Big Data in Ophthalmology

Research Trends and Hotspots of Big Data in Ophthalmology: A Bibliometric Analysis and Visualization

PURPOSE

The burst of modern information has significantly promoted the development of global medicine into a new era of big data healthcare. Ophthalmology is one of the most prominent medical specialties driven by big data analytics. This study aimed to describe the development status and research hotspots of big data in ophthalmology.

METHODS

English articles and reviews related to big data in ophthalmology published from January 1, 1999, to April 30, 2024, were retrieved from the Web of Science Core Collection. The relevant information was analyzed and visualized using VOSviewer and CiteSpace software.

RESULTS

A total of 406 qualified documents were included in the analysis. The annual number of publications on big data in ophthalmology reached a rapidly increasing stage since 2019. The United States (n = 147) led in the number of publications, followed by India (n = 77) and China (n = 69). The L.V. Prasad Eye Institute in India was the most productive institution (n = 50), and Anthony Vipin Das was the most influential author with the most relevant literature (n = 45). The electronic medical records were the primary source of ophthalmic big data, and artificial intelligence served as the principal analytics tool. Diabetic retinopathy, glaucoma, and myopia are currently the main topics of interest in this field.

CONCLUSIONS

The application of big data in ophthalmology has experienced rapid growth in recent years. Big data is expected to play an increasingly significant role in shaping the future of research and clinical practice in ophthalmology.

The Oregis Dashboard: Web-based Ophthalmic Research Benchmarking in Germany

INTRODUCTION

The oregis registry operated by the German Ophthalmological Society (DOG) serves as a central digital platform for collecting and analysing ophthalmological healthcare data in Germany. The aim of oregis is to provide a comprehensive picture of the current healthcare situation and promote healthcare research using real-world-data from inpatient and outpatient facilities. Since its launch in 2020, oregis has continuously expanded its database to enable scientific analyses on a wide range of topics. This paper presents the new dashboard feature allowing participating centres to compare their own patient data with aggregated data in real time while also covering privacy aspects of the system.

MATERIALS AND METHODS

The oregis steering committee opted to implement the oregis dashboard based on existing medical registries. First, forty-nine national and international registries were analysed to identify common features such as benchmarking functionality. This was followed by technical realisation and implementation.

RESULTS

Each centre connected to oregis has secure access to the oregis dashboard, which displays key indicators for patients, diagnoses, and treatments. Dynamic filtering options allow targeted data analysis, comparing each centre's results anonymously with aggregated data from other centres. The dashboard uses Apache Superset data visualisation software [! etwas informativer]. Data is synchronised using an integrated oregis Konnektor module to anonymise patient data according to defined standards. Extensive security and privacy measures ensure data security, including server-side encryption, transport encryption, and two-factor authentication. The dashboard is part of a comprehensive privacy policy developed and validated for oregis by privacy experts.

CONCLUSION

The number of centres connected to oregis is still growing. The new web-based dashboard allows flexible analysis of data and comparison with other centres without allowing conclusions to be drawn about any individual care centre; this ensures data privacy and independence in each centre. More features can be added to provide a more thorough overview of eye care in Germany as oregis grows.

Efficiency and safety of automated label cleaning on multimodal retinal images

Label noise is a common and important issue that would affect the model's performance in artificial intelligence. This study assessed the effectiveness and potential risks of automated label cleaning using an open-source framework, Cleanlab, in multi-category datasets of fundus photography and optical coherence tomography, with intentionally introduced label noise ranging from 0 to 70%. After six cycles of automatic cleaning, significant improvements are achieved in label accuracies (3.4-62.9%) and dataset quality scores (DQS, 5.1-74.4%). The majority (86.6 to 97.5%) of label errors were accurately modified, with minimal missed (0.5-2.8%) or misclassified (0.4-10.6%). The classification accuracy of RETFound significantly improved by 0.3-52.9% when trained with the datasets after cleaning. We also developed a DQS-guided cleaning strategy to mitigate over-cleaning. Furthermore, external validation on EyePACS and APTOS-2019 datasets boosted label accuracy by 1.3 and 1.8%, respectively. This approach automates label correction, enhances dataset reliability, and strengthens model performance efficiently and safely.

Detection of Disease Features on Retinal OCT Scans Using RETFound

Eye diseases such as age-related macular degeneration (AMD) are major causes of irreversible vision loss. Early and accurate detection of these diseases is essential for effective management. Optical coherence tomography (OCT) imaging provides clinicians with in vivo, cross-sectional views of the retina, enabling the identification of key pathological features. However, manual interpretation of OCT scans is labor-intensive and prone to variability, often leading to diagnostic inconsistencies. To address this, we leveraged the RETFound model, a foundation model pretrained on 1.6 million unlabeled retinal OCT images, to automate the classification of key disease signatures on OCT. We finetuned RETFound and compared its performance with the widely used ResNet-50 model, using single-task and multitask modes. The dataset included 1770 labeled B-scans with various disease features, including subretinal fluid (SRF), intraretinal fluid (IRF), drusen, and pigment epithelial detachment (PED). The performance was evaluated using accuracy and AUC-ROC values, which ranged across models from 0.75 to 0.77 and 0.75 to 0.80, respectively. RETFound models display comparable specificity and sensitivity to ResNet-50 models overall, making it also a promising tool for retinal disease diagnosis. These findings suggest that RETFound may offer improved diagnostic accuracy and interpretability for specific tasks, potentially aiding clinicians in more efficient and reliable OCT image analysis.

Evaluation of Sociomedical Factors on Corneal Donor Recovery Using Machine Learning

PURPOSE

To evaluate co-morbid sociomedical conditions affecting corneal donor endothelial cell density and transplant suitability.

METHOD(S)

Corneal donor transplant information was collected from the CorneaGen eye bank between June 1, 2012 and June 30, 2016. A natural language processing algorithm was applied to generate co-morbid sociomedical conditions for each donor. Variables of importance were identified using four machine learning models (random forest, Glmnet, Earth, nnet), for the outcomes of transplant suitability and endothelial cell density. SHAP (SHapley Additive exPlanations) values were generated, with beeswarm and box plots to visualize the contribution of each feature to the models.

RESULTS

With a total of 23,522 unique donors, natural language processing generated 30,573 indices, which were reduced to 41 most common co-morbid sociomedical conditions. For transplant suitability, hypertension ranked the top overall variable of importance in two models. Hypertension, chronic obstructive pulmonary disease, history of smoking, and alcohol use appeared consistently in the top variables of importance. By SHAP feature importance, hypertension (0.042), alcohol use (0.017), ventilation of donor (0.011), and history of smoking (0.010) contributed the most to the transplant suitability model. For endothelial cell density, hypertension was the sociomedical condition of highest importance in three models. SHAP scores were highest among the sociomedical conditions of hypertension (0.037), alcohol use (0.013), myocardial infarction (0.012), and history of smoking (0.011).

CONCLUSION

In a large cohort of corneal donor eyes, hypertension was identified as the most common contributor to machine learning models examining sociomedical conditions for corneal donor transplant suitability and endothelial cell density.

Big data to guide glaucoma treatment

Ophthalmology has been at the forefront of the medical application of big data. Often harnessed with a machine learning approach, big data has demonstrated potential to transform ophthalmic care, as evidenced by prior success on clinical tasks such as the screening of ophthalmic diseases and lesions via retinal images. With the recent establishment of various large ophthalmic datasets, there has been greater interest in determining whether the benefits of big data may extend to the downstream process of ophthalmic disease management. An area of substantial investigation has been the use of big data to help guide or streamline management of glaucoma, which remains a leading cause of irreversible blindness worldwide. In this review, we summarize relevant studies utilizing big data and discuss the application of the findings in the risk assessment and treatment of glaucoma.

Big data in visual field testing for glaucoma

Recent technological advancements and the advent of ever-growing databases in health care have fueled the emergence of "big data" analytics. Big data has the potential to revolutionize health care, particularly ophthalmology, given the data-intensive nature of the medical specialty. As one of the leading causes of irreversible blindness worldwide, glaucoma is an ocular disease that receives significant interest for developing innovations in eye care. Among the most vital sources of data in glaucoma is visual field (VF) testing, which stands as a cornerstone for diagnosing and managing the disease. The expanding accessibility of large VF databases has led to a surge in studies investigating various applications of big data analytics in glaucoma. In this study, we review the use of big data for evaluating the reliability of VF tests, gaining insights into real-world clinical practices and outcomes, understanding new disease associations and risk factors, characterizing the patterns of VF loss, defining the structure-function relationship of glaucoma, enhancing early diagnosis or earlier detection of progression, informing clinical decisions, and improving clinical trials. Equally important, we discuss current challenges in big data analytics and future directions for improvement.

Application of artificial intelligence in glaucoma care: An updated review

The application of artificial intelligence (AI) in ophthalmology has been increasingly explored in the past decade. Numerous studies have shown promising results supporting the utility of AI to improve the management of ophthalmic diseases, and glaucoma is of no exception. Glaucoma is an irreversible vision condition with insidious onset, complex pathophysiology, and chronic treatment. Since there remain various challenges in the clinical management of glaucoma, the potential role of AI in facilitating glaucoma care has garnered significant attention. In this study, we reviewed the relevant literature published in recent years that investigated the application of AI in glaucoma management. The main aspects of AI applications that will be discussed include glaucoma risk prediction, glaucoma detection and diagnosis, visual field estimation and pattern analysis, glaucoma progression detection, and other applications.

Trends in admission rates of primary angle closure diseases for the urban population in China, 2011-2021

Background

Cataract surgery and laser peripheral iridotomy (LPI) are effective approaches for preventing primary angle closure diseases (PACDs), as well as acute primary angle closure (APAC). Due to the development of population screening and increases in cataract surgery rates, this study aimed to examine trends in the admission rates of PACD among the urban population in China.

Methods

This cross-sectional study examined patients who were admitted to a hospital for PACD, and who underwent cataract surgery or LPI operations. The data were obtained from the Yinzhou Regional Health Information Platform (YRHIP) from 2011 to 2021. The annual rates of PACD and APAC admissions, cataract surgery and LPI were analyzed, with the number of cases used as numerators and the annual resident population in Yinzhou district used as denominators.

Results

A total of 2,979 patients with PACD admissions, 1,023 patients with APAC admissions, 53,635 patients who underwent cataract surgery and 16,450 patients who underwent LPI were included. The number of annual admissions for PACD gradually increased from 22 cases (1.6/100000) in 2011 to 387 cases (30.8/100000) in 2016, after which it decreased to 232 cases (16.2/100000) in 2019 and then increased to 505 cases (30.6/100000) in 2021. The number of cataract surgeries gradually increased from 1728 (127.7/100000) in 2011 to 7002 (424.9/100000) in 2021. Similarly, the number of LPI gradually increased from 109 (8.0/100000) in 2011 to 3704 (224.8/100000) in 2021.

Conclusion

The admission rates of PACD for the urban population in China have declined in recent years after a long increasing trend in the rates of cataract surgery and LPI. However, it increased rapidly during the COVID-19 epidemic. The national health database should be further utilized to investigate temporal trends in the prevalence of PACD.

SALUS-A Study on Self-Tonometry for Glaucoma Patients: Design and Implementation of the Electronic Case File

BACKGROUND

 In times of omnipresent digitization and big data, telemedicine and electronic case files (ECFs) are gaining ground for networking between players in the health care sector. In the context of the SALUS study, this approach is applied in practice in the form of electronic platforms to display and process disease-relevant data of glaucoma patients.

OBJECTIVES

 The SALUS ECF is designed and implemented to support data acquisition and presentation, monitoring, and outcome control for patients suffering from glaucoma in a clinical setting. Its main aim is to provide a means for out- and inpatient exchange of information between various stakeholders with an intuitive user interface in ophthalmologic care. Instrument data, anamnestic data, and diagnostic assessments need to be accessible and historic data stored for patient monitoring. Quality control of the data is ensured by a reading center.

METHODS

 Based on an intensive requirement analysis, we implemented the ECF as a web-based application in React with a Datomic back-end exposing REST and GraphQL APIs for data access and import. A flexible role management was developed, which addresses the various tasks of multiple stakeholders in the SALUS study. Data security is ensured by a comprehensive encryption concept. We evaluated the usability and efficiency of the ECF by measuring the durations medical doctors need to enter and work with the data.

RESULTS

 The evaluation showed that the ECF is time-saving in comparison to paper-based assessments and offers supportive monitoring and outcome control for numerical and imaging-related data. By allowing patients and physicians to access the digital ECF, data connectivity as well as patient autonomy were enhanced.

CONCLUSION

 ECFs have a great potential to efficiently support all patients and stakeholders involved in the care of glaucoma patients. They benefit from the efficient management and view of the data tailored to their specific role.

Feasibility of cross-vendor linkage of ophthalmic images with electronic health record data: an analysis from the IRIS Registry®

Purpose

To link compliant, universal Digital Imaging and Communications in Medicine (DICOM) ophthalmic imaging data at the individual patient level with the American Academy of Ophthalmology IRIS® Registry (Intelligent Research in Sight).

Design

A retrospective study using de-identified EHR registry data.

Subjects Participants Controls

IRIS Registry records.

Materials and Methods

DICOM files of several imaging modalities were acquired from two large retina ophthalmology practices. Metadata tags were extracted and harmonized to facilitate linkage to the IRIS Registry using a proprietary, heuristic patient-matching algorithm, adhering to HITRUST guidelines. Linked patients and images were assessed by image type and clinical diagnosis. Reasons for failed linkage were assessed by examining patients' records.

Main Outcome Measures

Success rate of linking clinicoimaging and EHR data at the patient level.

Results

A total of 2 287 839 DICOM files from 54 896 unique patients were available. Of these, 1 937 864 images from 46 196 unique patients were successfully linked to existing patients in the registry. After removing records with abnormal patient names and invalid birthdates, the success linkage rate was 93.3% for images. 88.2% of all patients at the participating practices were linked to at least one image.

Conclusions and Relevance

Using identifiers from DICOM metadata, we created an automated pipeline to connect longitudinal real-world clinical data comprehensively and accurately to various imaging modalities from multiple manufacturers at the patient and visit levels. The process has produced an enriched and multimodal IRIS Registry, bridging the gap between basic research and clinical care by enabling future applications in artificial intelligence algorithmic development requiring large linked clinicoimaging datasets.

Ophthalmology workforce over a decade in the Kingdom of Saudi Arabia: demographics, distribution, and future challenges

BACKGROUND

The ophthalmology workforce is an integral component of any health care system. However, the demand for eye care has imposed a heavy burden on this system. Hence, this study aimed to estimate the trends, demographic characteristics, distribution, and variation between Saudi and non-Saudi ophthalmologists and the future challenges of the ophthalmology workforce in the Kingdom of Saudi Arabia (KSA).

METHODS

This study was conducted in the KSA and included ophthalmologists practicing from 2010 to 2023. From the Saudi Commission for Health Specialties, we obtained the number, gender, nationality, and rank of ophthalmologists. The geographic distribution of ophthalmologists in the KSA was obtained from the Ministry of Health Statistical Yearbook 2021.

RESULTS

As of January 2023, the KSA had a total of 2608 registered ophthalmologists, with approximately 81.06 ophthalmologists per 1,000,000 people. Only 38% of all ophthalmologists in the country were Saudis. The percentage of Saudi female graduates increased from 13.3% to 37.2% over 12 years [Sen's estimator of slope for median increase per year = 1.33 (95% CI 1.22-1.57) graduates; trend test P < 0.001). Additionally, we found that the geographic distribution of ophthalmologists varied (test for homogeneity of rates, P < 0.0001), with the larger regions having a higher concentration of ophthalmologists than the smaller regions (75.6 in Riyadh versus 42.8 in Jazan per 1,000,000 people). However, the World Health Organization's target for the ophthalmologist-to-population ratio has been achieved in all 13 health regions of KSA.

CONCLUSION

The recommended ophthalmologist-to-population ratio has been achieved in the KSA, and the number of Saudi ophthalmologists has almost doubled over the past 8 years. However, the majority of ophthalmologists are still non-Saudi, as Saudi ophthalmologists constitute approximately one-third of the ophthalmology workforce in the KSA. The geographical distribution of ophthalmologists varies, which might affect access to care in peripheral regions. In response to the growing demand for eye care in the KSA, several more effective measures might need to be considered.

[Frequency and distribution of the active agent of intravitreal injections in German centers 2015-2021-An oregis study]

INTRODUCTION

Digitalization in medicine, especially the electronic documentation of patient data, is revolutionizing healthcare systems worldwide. The evaluation of real-world data collected under everyday conditions presents opportunities but also challenges. Electronic medical registries provide a means to compile extensive patient data for scientific inquiries. Oregis is the first nationwide digital registry for health services research established by the German Ophthalmological Society (DOG). Intravitreal operative medicinal injections (IVOM) are among the most frequently performed procedures in ophthalmology. Data on injection numbers and injection frequencies with anti-vascular endothelial growth factor (VEGF) are already available from other countries, whereas data at a national level are not yet available in Germany due to the lack of a nationwide register. It is known that the treatment success of anti-VEGF IVOMs depends largely on the adherence to treatment and thus on the number of injections. There are also differences in cost. In the context of this study, real-world data on the frequency and distribution of intravitreal injections in German centers from 2015 to 2021 were compiled for the first time since the introduction of oregis. The aim of this study is to collect data on the use of anti-VEGF IVOMs in Germany from oregis for the first time and to show the development of injection numbers and anti-VEGF drugs used. At the same time, the possibilities of data retrieval from oregis are demonstrated using a concrete example from daily ophthalmological practice.

MATERIAL AND METHODS

An automated query of records was performed for all patients who received IVOM at oregis-affiliated healthcare facilities between 2015 and 2021. The number of treated patients and the use of anti-VEGF medications, including aflibercept, bevacizumab, brolucizumab, and ranibizumab, were determined. The data were collected in a pseudonymized and anonymized manner.

RESULTS

At the time of data collection, 9 German ophthalmological healthcare facilities were affiliated with oregis. In total, 309,152 patients were registered during the observation period, with 8474 receiving IVOMs. Over the observation period, the number of participating centers, patients, and intravitreal injections increased. The proportional share of anti-VEGF agents among the total number of injections varied during the observation period.

DISCUSSION

Real-world data captured in oregis offer significant potential for enhancing healthcare provision. Oregis enables the depiction of ophthalmological care conditions in Germany and contributes to research and quality assurance. The ability to query the presented data exemplifies the multitude of inquiries through which oregis can contribute to the representation of ophthalmological care in Germany.

The Impact of Documentation Workflow on the Accuracy of the Coded Diagnoses in the Electronic Health Record

Objective

To determine the impact of documentation workflow on the accuracy of coded diagnoses in electronic health records (EHRs).

Design

Cross-sectional study.

Participants

All patients who completed visits at the Casey Eye Institute Retina Division faculty clinic between April 7, 2022 and April 13, 2022.

Main Outcome Measures

Agreement between coded diagnoses and clinical notes.

Methods

We assessed the rate of agreement between the diagnoses in the clinical notes and the coded diagnosis in the EHR using manual review and examined the impact of the documentation workflow on the rate of agreement in an academic retina practice.

Results

In 202 visits by 8 physicians, 78% (range, 22%-100%) had an agreement between the coded diagnoses and the clinical notes. When physicians integrated the diagnosis code entry and note composition, the rate of agreement was 87.9% (range, 62%-100%). For those who entered the diagnosis codes separately from writing notes, the agreement was 44.4% (22%-50%, P < 0.0001).

Conclusion

The visit-specific agreement between the coded diagnosis and the progress note can vary widely by workflow. The workflow and EHR design may be an important part of understanding and improving the quality of EHR data.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Asteroid Hyalosis: An Update on Prevalence, Risk Factors, Emerging Clinical Impact and Management Strategies

Asteroid hyalosis (AH) is a benign clinical entity characterized by the presence of multiple refractile spherical calcium and phospholipids within the vitreous body. First described by Benson in 1894, this entity has been well documented in the clinical literature and is named due to the resemblance of asteroid bodies on clinical examination to a starry night sky. Today, a growing body of epidemiologic data estimates the global prevalence of asteroid hyalosis to be around 1%, and there is a strong established association between AH and older age. While pathophysiology remains unclear, a variety of systemic and ocular risk factors for AH have recently been suggested in the literature and may provide insight into possible mechanisms for asteroid body (AB) development. As vision is rarely affected, clinical management is focused on differentiation of asteroid hyalosis from mimicking conditions, evaluation of the underlying retina for other pathology and consideration of vitrectomy in rare cases with visual impairment. Taking into account the recent technologic advances in large-scale medical databases, improving imaging modalities, and the popularity of telemedicine, this review summarizes the growing body of literature of AH epidemiology and pathophysiology and provides updates on the clinical diagnosis and management of AH.

Ophthalmic surgery in New Zealand: analysis of 410,099 surgical procedures and nationwide surgical intervention rates from 2009 to 2018

BACKGROUND

Surgical intervention rates (SIR) provide a proxy measure of disease burden, surgical capacity, and the relative risk-benefit ratio of surgery. The current study assessed decade trends in ophthalmic surgery and calculated SIRs for all major classes of commonly performed ophthalmic procedures in New Zealand.

METHODS

Retrospective population-based analysis of all ophthalmic surgical procedures performed in New Zealand from 2009 to 2018. National and regional datasets from public and private health sectors and industry were analysed. SIRs were calculated for all major ophthalmic procedures, and subgrouped by patient demographics.

RESULTS

There were 410,099 ophthalmic surgical procedures completed with a 25.3% overall increase over 10 years. Procedures were mostly government-funded (51%, n = 210,830) with 71% of patients aged over 64 years. Cataract surgery (78%, n = 318,564) had the highest mean SIR (703/100,000/year) and increased by 25% during the study period, consistent with population growth in the over 64 years old age group. Vitrectomy surgery had the second highest mean SIR (67/100,000/year) and increased by 50%, well above national population growth during the study period. Other SIRs included conjunctival lesion-biopsy (38/100,000/year), glaucoma (33/100,000/year), strabismus (20/100,000/year), dacryocystorhinostomy (10/100,000/year), and keratoplasty surgery (4/100,000/year).

CONCLUSIONS

This comprehensive review of New Zealand ophthalmic surgery reports increasing SIRs that cannot be explained by population growth alone. Cataract surgery numbers increased year on year consistent with the increase in the over 64 years old population. Vitrectomy surgery growth exceeded that of the national population, including those over 64 years.

Deceptive Tricks in Artificial Intelligence: Adversarial Attacks in Ophthalmology

The artificial intelligence (AI) systems used for diagnosing ophthalmic diseases have significantly progressed in recent years. The diagnosis of difficult eye conditions, such as cataracts, diabetic retinopathy, age-related macular degeneration, glaucoma, and retinopathy of prematurity, has become significantly less complicated as a result of the development of AI algorithms, which are currently on par with ophthalmologists in terms of their level of effectiveness. However, in the context of building AI systems for medical applications such as identifying eye diseases, addressing the challenges of safety and trustworthiness is paramount, including the emerging threat of adversarial attacks. Research has increasingly focused on understanding and mitigating these attacks, with numerous articles discussing this topic in recent years. As a starting point for our discussion, we used the paper by Ma et al. "Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems". A literature review was performed for this study, which included a thorough search of open-access research papers using online sources (PubMed and Google). The research provides examples of unique attack strategies for medical images. Unfortunately, unique algorithms for attacks on the various ophthalmic image types have yet to be developed. It is a task that needs to be performed. As a result, it is necessary to build algorithms that validate the computation and explain the findings of artificial intelligence models. In this article, we focus on adversarial attacks, one of the most well-known attack methods, which provide evidence (i.e., adversarial examples) of the lack of resilience of decision models that do not include provable guarantees. Adversarial attacks have the potential to provide inaccurate findings in deep learning systems and can have catastrophic effects in the healthcare industry, such as healthcare financing fraud and wrong diagnosis.

Eyes as the windows into cardiovascular disease in the era of big data

Cardiovascular disease (CVD) is a major cause of mortality and morbidity worldwide and imposes significant socioeconomic burdens, especially with late diagnoses. There is growing evidence of strong correlations between ocular images, which are information-dense, and CVD progression. The accelerating development of deep learning algorithms (DLAs) is a promising avenue for research into CVD biomarker discovery, early CVD diagnosis, and CVD prognostication. We review a selection of 17 recent DLAs on the less-explored realm of DL as applied to ocular images to produce CVD outcomes, potential challenges in their clinical deployment, and the path forward. The evidence for CVD manifestations in ocular images is well documented. Most of the reviewed DLAs analyze retinal fundus photographs to predict CV risk factors, in particular hypertension. DLAs can predict age, sex, smoking status, alcohol status, body mass index, mortality, myocardial infarction, stroke, chronic kidney disease, and hematological disease with significant accuracy. While the cardio-oculomics intersection is now burgeoning, very much remain to be explored. The increasing availability of big data, computational power, technological literacy, and acceptance all prime this subfield for rapid growth. We pinpoint the specific areas of improvement toward ubiquitous clinical deployment: increased generalizability, external validation, and universal benchmarking. DLAs capable of predicting CVD outcomes from ocular inputs are of great interest and promise to individualized precision medicine and efficiency in the provision of health care with yet undetermined real-world efficacy with impactful initial results.

Big data in corneal diseases and cataract: Current applications and future directions

The accelerated growth in electronic health records (EHR), Internet-of-Things, mHealth, telemedicine, and artificial intelligence (AI) in the recent years have significantly fuelled the interest and development in big data research. Big data refer to complex datasets that are characterized by the attributes of "5 Vs"-variety, volume, velocity, veracity, and value. Big data analytics research has so far benefitted many fields of medicine, including ophthalmology. The availability of these big data not only allow for comprehensive and timely examinations of the epidemiology, trends, characteristics, outcomes, and prognostic factors of many diseases, but also enable the development of highly accurate AI algorithms in diagnosing a wide range of medical diseases as well as discovering new patterns or associations of diseases that are previously unknown to clinicians and researchers. Within the field of ophthalmology, there is a rapidly expanding pool of large clinical registries, epidemiological studies, omics studies, and biobanks through which big data can be accessed. National corneal transplant registries, genome-wide association studies, national cataract databases, and large ophthalmology-related EHR-based registries (e.g., AAO IRIS Registry) are some of the key resources. In this review, we aim to provide a succinct overview of the availability and clinical applicability of big data in ophthalmology, particularly from the perspective of corneal diseases and cataract, the synergistic potential of big data, AI technologies, internet of things, mHealth, and wearable smart devices, and the potential barriers for realizing the clinical and research potential of big data in this field.

Diabetic Patients With Rosacea Increase the Risks of Diabetic Macular Edema, Dry Eye Disease, Glaucoma, and Cataract

PURPOSE

Inflammation plays a role in diabetic eye diseases, but the association between rosacea and eye diseases in patients with diabetes remains unknown.

DESIGN

This retrospective cohort study used claims data from the National Health Insurance Research Database in Taiwan to investigate the association between rosacea and eye diseases in patients with diabetes.

MATERIALS AND METHODS

Taiwanese patients diagnosed as having diabetes mellitus between January 1, 1997, and December 31, 2013, and using any hypoglycemic agents were included and divided into rosacea and nonrosacea groups. After applying 1:20 sex and age matching and exclusion criteria, 1:4 propensity score matching (PSM) was conducted to balance the covariate distribution between the groups. The risk of time-to-event outcome between rosacea and nonrosacea groups in the PSM cohort was compared using the Fine and Gray subdistribution hazard model.

RESULTS

A total of 4096 patients with rosacea and 16,384 patients without rosacea were included in the analysis. During a mean follow-up period of 5 years, diabetic patients with rosacea had significantly higher risks of diabetic macular edema [subdistribution hazard ratio (SHR): 1.31, 95% confidence interval (CI): 1.05-1.63], glaucoma with medical treatment (SHR: 1.11, 95% CI: 1.01-1.21), dry eye disease (SHR: 1.55, 95% CI: 1.38-1.75), and cataract surgery (SHR: 1.13, 95% CI: 1.02-1.25) compared with diabetic patients without rosacea. A cumulative incidence analysis performed up to 14 years after the index date revealed that the risks of developing ocular diseases consistently increased over time. No significant differences in diabetic retinopathy, age-related macular degeneration, retinal vascular occlusion, ischemic optic neuropathy, optic neuritis, uveitis, or retinal detachment were identified according to rosacea diagnosis. However, we observed significant associations between rosacea and psoriasis, irritable bowel syndrome, anxiety, and major depressive disorder among patients with diabetes.

CONCLUSIONS

Rosacea is associated with diabetic macular edema, glaucoma, dry eye disease, and cataract development in diabetic patients, as well as increased risks of psoriasis, irritable bowel syndrome, anxiety, and depression in diabetic patients.

Applications of natural language processing in ophthalmology: present and future

Advances in technology, including novel ophthalmic imaging devices and adoption of the electronic health record (EHR), have resulted in significantly increased data available for both clinical use and research in ophthalmology. While artificial intelligence (AI) algorithms have the potential to utilize these data to transform clinical care, current applications of AI in ophthalmology have focused mostly on image-based deep learning. Unstructured free-text in the EHR represents a tremendous amount of underutilized data in big data analyses and predictive AI. Natural language processing (NLP) is a type of AI involved in processing human language that can be used to develop automated algorithms using these vast quantities of available text data. The purpose of this review was to introduce ophthalmologists to NLP by (1) reviewing current applications of NLP in ophthalmology and (2) exploring potential applications of NLP. We reviewed current literature published in Pubmed and Google Scholar for articles related to NLP and ophthalmology, and used ancestor search to expand our references. Overall, we found 19 published studies of NLP in ophthalmology. The majority of these publications (16) focused on extracting specific text such as visual acuity from free-text notes for the purposes of quantitative analysis. Other applications included: domain embedding, predictive modeling, and topic modeling. Future ophthalmic applications of NLP may also focus on developing search engines for data within free-text notes, cleaning notes, automated question-answering, and translating ophthalmology notes for other specialties or for patients, especially with a growing interest in open notes. As medicine becomes more data-oriented, NLP offers increasing opportunities to augment our ability to harness free-text data and drive innovations in healthcare delivery and treatment of ophthalmic conditions.

Survey-based Evaluation of the Use of Picture Archiving and Communication Systems in an Eye Hospital-Ophthalmologists' Perspective

PURPOSE

Picture archiving and communication system (PACS) is a medical imaging system for sharing, storage, retrieval, and access of medical images stored. Our study aimed to identify ophthalmologists' views on PACS, with the comparison between 3 platforms, namely electronic patient record (ePR), HEYEX (Heidelberg Engineering, Switzerland), and FORUM (Zeiss, US), following their implementation in an eye hospital for common ophthalmic investigations [visual field, optical coherence tomography (OCT) of retinal nerve fiber layer and macula, and fluorescein/indocyanine green angiography (FA/ICG)].

METHODS

An online survey was distributed among ophthalmologists in a single center. Primary outcome included comparison of PACS with paper-based system. Secondary outcomes included pattern of use and comparison of different PACS platforms.

RESULTS

Survey response rate was 28/37 (75.7%). Images were most commonly accessed through ePR (median: 80% of time, interquartile range: 50 to 90%).All systems scored highly in information display items (median scores ≥7.5 out of 10) and in reducing patient identification error in investigation filing and retrieval during consultation compared to paper (score ≥7.0). However, ePR was inferior to paper in "facilitating comparison with previous results" in all investigation types (scores 3.0 to 4.5). ePR scored significantly higher in all system quality items than HEYEX ( P  < 0.001) and FORUM ( P  < 0.022), except login response time ( P  = 0.081). HEYEX scored significantly higher among vitreoretinaluveitis members (VRU) for information quality items for OCT macula and FA/ICG [VRU: 10.0 (8.0 to 10.0), non-VRU: 8.0 (6.75 to 9.25), P  = 0.042].

CONCLUSIONS

Overall feedback for PACS among ophthalmologists was positive, with limitations of inefficiency in use of information, for example, comparison with previous results. Subspecialty played an important role in evaluating PACS.

Validation of Soft Labels in Developing Deep Learning Algorithms for Detecting Lesions of Myopic Maculopathy From Optical Coherence Tomographic Images

PURPOSE

It is common for physicians to be uncertain when examining some images. Models trained with human uncertainty could be a help for physicians in diagnosing pathologic myopia.

DESIGN

This is a hospital-based study that included 9176 images from 1327 patients that were collected between October 2015 and March 2019.

METHODS

All collected images were graded by 21 myopia specialists according to the presence of myopic neovascularization (MNV), myopic traction maculopathy (MTM), and dome-shaped macula (DSM). Hard labels were made by the rule of major wins, while soft labels were possibilities calculated by whole grading results from the different graders. The area under the curve (AUC) of the receiver operating characteristics curve, the area under precision-recall (AUPR) curve, F-score, and least square errors were used to evaluate the performance of the models.

RESULTS

The AUC values of models trained by soft labels in MNV, MTM, and DSM models were 0.985, 0.946, and 0.978; and the AUPR values were 0.908, 0.876, and 0.653 respectively. However, 0.56% of MNV "negative" cases were answered as "positive" with high certainty by the hard label model, whereas no case was graded with extreme errors by the soft label model. The same results were found for the MTM (0.95% vs none) and DSM (0.43% vs 0.09%) models.

CONCLUSIONS

The predicted possibilities from the models trained by soft labels were close to the results made by myopia specialists. These findings could inspire the novel use of deep learning models in the medical field.

Big Data Reality Check (BDRC) for public health: to what extent the environmental health and health services research did meet the 'V' criteria for big data? A study protocol

INTRODUCTION

Big data technologies have been talked up in the fields of science and medicine. The V-criteria (volume, variety, velocity and veracity, etc) for defining big data have been well-known and even quoted in most research articles; however, big data research into public health is often misrepresented due to certain common misconceptions. Such misrepresentations and misconceptions would mislead study designs, research findings and healthcare decision-making. This study aims to identify the V-eligibility of big data studies and their technologies applied to environmental health and health services research that explicitly claim to be big data studies.

METHODS AND ANALYSIS

Our protocol follows Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P). Scoping review and/or systematic review will be conducted. The results will be reported using PRISMA for Scoping Reviews (PRISMA-ScR), or PRISMA 2020 and Synthesis Without Meta-analysis guideline. Web of Science, PubMed, Medline and ProQuest Central will be searched for the articles from the database inception to 2021. Two reviewers will independently select eligible studies and extract specified data. The numeric data will be analysed with R statistical software. The text data will be analysed with NVivo wherever applicable.

ETHICS AND DISSEMINATION

This study will review the literature of big data research related to both environmental health and health services. Ethics approval is not required as all data are publicly available and involves confidential personal data. We will disseminate our findings in a peer-reviewed journal.

PROSPERO REGISTRATION NUMBER

CRD42021202306.

Potential Protective Role of TRPM7 and Involvement of PKC/ERK Pathway in Blue Light-Induced Apoptosis in Retinal Pigment Epithelium Cells in Vitro

PURPOSE

Blue light triggers apoptosis of retinal pigment epithelium (RPE) cells and causes retinal damage. The aim of this study was to elucidate the protective role of transient receptor potential melastatin 7 (TRPM7) in photodamaged RPE cells.

METHODS

RPE cells were isolated from Sprague-Dawley (SD) rats and exposed to varying intensities of blue light (500-5000 lux) in vitro. Cell proliferation and metabolic activity were respectively assessed by bromodeoxyuridine (BrdU) incorporation and 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl-2H-tetrazolium bromide (MTT) assays. Real-time polymerase chain reaction (RT-PCR) and western blotting were used to analyze the TRPM7, protein kinase C (PKC), extracellular signal-regulated kinase (ERK) and Bcl2-associated x/B-cell lymphoma 2 (Bax/Bcl-2) messenger RNA (mRNA) and protein expression levels. The cells were transfected with TRPM7 small interfering RNA (siRNA) or transduced with TRPM7-overexpressing lentiviruses and cultured with or without the pigment epithelium-derived factor (PEDF).

RESULTS

Blue light inhibited the proliferation and metabolic activity of RPE cells in an intensity-dependent manner when compared to nonirradiated controls (P < 0.05). Compared to the control, photodamaged RPE cells showed decreased levels of TRPM7, PKC, ERK, and Bax, and an increase in Bcl-2 levels (P < 0.01). Forced expression of TRPM7 partially rescued the proliferative capacity of RPE cells (P < 0.01) and restored the levels of TRPM7, PKC, ERK, and Bax (P < 0.01), whereas TRPM7 knockdown had the opposite effects (P < 0.01). TRPM7 and PEDF synergistically alleviated the damaging effects of blue light.

CONCLUSIONS

Blue light triggers apoptosis of RPE cells, and its deleterious effects can be partially attenuated by the synergistic action of TRPM7 and PEDF via the PKC/ERK signaling pathway.

In Search of Excellence: From a Small Clinical Unit to an Internationally Recognized Center for Orbital Diseases Research and Surgery at the Department of Ophthalmology, Shanghai Ninth People's Hospital, China

ABSTRACT

"Where there is a will, there is a way." It is never easy to make progress and development but with full dedication and firm commitment, many aspirations can still be realized. We would like to share with the readers the story of how we develop our division of orbital diseases and surgery from scratch to strengths over a period of 2 decades at the Department of Ophthalmology of Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, China.

Digital Transformation in Ophthalmic Clinical Care During the COVID-19 Pandemic

ABSTRACT

COVID-19 has placed unprecedented pressure on health systems globally, whereas simultaneously stimulating unprecedented levels of transformation. Here, we review digital adoption that has taken place during the pandemic to drive improvements in ophthalmic clinical care, with a specific focus on out-of-hospital triage and services, clinical assessment, patient management, and use of electronic health records. We show that although there have been some successes, shortcomings in technology infrastructure prepandemic became only more apparent and consequential as COVID-19 progressed. Through our review, we emphasize the need for clinicians to better grasp and harness key technology trends such as telecommunications and artificial intelligence, so that they can effectively and safely shape clinical practice using these tools going forward.