated cohort of 100,000 individuals from age 50 is built through a total of 30 1-year Markov cycles. The primary outcomes are incremental cost-effectiveness ratio and incremental cost-utility ratio. The results show that DH screening dominates no screening, telescreening and AI screening in urban and rural China. Annual DH screening emerges as the most economically effective strategy with 341 (338 to 344) and 1326 (1312 to 1340) years of blindness avoided compared with telescreening, and 37 (35 to 39) and 140 (131 to 148) years compared with AI screening in urban and rural settings, respectively. The findings remain robust across all sensitivity analyses conducted. Here, we report that DH screening is cost-effective in urban and rural China, and the annual screening proves to be the most cost-effective option, providing an economic rationale for policymakers promoting public eye health in low- and middle-income countries., (© 2024. The Author(s).)

Background: Emerging three-dimensional digital visualization technology (DVT) provides more advantages than traditional microscopy in microsurgery; however, its impact on microsurgeons' visual and nervous systems and delicate microsurgery is still unclear, which hinders the wider implementation of DVT in digital visualization for microsurgery., Methods and Material: Forty-two microsurgeons from the Zhongshan Ophthalmic Center were enrolled in this prospective self-controlled study. Each microsurgeon consecutively performed 30 min conjunctival sutures using a three-dimensional digital display and a microscope, respectively. Visual function, autonomic nerve activity, and subjective symptoms were evaluated before and immediately after the operation. Visual functions, including accommodative lag, accommodative amplitude, near point of convergence and contrast sensitivity function (CSF), were measured by an expert optometrist. Heart rate variability was recorded by a wearable device for monitoring autonomic nervous activity. Subjective symptoms were evaluated by questionnaires. Microsurgical performance was assessed by the video-based Objective Structured Assessment of Technical Skill (OSATS) tool., Results: Accommodative lag decreased from 0.63 (0.18) diopters (D) to 0.55 (0.16) D ( P =0.014), area under the log contrast sensitivity function increased from 1.49 (0.15) to 1.52 (0.14) ( P =0.037), and heart rate variability decreased from 36.00 (13.54) milliseconds (ms) to 32.26 (12.35) ms ( P =0.004) after using the DVT, but the changes showed no differences compared to traditional microscopy ( P >0.05). No statistical significance was observed for global OSATS scores between the two rounds of operations [mean difference, 0.05 (95% CI: -1.17 to 1.08) points; P =0.95]. Subjective symptoms were quite mild after using both techniques., Conclusions: The impact of DVT-based procedures on microsurgeons includes enhanced accommodation and sympathetic activity, but the changes and surgical performance are not significantly different from those of microscopy-based microsurgery. Our findings indicate that short-term use of DVT is reliable for microsurgery and the long-term effect of using DVT deserve more consideration., (Copyright © 2023 The Author(s). Published by Wolters Kluwer Health, Inc.)

Importance: China has experienced both rapid urbanization and major increases in myopia prevalence. Previous studies suggest that green space exposure reduces the risk of myopia, but the association between myopia risk and specific geometry and distribution characteristics of green space has yet to be explored. These must be understood to craft effective interventions to reduce myopia., Objective: To evaluate the associations between myopia and specific green space morphology using novel quantitative data from high-resolution satellite imaging., Design, Setting, and Participants: This prospective cohort study included students grades 1 to 4 (aged 6 to 9 years) in Shenzhen, China. Baseline data were collected in 2016-2017, and students were followed up in 2018-2019. Data were analyzed from September 2020 to January 2022., Exposures: Eight landscape metrics were calculated using land cover data from high-resolution Gaofen-2 satellite images to measure area, aggregation, and shape of green space., Main Outcome and Measures: The 2-year cumulative change in myopia prevalence at each school and incidence of myopia at the student level after 2 years were calculated as main outcomes. The associations between landscape metrics and school myopia were assessed, controlling for geographical, demographic, and socioeconomic factors. Principal component analyses were performed to further assess the joint effect of landscape metrics at the school and individual level., Results: A total of 138 735 students were assessed at baseline. Higher proportion, aggregation, and better connectivity of green space were correlated with slower increases in myopia prevalence. In the principal component regression, a 1-unit increase in the myopia-related green space morphology index (the first principal component) was negatively associated with a 1.7% (95% CI, -2.7 to -0.6) decrease in myopia prevalence change at the school level (P = .002). At the individual level, a 1-unit increase in myopia-related green space morphology index was associated with a 9.8% (95% CI, 4.1 to 15.1) reduction in the risk of incident myopia (P < .001), and the association remained after further adjustment for outdoor time, screen time, reading time, and parental myopia (adjusted odds ratio, 0.88; 95% CI, 0.80 to 0.97; P = .009)., Conclusions and Relevance: Structure of green space was associated with a decreased relative risk of myopia, which may provide guidance for construction and renovation of schools. Since risk estimates only indicate correlations rather than causation, further interventional studies are needed to assess the effect on school myopia of urban planning and environmental designs, especially size and aggregation metrics of green space, on school myopia.

Aims: To characterise retinal microvascular alterations in the eyes of pregnant patients with anaemia (PA) and to compare the alterations with those in healthy controls (HC) using optical coherence tomography angiography (OCTA)., Methods: This nested case‒control study included singleton PA and HC from the Eye Health in Pregnancy Study. Fovea avascular zone (FAZ) metrics, perfusion density (PD) in the superficial capillary plexus, deep capillary plexus and flow deficit (FD) density in the choriocapillaris (CC) were quantified using FIJI software. Linear regressions were conducted to evaluate the differences in OCTA metrics between PA and HC. Subgroup analyses were performed based on comparisons between PA diagnosed in the early or late trimester and HC., Results: In total, 99 eyes of 99 PA and 184 eyes of 184 HC were analysed. PA had a significantly reduced FAZ perimeter ( β coefficient=-0.310, p<0.001), area ( β coefficient=-0.121, p=0.001) and increased circularity ( β coefficient=0.037, p<0.001) compared with HC. Furthermore, higher PD in the central ( β coefficient=0.327, p=0.001) and outer ( β coefficient=0.349, p=0.007) regions were observed in PA. PA diagnosed in the first trimester had more extensive central FD ( β coefficient=4.199, p=0.003) in the CC, indicating impaired perfusion in the CC., Conclusion: It was found that anaemia during pregnancy was associated with macular microvascular abnormalities, which differed in PA as pregnancy progressed. The results suggest that quantitative OCTA metrics may be useful for risk evaluation before clinical diagnosis., Trial Registration Numbers: 2021KYPJ098 and ChiCTR2100049850., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Data quality issues have been acknowledged as one of the greatest obstacles in medical artificial intelligence research. Here, we present DeepFundus, which employs deep learning techniques to perform multidimensional classification of fundus image quality and provide real-time guidance for on-site image acquisition. We describe steps for data preparation, model training, model inference, model evaluation, and the visualization of results using heatmaps. This protocol can be implemented in Python using either the suggested dataset or a customized dataset. For complete details on the use and execution of this protocol, please refer to Liu et al. 1 ., Competing Interests: Declaration of interests The authors declare no competing interests., (Copyright © 2023 The Authors. Published by Elsevier Inc. All rights reserved.)

Age is closely related to human health and disease risks. However, chronologically defined age often disagrees with biological age, primarily due to genetic and environmental variables. Identifying effective indicators for biological age in clinical practice and self-monitoring is important but currently lacking. The human lens accumulates age-related changes that are amenable to rapid and objective assessment. Here, using lens photographs from 20 to 96-year-olds, we develop LensAge to reflect lens aging via deep learning. LensAge is closely correlated with chronological age of relatively healthy individuals (R 2  > 0.80, mean absolute errors of 4.25 to 4.82 years). Among the general population, we calculate the LensAge index by contrasting LensAge and chronological age to reflect the aging rate relative to peers. The LensAge index effectively reveals the risks of age-related eye and systemic disease occurrence, as well as all-cause mortality. It outperforms chronological age in reflecting age-related disease risks (p < 0.001). More importantly, our models can conveniently work based on smartphone photographs, suggesting suitability for routine self-examination of aging status. Overall, our study demonstrates that the LensAge index may serve as an ideal quantitative indicator for clinically assessing and self-monitoring biological age in humans., (© 2023. The Author(s).)

Importance: Retinal diseases are the leading cause of irreversible blindness worldwide, and timely detection contributes to prevention of permanent vision loss, especially for patients in rural areas with limited medical resources. Deep learning systems (DLSs) based on fundus images with a 45° field of view have been extensively applied in population screening, while the feasibility of using ultra-widefield (UWF) fundus image-based DLSs to detect retinal lesions in patients in rural areas warrants exploration., Objective: To explore the performance of a DLS for multiple retinal lesion screening using UWF fundus images from patients in rural areas., Design, Setting, and Participants: In this diagnostic study, a previously developed DLS based on UWF fundus images was used to screen for 5 retinal lesions (retinal exudates or drusen, glaucomatous optic neuropathy, retinal hemorrhage, lattice degeneration or retinal breaks, and retinal detachment) in 24 villages of Yangxi County, China, between November 17, 2020, and March 30, 2021., Interventions: The captured images were analyzed by the DLS and ophthalmologists., Main Outcomes and Measures: The performance of the DLS in rural screening was compared with that of the internal validation in the previous model development stage. The image quality, lesion proportion, and complexity of lesion composition were compared between the model development stage and the rural screening stage., Results: A total of 6222 eyes in 3149 participants (1685 women [53.5%]; mean [SD] age, 70.9 [9.1] years) were screened. The DLS achieved a mean (SD) area under the receiver operating characteristic curve (AUC) of 0.918 (0.021) (95% CI, 0.892-0.944) for detecting 5 retinal lesions in the entire data set when applied for patients in rural areas, which was lower than that reported at the model development stage (AUC, 0.998 [0.002] [95% CI, 0.995-1.000]; P < .001). Compared with the fundus images in the model development stage, the fundus images in this rural screening study had an increased frequency of poor quality (13.8% [860 of 6222] vs 0%), increased variation in lesion proportions (0.1% [6 of 6222]-36.5% [2271 of 6222] vs 14.0% [2793 of 19 891]-21.3% [3433 of 16 138]), and an increased complexity of lesion composition., Conclusions and Relevance: This diagnostic study suggests that the DLS exhibited excellent performance using UWF fundus images as a screening tool for 5 retinal lesions in patients in a rural setting. However, poor image quality, diverse lesion proportions, and a complex set of lesions may have reduced the performance of the DLS; these factors in targeted screening scenarios should be taken into consideration in the model development stage to ensure good performance.

Ischemic retinal diseases (IRDs) are a series of common blinding diseases that depend on accurate fundus fluorescein angiography (FFA) image interpretation for diagnosis and treatment. An artificial intelligence system (Ai-Doctor) was developed to interpret FFA images. Ai-Doctor performed well in image phase identification (area under the curve [AUC], 0.991-0.999, range), diabetic retinopathy (DR) and branch retinal vein occlusion (BRVO) diagnosis (AUC, 0.979-0.992), and non-perfusion area segmentation (Dice similarity coefficient [DSC], 89.7%-90.1%) and quantification. The segmentation model was expanded to unencountered IRDs (central RVO and retinal vasculitis), with DSCs of 89.2% and 83.6%, respectively. A clinically applicable ischemia index (CAII) was proposed to evaluate ischemic degree; patients with CAII values exceeding 0.17 in BRVO and 0.08 in DR may be associated with increased possibility for laser therapy. Ai-Doctor is expected to achieve accurate FFA image interpretation for IRDs, potentially reducing the reliance on retinal specialists., Competing Interests: Declaration of interests The authors declare no competing interests., (Copyright © 2023 The Author(s). Published by Elsevier Inc. All rights reserved.)

Image quality variation is a prominent cause of performance degradation for intelligent disease diagnostic models in clinical applications. Image quality issues are particularly prominent in infantile fundus photography due to poor patient cooperation, which poses a high risk of misdiagnosis. Here, we developed a deep learning-based image quality assessment and enhancement system (DeepQuality) for infantile fundus images to improve infant retinopathy screening. DeepQuality can accurately detect various quality defects concerning integrity, illumination, and clarity with area under the curve (AUC) values ranging from 0.933 to 0.995. It can also comprehensively score the overall quality of each fundus photograph. By analyzing 2,015,758 infantile fundus photographs from real-world settings using DeepQuality, we found that 58.3% of them had varying degrees of quality defects, and large variations were observed among different regions and categories of hospitals. Additionally, DeepQuality provides quality enhancement based on the results of quality assessment. After quality enhancement, the performance of retinopathy of prematurity (ROP) diagnosis of clinicians was significantly improved. Moreover, the integration of DeepQuality and AI diagnostic models can effectively improve the model performance for detecting ROP. This study may be an important reference for the future development of other image-based intelligent disease screening systems., (© 2023. Springer Nature Limited.)

Medical artificial intelligence (AI) has been moving from the research phase to clinical implementation. However, most AI-based models are mainly built using high-quality images preprocessed in the laboratory, which is not representative of real-world settings. This dataset bias proves a major driver of AI system dysfunction. Inspired by the design of flow cytometry, DeepFundus, a deep-learning-based fundus image classifier, is developed to provide automated and multidimensional image sorting to address this data quality gap. DeepFundus achieves areas under the receiver operating characteristic curves (AUCs) over 0.9 in image classification concerning overall quality, clinical quality factors, and structural quality analysis on both the internal test and national validation datasets. Additionally, DeepFundus can be integrated into both model development and clinical application of AI diagnostics to significantly enhance model performance for detecting multiple retinopathies. DeepFundus can be used to construct a data-driven paradigm for improving the entire life cycle of medical AI practice., Competing Interests: Declaration of interests The authors declare no competing interests., (Copyright © 2022 The Authors. Published by Elsevier Inc. All rights reserved.)

Early detection of visual impairment is crucial but is frequently missed in young children, who are capable of only limited cooperation with standard vision tests. Although certain features of visually impaired children, such as facial appearance and ocular movements, can assist ophthalmic practice, applying these features to real-world screening remains challenging. Here, we present a mobile health (mHealth) system, the smartphone-based Apollo Infant Sight (AIS), which identifies visually impaired children with any of 16 ophthalmic disorders by recording and analyzing their gazing behaviors and facial features under visual stimuli. Videos from 3,652 children (≤48 months in age; 54.5% boys) were prospectively collected to develop and validate this system. For detecting visual impairment, AIS achieved an area under the receiver operating curve (AUC) of 0.940 in an internal validation set and an AUC of 0.843 in an external validation set collected in multiple ophthalmology clinics across China. In a further test of AIS for at-home implementation by untrained parents or caregivers using their smartphones, the system was able to adapt to different testing conditions and achieved an AUC of 0.859. This mHealth system has the potential to be used by healthcare professionals, parents and caregivers for identifying young children with visual impairment across a wide range of ophthalmic disorders., (© 2023. The Author(s), under exclusive licence to Springer Nature America, Inc.)

The storage of facial images in medical records poses privacy risks due to the sensitive nature of the personal biometric information that can be extracted from such images. To minimize these risks, we developed a new technology, called the digital mask (DM), which is based on three-dimensional reconstruction and deep-learning algorithms to irreversibly erase identifiable features, while retaining disease-relevant features needed for diagnosis. In a prospective clinical study to evaluate the technology for diagnosis of ocular conditions, we found very high diagnostic consistency between the use of original and reconstructed facial videos (κ ≥ 0.845 for strabismus, ptosis and nystagmus, and κ = 0.801 for thyroid-associated orbitopathy) and comparable diagnostic accuracy (P ≥ 0.131 for all ocular conditions tested) was observed. Identity removal validation using multiple-choice questions showed that compared to image cropping, the DM could much more effectively remove identity attributes from facial images. We further confirmed the ability of the DM to evade recognition systems using artificial intelligence-powered re-identification algorithms. Moreover, use of the DM increased the willingness of patients with ocular conditions to provide their facial images as health information during medical treatment. These results indicate the potential of the DM algorithm to protect the privacy of patients' facial images in an era of rapid adoption of digital health technologies., (© 2022. The Author(s).)

The deletion of chromosome 11p13 involving the WT1 and PAX6 genes has been shown to cause WAGR syndrome (OMIM #194072), a rare genetic disorder that features Wilms' tumor, aniridia, genitourinary anomalies, as well as mental retardation. In this study, we expand the genotypic and phenotypic spectrum of WAGR syndrome by reporting on six patients from six unrelated families with different de novo deletions located on chromosome 11p13. Very rare phenotypes of lens automated absorption and lens thinning were detected in four of the six patients. We assessed the involvement of the ARL14EP gene in patients with and without severe lens abnormalities and found that its deletion may worsen the lens abnormalities in these patients.

Background: Retinal exudates and/or drusen (RED) can be signs of many fundus diseases that can lead to irreversible vision loss. Early detection and treatment of these diseases are critical for improving vision prognosis. However, manual RED screening on a large scale is time-consuming and labour-intensive. Here, we aim to develop and assess a deep learning system for automated detection of RED using ultra-widefield fundus (UWF) images., Methods: A total of 26,409 UWF images from 14,994 subjects were used to develop and evaluate the deep learning system. The Zhongshan Ophthalmic Center (ZOC) dataset was selected to compare the performance of the system to that of retina specialists in RED detection. The saliency map visualization technique was used to understand which areas in the UWF image had the most influence on our deep learning system when detecting RED., Results: The system for RED detection achieved areas under the receiver operating characteristic curve of 0.994 (95% confidence interval [CI]: 0.991-0.996), 0.972 (95% CI: 0.957-0.984), and 0.988 (95% CI: 0.983-0.992) in three independent datasets. The performance of the system in the ZOC dataset was comparable to that of an experienced retina specialist. Regions of RED were highlighted by saliency maps in UWF images., Conclusions: Our deep learning system is reliable in the automated detection of RED in UWF images. As a screening tool, our system may promote the early diagnosis and management of RED-related fundus diseases., (© 2021. The Author(s), under exclusive licence to The Royal College of Ophthalmologists.)

Delay in seeking medical services is common in elderly populations, which leads to disease progression and life difficulty. This study aims to assess the prevalence of delay in medical visits and treatment and define associated effects and factors in patients with senile cataract, which may help obtain a better understanding of late-life psychopathology and provide the basis for interventions. Patients aged more than 60 years were prospectively recruited in Zhongshan Ophthalmic Center (ZOC). All participants were diagnosed with binocular senile cataract and decided to have primary surgery in ZOC. The distributions of the popularity of delaying outpatient visits and treatment, the degrees of visual impairment, the influences on quality of life, and the reasons for delaying treatment among participants were accessed by the descriptive statistics. Factors associated with the perceptions of cataract treatment were accessed using a binary logistic regression model. A total of 400 senile patients aged from 60 to 94 years were enrolled. At diagnosis, 82 (20.5%) participants had a low vision with monocular acuity of both eyes below 0.05. All participants have felt that their normal lives were affected, and 64 (16%) participants felt that their lives were affected severely. Only 17 (4.25%) participants have sought for medical services immediately after feeling vision loss, and 294 (73.50%) participants have felt vision loss since a year ago before seeking medical help. A total of 298 (74.50%) participants have delayed the surgery time, and 229 (57.25%) patients delayed it for more than 12 months. There were 147 (36.75%) participants delaying surgery on account of no knowledge about it and 114 (28.50%) participants delaying surgery because of fear. There are a high proportion of elderly patients with senile cataract delaying their outpatient visits and surgery treatment, whose normal lives were severely affected. Increasing medical service propaganda about cataract and other common diseases in elderly populations would probably be helpful for improving perceptions of diseases and decreasing medical delays. Public needs to draw more attention to the healthy and medical status of the elderly ocular patients., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Xiang, Jiang, Zhao, Liu and Lin.)

Background/aims: To apply deep learning technology to develop an artificial intelligence (AI) system that can identify vision-threatening conditions in high myopia patients based on optical coherence tomography (OCT) macular images., Methods: In this cross-sectional, prospective study, a total of 5505 qualified OCT macular images obtained from 1048 high myopia patients admitted to Zhongshan Ophthalmic Centre (ZOC) from 2012 to 2017 were selected for the development of the AI system. The independent test dataset included 412 images obtained from 91 high myopia patients recruited at ZOC from January 2019 to May 2019. We adopted the InceptionResnetV2 architecture to train four independent convolutional neural network (CNN) models to identify the following four vision-threatening conditions in high myopia: retinoschisis, macular hole, retinal detachment and pathological myopic choroidal neovascularisation. Focal Loss was used to address class imbalance, and optimal operating thresholds were determined according to the Youden Index., Results: In the independent test dataset, the areas under the receiver operating characteristic curves were high for all conditions (0.961 to 0.999). Our AI system achieved sensitivities equal to or even better than those of retina specialists as well as high specificities (greater than 90%). Moreover, our AI system provided a transparent and interpretable diagnosis with heatmaps., Conclusions: We used OCT macular images for the development of CNN models to identify vision-threatening conditions in high myopia patients. Our models achieved reliable sensitivities and high specificities, comparable to those of retina specialists and may be applied for large-scale high myopia screening and patient follow-up., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Purpose: To predict central serous chorioretinopathy (CSC) recurrence 3 and 6 months after laser treatment by using machine learning. Methods: Clinical and imaging features of 461 patients (480 eyes) with CSC were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The ZOC data (416 eyes of 401 patients) were used as the training dataset and the internal test dataset, while the XEC data (64 eyes of 60 patients) were used as the external test dataset. Six different machine learning algorithms and an ensemble model were trained to predict recurrence in patients with CSC. After completing the initial detailed investigation, we designed a simplified model using only clinical data and OCT features. Results: The ensemble model exhibited the best performance among the six algorithms, with accuracies of 0.941 (internal test dataset) and 0.970 (external test dataset) at 3 months and 0.903 (internal test dataset) and 1.000 (external test dataset) at 6 months. The simplified model showed a comparable level of predictive power. Conclusion: Machine learning achieves high accuracies in predicting the recurrence of CSC patients. The application of an intelligent recurrence prediction model for patients with CSC can potentially facilitate recurrence factor identification and precise individualized interventions., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Xu, Wan, Zhao, You, Xiang, Zhou, Li, Gong, Zhu, Chen, Li, Zhang, Guo, Li, Gong, Zhang, Lai, Huang, Zhao, Ting, Jin and Lin.)

To predict visual acuity (VA) and post-therapeutic optical coherence tomography (OCT) images 1, 3, and 6 months after laser treatment in patients with central serous chorioretinopathy (CSC) by artificial intelligence (AI). Real-world clinical and imaging data were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The data obtained from ZOC (416 eyes of 401 patients) were used as the training set; the data obtained from XEC (64 eyes of 60 patients) were used as the test set. Six different machine learning algorithms and a blending algorithm were used to predict VA, and a pix2pixHD method was adopted to predict post-therapeutic OCT images in patients after laser treatment. The data for VA predictions included clinical features obtained from electronic medical records (20 features) and measured features obtained from fundus fluorescein angiography, indocyanine green angiography, and OCT (145 features). The data for OCT predictions included 480 pairs of pre- and post-therapeutic OCT images. The VA and OCT images predicted by AI were compared with the ground truth. In the VA predictions of XEC dataset, the mean absolute errors (MAEs) were 0.074-0.098 logMAR (within four to five letters), and the root mean square errors were 0.096-0.127 logMAR (within five to seven letters) for the 1-, 3-, and 6-month predictions, respectively; in the post-therapeutic OCT predictions, only about 5.15% (5 of 97) of synthetic OCT images could be accurately identified as synthetic images. The MAEs of central macular thickness of synthetic OCT images were 30.15 ± 13.28 μm and 22.46 ± 9.71 μm for the 1- and 3-month predictions, respectively. This is the first study to apply AI to predict VA and post-therapeutic OCT of patients with CSC. This work establishes a reliable method of predicting prognosis 6 months in advance; the application of AI has the potential to help reduce patient anxiety and serve as a reference for ophthalmologists when choosing optimal laser treatments., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Xu, Wan, Zhao, Liu, Hong, Xiang, You, Zhou, Li, Gong, Zhu, Chen, Zhang, Gong, Li, Li, Zhang, Guo, Lai, Huang, Ting, Lin and Jin.)

Background/aims: To develop a deep learning system for automated glaucomatous optic neuropathy (GON) detection using ultra-widefield fundus (UWF) images., Methods: We trained, validated and externally evaluated a deep learning system for GON detection based on 22 972 UWF images from 10 590 subjects that were collected at 4 different institutions in China and Japan. The InceptionResNetV2 neural network architecture was used to develop the system. The area under the receiver operating characteristic curve (AUC), sensitivity and specificity were used to assess the performance of detecting GON by the system. The data set from the Zhongshan Ophthalmic Center (ZOC) was selected to compare the performance of the system to that of ophthalmologists who mainly conducted UWF image analysis in clinics., Results: The system for GON detection achieved AUCs of 0.983-0.999 with sensitivities of 97.5-98.2% and specificities of 94.3-98.4% in four independent data sets. The most common reasons for false-negative results were confounding optic disc characteristics caused by high myopia or pathological myopia (n=39 (53%)). The leading cause for false-positive results was having other fundus lesions (n=401 (96%)). The performance of the system in the ZOC data set was comparable to that of an experienced ophthalmologist (p>0.05)., Conclusion: Our deep learning system can accurately detect GON from UWF images in an automated fashion. It may be used as a screening tool to improve the accessibility of screening and promote the early diagnosis and management of glaucoma., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2021. No commercial re-use. See rights and permissions. Published by BMJ.)

Background: Medical artificial intelligence (AI) has entered the clinical implementation phase, although real-world performance of deep-learning systems (DLSs) for screening fundus disease remains unsatisfactory. Our study aimed to train a clinically applicable DLS for fundus diseases using data derived from the real world, and externally test the model using fundus photographs collected prospectively from the settings in which the model would most likely be adopted., Methods: In this national real-world evidence study, we trained a DLS, the Comprehensive AI Retinal Expert (CARE) system, to identify the 14 most common retinal abnormalities using 207 228 colour fundus photographs derived from 16 clinical settings with different disease distributions. CARE was internally validated using 21 867 photographs and externally tested using 18 136 photographs prospectively collected from 35 real-world settings across China where CARE might be adopted, including eight tertiary hospitals, six community hospitals, and 21 physical examination centres. The performance of CARE was further compared with that of 16 ophthalmologists and tested using datasets with non-Chinese ethnicities and previously unused camera types. This study was registered with ClinicalTrials.gov, NCT04213430, and is currently closed., Findings: The area under the receiver operating characteristic curve (AUC) in the internal validation set was 0·955 (SD 0·046). AUC values in the external test set were 0·965 (0·035) in tertiary hospitals, 0·983 (0·031) in community hospitals, and 0·953 (0·042) in physical examination centres. The performance of CARE was similar to that of ophthalmologists. Large variations in sensitivity were observed among the ophthalmologists in different regions and with varying experience. The system retained strong identification performance when tested using the non-Chinese dataset (AUC 0·960, 95% CI 0·957-0·964 in referable diabetic retinopathy)., Interpretation: Our DLS (CARE) showed satisfactory performance for screening multiple retinal abnormalities in real-world settings using prospectively collected fundus photographs, and so could allow the system to be implemented and adopted for clinical care., Funding: This study was funded by the National Key R&D Programme of China, the Science and Technology Planning Projects of Guangdong Province, the National Natural Science Foundation of China, the Natural Science Foundation of Guangdong Province, and the Fundamental Research Funds for the Central Universities., Translation: For the Chinese translation of the abstract see Supplementary Materials section., Competing Interests: Declaration of interests JX and XZ report a valid patent (application number CN108596895A; for an eye-fundus image-detection method and device based on machine learning as well as system), which is used for the class 3 medical device of the Chinese National Medical Products Administration (registration number 20203210686; fundus-photography auxiliary-diagnosis software for diabetic retinopathy). All other authors declare no competing interests., (Copyright © 2021 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.)

Aims: To compare macular structure and vasculature between neuromyelitis optica spectrum disorder (NMOSD) and primary open angle glaucoma (POAG) using optical coherence tomography angiography., Methods: NMOSD patients (n=124) with/without a history of optic neuritis (ON) (NMO+ON: 113 eyes; NMO-ON: 95 eyes), glaucomatous patients (n=102) with early/advanced glaucoma (G-E: 74 eyes; G-A: 50 eyes) and healthy controls (n=62; 90 eyes) were imaged. The main outcome measures were macular ganglion cell-inner plexiform layer (GC-IPL) thickness, vessel density (VD) and perfusion density (PD) in the superficial capillary plexus, and diagnostic capabilities of the parameters as calculated by area under the curve (AUC)., Results: Significant losses in GC-IPL, VD and PD were detected in both patients with NMOSD and POAG. With matched losses in the peripapillary retinal nerve fibre layer, NMOSD group showed significant thinning of GC-IPL in the nasal-superior quadrant, whereas in POAG group, significant thinning was observed in the inferior and temporal-inferior quadrants. GC-IPL thinning was more prominent in the superior, nasal-superior and nasal-inferior quadrants in NMO+ON eyes. In G-A eyes, significant GC-IPL thinning was seen in the temporal-inferior quadrant. The specific structural parameters combining VD and foveal avascular zone (FAZ) indices showed the best diagnostic accuracies. The FAZ area in eyes with NMOSD was significantly smaller than the eyes of healthy controls and POAG., Conclusion: NMOSD and POAG have specific patterns of macular structural and vascular changes associated with pathophysiology. Our results indicate that FAZ could be a sensitive biomarker of macular changes in NMOSD., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Background: Human immunodeficiency virus (HIV) infection has become a chronic disease and attracted public attention globally. Population migration was considered hindering the control and management of HIV infection, but limited studies have explored how population mobility could influence the development of HIV-related complications and overall prognosis., Methods: We enrolled hospitalized HIV patients in this cross-sectional study between January 1, 2006, and December 31, 2016. We extracted demographic, hospitalization, and patient diagnosis data. Patients were divided into three groups according to the population type: (I) resident of Guangzhou City (local resident); (II) migrant outside of Guangzhou City but within Guangdong Province (migrant within the province); and (III) migrant outside of Guangdong Province (migrant outside the province). To represent the prognosis of HIV, in-hospital death was defined as the worst outcome, whereas vision-related events were considered moderate-to-severe complications. Logistic regression models were used to analyze factors influencing the prognosis of HIV., Results: Eight thousand and six hundred thirty-one inpatients (14,954 cases) were enrolled. The overall mortality was 7.9%, decreasing from 21.5% in 2006 to 3.8% in 2016. The prevalence of vision-related events was 14.4% between 2015 and 2016. Compared to local patients, migrant patients (within and outside the province) were younger, had significantly less access to health insurance, fewer hospitalization admissions, longer hospital stays, and a higher proportion of physical work (P<0.01). Furthermore, they had a higher prevalence of vision-related events (16.2% and 17.4% in migrant patients within the province and outside the province, respectively vs. 9.5%) and infectious diseases, but lower in-hospital mortality (5.9% and 7.0% vs. 12.3%) than local patients. Migrants correlated negatively with in-hospital death [odds ratio (OR) 95% CI, 0.37 (0.29-0.48) and 0.52 (0.40-0.68)] but correlated positively with vision-related events [OR (95% CI), 2.08 (1.54-2.80) and 2.03 (1.47-2.80)]., Conclusions: Migrant patients have significantly poorer access to health insurance, with an increased risk of developing moderate-to-severe HIV infection but a decreased risk of in-hospital death, indicating a trend toward withdrawing treatment in migrant patients when they have advanced diseases. Managements such as optimizing access to health insurance and improving follow-up visits for HIV infection should be considered in the context of the population mobility of HIV patients., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/atm-20-4514). The authors have no conflicts of interest to declare., (2021 Annals of Translational Medicine. All rights reserved.)

Purpose: To investigate environmental factors associated with corneal morphologic changes., Methods: A cross-sectional study was conducted, which enrolled adults of the Han ethnicity aged 18 to 44 years from 20 cities. The cornea-related morphology was measured using an ocular anterior segment analysis system. The geographic indexes of each city and meteorological indexes of daily city-level data from the past 40 years (1980-2019) were obtained. Correlation analyses at the city level and multilevel model analyses at the eye level were performed., Results: In total, 114,067 eyes were used for analysis. In the correlation analyses at the city level, the corneal thickness was positively correlated with the mean values of precipitation (highest r [correlation coefficient]: >0.700), temperature, and relative humidity (RH), as well as the amount of annual variation in precipitation (r: 0.548 to 0.721), and negatively correlated with the mean daily difference in the temperature (DIF T), duration of sunshine, and variance in RH (r: -0.694 to 0.495). In contrast, the anterior chamber (AC) volume was negatively correlated with the mean values of precipitation, temperature, RH, and the amount of annual variation in precipitation (r: -0.672 to -0.448), and positively associated with the mean DIF T (r = 0.570) and variance in temperature (r = 0.507). In total 19,988 eyes were analyzed at the eye level. After adjusting for age, precipitation was the major explanatory factor among the environmental factors for the variability in corneal thickness and AC volume., Conclusions: Individuals who were raised in warm and wet environments had thicker corneas and smaller AC volumes than those from cold and dry ambient environments. Our findings demonstrate the role of local environmental factors in corneal-related morphology.

Background: The high prevalence of ocular manifestations (OMs) in patients with human immunodeficiency virus (HIV) infection and chronic diseases such as diabetes has become a global health issue. However, there is still a lack of an appropriate ophthalmic diagnostic procedure for the early detection of OMs in this population, leading to the risk of an irreversible visual impairment that substantially affects the quality of life of these patients., Methods: The Guangzhou HIV Infection Study was a retrospective study that enrolled hospitalised HIV-infected patients in Guangzhou between January 2005 and December 2016, period corresponding to the highly active antiretroviral therapy (HAART) era in China. We collected data on OMs, systemic diseases, hospitalisation, and demographic characteristics. We classified the patients into 3 groups according to the ophthalmic examination mode they underwent: the non-ophthalmologist examination group (patients hospitalised in 2005-2011 who were only treated by infectious disease physicians), the on-demand ophthalmic examination group (patients hospitalised in 2012-2013 who were referred for a consultation with an ophthalmologist), and the routine ophthalmic examination group (patients hospitalised in 2014-2016 who routinely underwent standard ophthalmic examinations). Binary logistic regression models were used to investigate the factors related to OMs., Findings: A total of 8,743 hospitalised HIV-infected patients were enrolled. The prevalence of detected OMs were 1.5% in the non-ophthalmologist examination group, 1.9% in the on-demand ophthalmic examination group, and 12.8% in the routine ophthalmic examination group. The odds of detection of OMs were highest in the routine ophthalmic examination group (adjusted odds ratio [aOR]=9.24, [95%CI, 6.51-13.12], compared to the non-ophthalmologist examination group). The detection of all types of OMs increased substantially, with keratitis, retinitis and vascular abnormalities increased the most (by 15.8-20.0 times). In the routine examination group, patients who were older than 50 years, males, with medical insurance, and were not resident in Guangzhou, had higher odds to have OMs. Several systemic diseases also increased the odds of OMs, with the highest odds among patients with a cytomegalovirus infection (aOR=5.59, [95%CI, 4.12-7.59]). Patients with retinitis, retinopathy and conjunctivitis had higher odds of having a CD4 + T cell counts less than 200 cells/μL compared to the patients that did not have these referred OMs., Interpretation: The implementation of a routine ophthalmic examination has improved the odds of OM detection by approximately 9 times and increased the diagnosis rates of all types of OMs. Therefore, we encourage all HIV-infected patients to undergo regular ophthalmic examinations. Patients with OMs, especially retinopathy and retinitis, need to be evaluated for immune function (such as CD4 + T cell counts) and systemic diseases., Competing Interests: The authors declare no competing financial interests., (© 2020 The Author(s).)

Background: Although influencing the severity of postoperative intraocular inflammation of congenital cataract, the developmental characteristics of cytokine profile in the aqueous humor during childhood had not been described. And its relationship with the inflammatory response after intraocular surgery remained unsolved., Methods: Preoperative aqueous humor samples were collected from 65 eyes of congenital cataract patients (CC group) and 13 eyes of age-related cataract patients (ARC group) from January 2015 to May 2017. The concentrations of 22 cytokines were measured. Differences in concentrations between the CC and ARC groups were described. Correlation analysis, least absolute shrinkage and selection operator (LASSO) and multivariate linear regression were then used to investigate the dynamic changes in the cytokine profile with age and their relationships with the postoperative inflammatory response., Results: The concentrations of granulocyte colony stimulating factor (G-CSF), interferon (IFN)-α2, interleukin (IL)-1α and IL-7 were higher in the CC group than in the ARC group, while the concentrations of epidermal growth factor (EGF), granulocyte-macrophage colony stimulating factor (GM-CSF), IL-10, IL-12p70, IL-2, IL-3, IL-4, IL-5, IL-6, IL-8, and tumor necrosis factor (TNF)-α were more abundant in the ARC group (P<0.05). Within the CC group, the concentrations of EGF and IL-3 were positively correlated with age, while negative correlations were observed for monocyte chemotactic protein-1 (MCP-1) and IL-8 (P<0.05). Further multivariate analysis revealed that age was an independent associated factor of MCP-1 (β=-0.337, P<0.001). IL-3 (β=-0.490, P=0.006) and EGF (β=-0.415, P=0.044) were significantly correlated with the postoperative inflammatory response [evaluation of posterior capsule opacification (EPCO)] at 3 and 12 months after surgery, respectively., Conclusions: This study demonstrated the dynamic change in the cytokine profile of the aqueous humor in children and its relationship with the postoperative inflammatory response. These findings can serve as the foundation for further investigation into the mechanisms that underlie the early development of intraocular immunology., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/atm-19-2377). The series “Recent developments in cataract surgery” was commissioned by the editorial office without any funding or sponsorship. The authors report grants from National Key R&D Program of China, grants from National Natural Science Foundation of China, grants from the Science and Technology Planning Projects of Guangdong Province, during the conduct of the study. The authors have no other conflicts of interest to declare., (2020 Annals of Translational Medicine. All rights reserved.)

Artificial intelligence (AI) based on deep learning has shown excellent diagnostic performance in detecting various diseases with good-quality clinical images. Recently, AI diagnostic systems developed from ultra-widefield fundus (UWF) images have become popular standard-of-care tools in screening for ocular fundus diseases. However, in real-world settings, these systems must base their diagnoses on images with uncontrolled quality ("passive feeding"), leading to uncertainty about their performance. Here, using 40,562 UWF images, we develop a deep learning-based image filtering system (DLIFS) for detecting and filtering out poor-quality images in an automated fashion such that only good-quality images are transferred to the subsequent AI diagnostic system ("selective eating"). In three independent datasets from different clinical institutions, the DLIFS performed well with sensitivities of 96.9%, 95.6% and 96.6%, and specificities of 96.6%, 97.9% and 98.8%, respectively. Furthermore, we show that the application of our DLIFS significantly improves the performance of established AI diagnostic systems in real-world settings. Our work demonstrates that "selective eating" of real-world data is necessary and needs to be considered in the development of image-based AI systems., Competing Interests: Competing interestsThe authors declare no competing interests., (© The Author(s) 2020.)

Cerebrovascular disease (CeVD) is one of the leading global causes of death and severe disability. To date, retinal microangiopathy has become a reflection of cerebral microangiopathy, mirroring the vascular pathological modifications in vivo . To evaluate the retinal structure and microvasculature in patients with CeVD, we conducted a cross-sectional study in Zhongshan Ophthalmic Center and Department of Neurology of Third Affiliated Hospital, Sun Yat-sen University using optical coherence tomography angiography (OCTA). CeVD patients ( n = 121; 238 eyes) and healthy controls ( n = 44; 57 eyes) were included in the analysis. The CeVD group showed significant thinning of the peripapillary retinal nerve fiber layer (pRNFL) thickness in the temporal and nasal quadrants, and thinning of the macular ganglion cell-inner plexiform layer (GC-IPL) in the inferior quadrant, while macular microvasculature reduction was prominent in all nine quadrants. There were significant correlations between OCTA parameters, visual acuity, and transcranial doppler parameters in the CeVD group. The specific structural parameters combining microvasculature indices showed the best diagnostic accuracies (AUC = 0.918) to discriminate CeVD group from healthy controls. To conclude, we proved that OCTA reveals specific patterns of retinal structural changes and extensive macular microvascular changes in CeVD. Additionally, these retinal abnormalities could prove useful disease biomarkers in the management of individuals at high risk of debilitating complications from a cerebrovascular event., (Copyright © 2020 Zhang, Xiao, Liu, Liu, Zhao, Wang, Wang, Wang, Zhu, Chen, Wu, Lin, Qiu, Yu-Wai-Man, Lu and Lin.)

A challenge of chronic diseases that remains to be solved is how to liberate patients and medical resources from the burdens of long-term monitoring and periodic visits. Precise management based on artificial intelligence (AI) holds great promise; however, a clinical application that fully integrates prediction and telehealth computing has not been achieved, and further efforts are required to validate its real-world benefits. Taking congenital cataract as a representative, we used Bayesian and deep-learning algorithms to create CC-Guardian, an AI agent that incorporates individualized prediction and scheduling, and intelligent telehealth follow-up computing. Our agent exhibits high sensitivity and specificity in both internal and multi-resource validation. We integrate our agent with a web-based smartphone app and prototype a prediction-telehealth cloud platform to support our intelligent follow-up system. We then conduct a retrospective self-controlled test validating that our system not only accurately detects and addresses complications at earlier stages, but also reduces the socioeconomic burdens compared to conventional methods. This study represents a pioneering step in applying AI to achieve real medical benefits and demonstrates a novel strategy for the effective management of chronic diseases., Competing Interests: Competing interestsThe authors declare no competing interests., (© The Author(s) 2020.)

Artificial intelligence (AI) based on machine learning (ML) and deep learning (DL) techniques has gained tremendous global interest in this era. Recent studies have demonstrated the potential of AI systems to provide improved capability in various tasks, especially in image recognition field. As an image-centric subspecialty, ophthalmology has become one of the frontiers of AI research. Trained on optical coherence tomography, slit-lamp images and even ordinary eye images, AI can achieve robust performance in the detection of glaucoma, corneal arcus and cataracts. Moreover, AI models based on other forms of data also performed satisfactorily. Nevertheless, several challenges with AI application in ophthalmology have also arisen, including standardization of data sets, validation and applicability of AI models, and ethical issues. In this review, we provided a summary of the state-of-the-art AI application in anterior segment ophthalmic diseases, potential challenges in clinical implementation and our prospects., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/atm-20-976). The series “Medical Artificial Intelligent Research” was commissioned by the editorial office without any funding or sponsorship. HL served as the unpaid Guest Editor of the series. The other authors have no other conflicts of interest to declare., (2020 Annals of Translational Medicine. All rights reserved.)

Background: Myopia is the leading cause of visual impairment and affects millions of children worldwide. Timely and annual manual optometric screenings of the entire at-risk population improve outcomes, but screening is challenging due to the lack of availability and training of assessors and the economic burden imposed by the screenings. Recently, deep learning and computer vision have shown powerful potential for disease screening. However, these techniques have not been applied to large-scale myopia screening using ocular appearance images., Methods: We trained a deep learning system (DLS) for myopia detection using 2,350 ocular appearance images (processed by 7,050 pictures) from children aged 6 to 18. Myopia is defined as a spherical equivalent refraction (SER) [the algebraic sum in diopters (D), sphere + 1/2 cylinder] ≤-0.5 diopters. Saliency maps and gradient class activation maps (grad-CAM) were used to highlight the regions recognized by VGG-Face. In a prospective clinical trial, 100 ocular appearance images were used to assess the performance of the DLS., Results: The area under the curve (AUC), sensitivity, and specificity of the DLS were 0.9270 (95% CI, 0.8580-0.9610), 81.13% (95% CI, 76.86-5.39%), and 86.42% (95% CI, 82.30-90.54%), respectively. Based on the saliency maps and grad-CAMs, the DLS mainly focused on eyes, especially the temporal sclera, rather than the background or other parts of the face. In the prospective clinical trial, the DLS achieved better diagnostic performance than the ophthalmologists in terms of sensitivity [DLS: 84.00% (95% CI, 73.50-94.50%) versus ophthalmologists: 64.00% (95% CI, 48.00-72.00%)] and specificity [DLS: 74.00% (95% CI, 61.40-86.60%) versus ophthalmologists: 53.33% (95% CI, 30.00-66.00%)]. We also computed AUC subgroups stratified by sex and age. DLS achieved comparable AUCs for children of different sexes and ages., Conclusions: This study for the first time applied deep learning to myopia screening using ocular images and achieved high screening accuracy, enabling the remote monitoring of the refractive status in children with myopia. The application of our DLS will directly benefit public health and relieve the substantial burden imposed by myopia-associated visual impairment or blindness., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/atm.2019.12.39). The series “Medical Artificial Intelligent Research” was commissioned by the editorial office without any funding or sponsorship. HL served as the unpaid Guest Editor of the series. The other authors have no other conflicts of interest to declare., (2020 Annals of Translational Medicine. All rights reserved.)

Background: To investigate the attitude and formal suggestions on talent cultivation in the field of medical artificial intelligence (AI)., Methods: An electronic questionnaire was sent to both medical-related field or non-medical field population using the WenJuanXing web-application via social media. The questionnaire was designed to collect: (I) demographic information; (II) perception of medical AI; (III) willingness to participate in the medical AI related teaching activities; (IV) teaching content of medical AI; (V) the role of medical AI teaching; (VI) future career planning. Respondents' anonymity was ensured., Results: A total of 710 respondents provided valid answers to the questionnaire (57.75% medical related, 42.25% non-medical). About 73.8% of respondents acquired related information from network and social platform. More than half the respondents had basic perception of AI applicational scenarios and specialties in medicine, meanwhile were willing to participate in related general science activities (conference and lectures). Respondents from medical healthcare related fields, with high academic qualifications of male ones demonstrated showed significant better understanding and stronger willingness (P<0.05). The majority agreed medical AI courses should be set as major elective (42.82%) during undergraduate stages (89.58%) involving medical and computer science contents. An overwhelming majority of respondents (>80%) acknowledged the potential roles of medical AI teaching. Surgeon, ophthalmologist, physicians and researchers are the top tier considerations for ideal career regardless of AI influence. Radiology and clinical laboratory subjects are more preferred considering the development of medical AI (P>0.05)., Conclusions: The potential role of medical AI talent cultivation is widely acknowledged by public. Medical related professions demonstrated higher level of perception and stronger willingness for medical AI educational events. Merging subjects as radiology and clinical laboratory subjects are preferred with broad talents demands and bright prospects., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/atm.2019.12.149). The series “Medical Artificial Intelligent Research” was commissioned by the editorial office without any funding or sponsorship. HL served as the unpaid Guest Editor of the series. The other authors have no other conflicts of interest to declare., (2020 Annals of Translational Medicine. All rights reserved.)

Importance: Evaluating corneal morphologic characteristics with corneal tomographic scans before refractive surgery is necessary to exclude patients with at-risk corneas and keratoconus. In previous studies, researchers performed screening with machine learning methods based on specific corneal parameters. To date, a deep learning algorithm has not been used in combination with corneal tomographic scans., Objective: To examine the use of a deep learning model in the screening of candidates for refractive surgery., Design, Setting, and Participants: A diagnostic, cross-sectional study was conducted at the Zhongshan Ophthalmic Center, Guangzhou, China, with examination dates extending from July 18, 2016, to March 29, 2019. The investigation was performed from July 2, 2018, to June 28, 2019. Participants included 1385 patients; 6465 corneal tomographic images were used to generate the artificial intelligence (AI) model. The Pentacam HR system was used for data collection., Interventions: The deidentified images were analyzed by ophthalmologists and the AI model., Main Outcomes and Measures: The performance of the AI classification system., Results: A classification system centered on the AI model Pentacam InceptionResNetV2 Screening System (PIRSS) was developed for screening potential candidates for refractive surgery. The model achieved an overall detection accuracy of 94.7% (95% CI, 93.3%-95.8%) on the validation data set. Moreover, on the independent test data set, the PIRSS model achieved an overall detection accuracy of 95% (95% CI, 88.8%-97.8%), which was comparable with that of senior ophthalmologists who are refractive surgeons (92.8%; 95% CI, 91.2%-94.4%) (P = .72). In distinguishing corneas with contraindications for refractive surgery, the PIRSS model performed better than the classifiers (95% vs 81%; P < .001) in the Pentacam HR system on an Asian patient database., Conclusions and Relevance: PIRSS appears to be useful in classifying images to provide corneal information and preliminarily identify at-risk corneas. PIRSS may provide guidance to refractive surgeons in screening candidates for refractive surgery as well as for generalized clinical application for Asian patients, but its use needs to be confirmed in other populations.

Objective: The aim of our research was to examine the impact of a patient education program for parents of children with congenital cataract on parental stress, comprehension of disease information and parental satisfaction., Methods: This prospective study included 177 parents of children with congenital cataract. The children were randomized into the following groups: the health education program with a multifaceted, interactive approach and conventional follow-up. Self-administered questionnaires were used for parental evaluation before and after the education program. The anxiety level, parental satisfaction and comprehension of the information were evaluated at each time point., Results: A multifaceted, interactive approach to education significantly reduced parental levels of anxiety compared with the conventional group (effect sizes: Parenting Stress Index, ƞ2 = 0.285; Ocular Treatment Index, ƞ2 = 0.346). This approach also improved comprehension-memorization scores (effect sizes: ƞ2 = 0.303) and parental satisfaction (p < 0.001). The impact of this new intervention was maintained for 6 and 12 months after the course., Conclusion: The interactive, multifaceted education approach could efficiently improve the comprehension of disease-related information and parental satisfaction, resulting in significantly decreased parental anxiety., Practice Implications: This new patient education approach had a significant impact on congenital cataracts and may be generalized to other pediatric diseases., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Purpose: To develop and evaluate a deep learning (DL) system for retinal hemorrhage (RH) screening using ultra-widefield fundus (UWF) images., Methods: A total of 16,827 UWF images from 11,339 individuals were used to develop the DL system. Three experienced retina specialists were recruited to grade UWF images independently. Three independent data sets from 3 different institutions were used to validate the effectiveness of the DL system. The data set from Zhongshan Ophthalmic Center (ZOC) was selected to compare the classification performance of the DL system and general ophthalmologists. A heatmap was generated to identify the most important area used by the DL model to classify RH and to discern whether the RH involved the anatomical macula., Results: In the three independent data sets, the DL model for detecting RH achieved areas under the curve of 0.997, 0.998, and 0.999, with sensitivities of 97.6%, 96.7%, and 98.9% and specificities of 98.0%, 98.7%, and 99.4%. In the ZOC data set, the sensitivity of the DL model was better than that of the general ophthalmologists, although the general ophthalmologists had slightly higher specificities. The heatmaps highlighted RH regions in all true-positive images, and the RH within the anatomical macula was determined based on heatmaps., Conclusions: Our DL system showed reliable performance for detecting RH and could be used to screen for RH-related diseases., Translational Relevance: As a screening tool, this automated system may aid early diagnosis and management of RH-related retinal and systemic diseases by allowing timely referral., Competing Interests: Disclosure: Zhongwen Li, None; Chong Guo, None; Danyao Nie, None; Duoru Lin, None; Yi Zhu, None; Chuan Chen, None; Yifan Xiang, None; Fabao Xu, None; Chenjin Jin, None; Xiayin Zhang, None; Yahan Yang, None; Kai Zhang, None; Lanqin Zhao, None; Ping Zhang, None; Yu Han, None; Dongyuan Yun, None; Xiaohang Wu, None; Pisong Yan, None; Haotian Lin, None, (Copyright 2020 The Authors.)

Retinal detachment can lead to severe visual loss if not treated timely. The early diagnosis of retinal detachment can improve the rate of successful reattachment and the visual results, especially before macular involvement. Manual retinal detachment screening is time-consuming and labour-intensive, which is difficult for large-scale clinical applications. In this study, we developed a cascaded deep learning system based on the ultra-widefield fundus images for automated retinal detachment detection and macula-on/off retinal detachment discerning. The performance of this system is reliable and comparable to an experienced ophthalmologist. In addition, this system can automatically provide guidance to patients regarding appropriate preoperative posturing to reduce retinal detachment progression and the urgency of retinal detachment repair. The implementation of this system on a global scale may drastically reduce the extent of vision impairment resulting from retinal detachment by providing timely identification and referral.

PRéCIS:: The overall incidence of postoperative suspected glaucoma and glaucoma after congenital cataract surgery is low; however, the identification of the associated risk factors helps to monitor susceptible individuals and to provide real-time surveillance and timely intervention., Purpose: Pediatric patients who have undergone surgery for congenital or infantile cataracts have a risk of developing suspected glaucoma and glaucoma, but the current evidence does not address our understanding of the incidence and associated risk factors of suspected glaucoma/glaucoma for application in clinical standard care. Therefore, this study investigated the incidence of and risk factors for suspected glaucoma/glaucoma in patients who have undergone surgery for congenital/infantile cataracts., Methods: This study used a prospective cohort of 241 eyes from 241 patients who were 10 years of age or younger and who had undergone congenital/infantile cataract surgeries and were recruited from January 2011 to December 2016 at the Zhongshan Ophthalmic Center. Pediatric patients who underwent cataract surgery were classified into 2 groups according to intraocular lens (IOL) implantation. The patients' baseline characteristics and the incidence and risk factors for suspected glaucoma/glaucoma were assessed., Results: The incidence of suspected glaucoma after cataract surgery was 10.70% [26 of 241 eyes; 95% confidence interval (CI), 6.88%-14.70%]. The rate of suspected glaucoma developing into glaucoma was 26.92% (7 of 26 eyes; 95% CI, 9.87%-43.97%), and the incidence of glaucoma was 2.90% (7 of 241 eyes; 95% CI, 0.79%-5.03%). Our study revealed that the incidence of suspected glaucoma/glaucoma in patients who did not receive IOL implantation was 13.91% (21 of 151 eyes; 95% CI, 8.39%-19.42%), and the incidence in patients who received IOL implantation was 5.56% (5 of 90 eyes; 95% CI, 8.23%-10.28%). The preoperative central corneal thickness (hazard ratio, 1.003; 95% CI, 1.001 to 1.004; P=0.004) and a family history of congenital cataracts (hazard ratio, 2.314; 95% CI, 1.004-5.331; P=0.049) were significant risk factors in patients without IOL implantation. Patient age at the time of cataract surgery was not a statistically significant risk factor for the development of suspected glaucoma/glaucoma in patients without IOL implantation., Conclusions: Identification of the incidence of and risk factors for suspected glaucoma/glaucoma may help clinicians monitor susceptible individuals and provide timely surveillance and interventions in a clinical setting. Age at the time of cataract surgery was not a risk factor for suspected glaucoma/glaucoma in patients without IOL implantation, and this may allow the timing window for pediatric cataract surgery to be expanded and support new insights into the optimal timing of surgery for standard care.

Background: Approximately 1 in 33 newborns is affected by congenital anomalies worldwide. We aimed to develop a practical model for identifying infants with a high risk of congenital cataracts (CCs), which is the leading cause of avoidable childhood blindness., Methods: This case-control study was performed in the Zhongshan Ophthalmic Center and involved 2005 subjects, including 1274 children with CCs and 731 healthy controls. The CC identification models were established based on birth conditions, family medical history, and family environmental factors using the random forest (RF) and adaptive boosting methods (trained by 1129 CC cases and 609 healthy controls), which were tested by internal 4-fold cross-validation and external validation (145 CC cases and 122 healthy controls). The models were also tested using 4 datasets with gradually reduced proportions of CC patients (bilateral cases) to validate their performance in an approximate simulation of a clinical environment with a relatively low disease prevalence., Findings: The CC identification models showed high discrimination in both the 4-fold cross validation (area under the curve (AUC)=0.91 [95% confidence interval: 0.88-0.94] in bilateral cases; 0.82 [0.77-0.89] in unilateral cases) and external validation (AUC=0.93±0.05 in bilateral cases; 0.86±0.01 in unilateral cases), and achieved stable performance in the clinical tests (AUC=0.94-0.96 in the four subgroups by RF). Furthermore, family history of CC, low parental education level, and comorbidity were identified as the top three most relevant factors to both bilateral and unilateral CC diagnosis., Interpretation: Our CC identification models can accurately discriminate CC patients from healthy children and have the potential to serve as a complementary screening procedure, especially in undeveloped and remote areas., Competing Interests: Declaration of Competing Interest The authors declare that they have no competing interests., (Copyright © 2019 The Authors. Published by Elsevier B.V. All rights reserved.)

The general public's attitudes, demands, and expectations regarding medical AI could provide guidance for the future development of medical AI to satisfy the increasing needs of doctors and patients. The objective of this study is to investigate public perceptions, receptivity, and demands regarding the implementation of medical AI. An online questionnaire was designed to investigate the perceptions, receptivity, and demands of general public regarding medical AI between October 13 and October 30, 2018. The distributions of the current achievements, public perceptions, receptivity, and demands among individuals in different lines of work (i.e., healthcare vs non-healthcare) and different age groups were assessed by performing descriptive statistics. The factors associated with public receptivity of medical AI were assessed using a linear regression model. In total, 2,780 participants from 22 provinces were enrolled. Healthcare workers accounted for 54.3 % of all participants. There was no significant difference between the healthcare workers and non-healthcare workers in the high proportion (99 %) of participants expressing acceptance of AI (p = 0.8568), but remarkable distributional differences were observed in demands (p < 0.001 for both demands for AI assistance and the desire for AI improvements) and perceptions (p < 0.001 for safety, validity, trust, and expectations). High levels of receptivity (approximately 100 %), demands (approximately 80 %), and expectations (100 %) were expressed among different age groups. The receptivity of medical AI among the non-healthcare workers was associated with gender, educational qualifications, and demands and perceptions of AI. There was a very large gap between current availability of and public demands for intelligence services (p < 0.001). More than 90 % of healthcare workers expressed a willingness to devote time to learning about AI and participating in AI research. The public exhibits a high level of receptivity regarding the implementation of medical AI. To date, the achievements have been rewarding, and further advancements are required to satisfy public demands. There is a strong demand for intelligent assistance in many medical areas, including imaging and pathology departments, outpatient services, and surgery. More contributions are imperative to facilitate integrated and advantageous implementation in medical AI., Competing Interests: Declaration of Competing Interest The authors declare no competing financial interests., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Background: Lattice degeneration and/or retinal breaks, defined as notable peripheral retinal lesions (NPRLs), are prone to evolving into rhegmatogenous retinal detachment which can cause severe visual loss. However, screening NPRLs is time-consuming and labor-intensive. Therefore, we aimed to develop and evaluate a deep learning (DL) system for automated identifying NPRLs based on ultra-widefield fundus (UWF) images., Methods: A total of 5,606 UWF images from 2,566 participants were used to train and verify a DL system. All images were classified by 3 experienced ophthalmologists. The reference standard was determined when an agreement was achieved among all 3 ophthalmologists, or adjudicated by another retinal specialist if disagreements existed. An independent test set of 750 images was applied to verify the performance of 12 DL models trained using 4 different DL algorithms (InceptionResNetV2, InceptionV3, ResNet50, and VGG16) with 3 preprocessing techniques (original, augmented, and histogram-equalized images). Heatmaps were generated to visualize the process of the best DL system in the identification of NPRLs., Results: In the test set, the best DL system for identifying NPRLs achieved an area under the curve (AUC) of 0.999 with a sensitivity and specificity of 98.7% and 99.2%, respectively. The best preprocessing method in each algorithm was the application of original image augmentation (average AUC =0.996). The best algorithm in each preprocessing method was InceptionResNetV2 (average AUC =0.996). In the test set, 150 of 154 true-positive cases (97.4%) displayed heatmap visualization in the NPRL regions., Conclusions: A DL system has high accuracy in identifying NPRLs based on UWF images. This system may help to prevent the development of rhegmatogenous retinal detachment by early detection of NPRLs., Competing Interests: Conflicts of Interest: The authors have no conflicts of interest to declare., (2019 Annals of Translational Medicine. All rights reserved.)

Competing Interests: The authors declare no competing financial interests.