The current state of artificial intelligence in ophthalmology

OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods

Optical coherence tomography (OCT) is a non-invasive imaging technique with extensive clinical applications in ophthalmology. OCT enables the visualization of the retinal layers, playing a vital role in the early detection and monitoring of retinal diseases. OCT uses the principle of light wave interference to create detailed images of the retinal microstructures, making it a valuable tool for diagnosing ocular conditions. This work presents an open-access OCT dataset (OCTDL) comprising over 2000 OCT images labeled according to disease group and retinal pathology. The dataset consists of OCT records of patients with Age-related Macular Degeneration (AMD), Diabetic Macular Edema (DME), Epiretinal Membrane (ERM), Retinal Artery Occlusion (RAO), Retinal Vein Occlusion (RVO), and Vitreomacular Interface Disease (VID). The images were acquired with an Optovue Avanti RTVue XR using raster scanning protocols with dynamic scan length and image resolution. Each retinal b-scan was acquired by centering on the fovea and interpreted and cataloged by an experienced retinal specialist. In this work, we applied Deep Learning classification techniques to this new open-access dataset.

The utilization of artificial intelligence in glaucoma: diagnosis versus screening

With advancements in the implementation of artificial intelligence (AI) in different ophthalmology disciplines, it continues to have a significant impact on glaucoma diagnosis and screening. This article explores the distinct roles of AI in specialized ophthalmology clinics and general practice, highlighting the critical balance between sensitivity and specificity in diagnostic and screening models. Screening models prioritize sensitivity to detect potential glaucoma cases efficiently, while diagnostic models emphasize specificity to confirm disease with high accuracy. AI applications, primarily using machine learning (ML) and deep learning (DL), have been successful in detecting glaucomatous optic neuropathy from colored fundus photographs and other retinal imaging modalities. Diagnostic models integrate data extracted from various forms of modalities (including tests that assess structural optic nerve damage as well as those evaluating functional damage) to provide a more nuanced, accurate and thorough approach to diagnosing glaucoma. As AI continues to evolve, the collaboration between technology and clinical expertise should focus more on improving specificity of glaucoma diagnostic models to assess ophthalmologists to revolutionize glaucoma diagnosis and improve patients care.

A high-speed microscopy system based on deep learning to detect yeast-like fungi cells in blood

Background: Blood-invasive fungal infections can cause the death of patients, while diagnosis of fungal infections is challenging. Methods: A high-speed microscopy detection system was constructed that included a microfluidic system, a microscope connected to a high-speed camera and a deep learning analysis section. Results: For training data, the sensitivity and specificity of the convolutional neural network model were 93.5% (92.7-94.2%) and 99.5% (99.1-99.5%), respectively. For validating data, the sensitivity and specificity were 81.3% (80.0-82.5%) and 99.4% (99.2-99.6%), respectively. Cryptococcal cells were found in 22.07% of blood samples. Conclusion: This high-speed microscopy system can analyze fungal pathogens in blood samples rapidly with high sensitivity and specificity and can help dramatically accelerate the diagnosis of fungal infectious diseases.

Autosomal recessive cerebellar ataxias: a diagnostic classification approach according to ocular features

Autosomal recessive cerebellar ataxias (ARCAs) are a heterogeneous group of neurodegenerative disorders affecting primarily the cerebellum and/or its afferent tracts, often accompanied by damage of other neurological or extra-neurological systems. Due to the overlap of clinical presentation among ARCAs and the variety of hereditary, acquired, and reversible etiologies that can determine cerebellar dysfunction, the differential diagnosis is challenging, but also urgent considering the ongoing development of promising target therapies. The examination of afferent and efferent visual system may provide neurophysiological and structural information related to cerebellar dysfunction and neurodegeneration thus allowing a possible diagnostic classification approach according to ocular features. While optic coherence tomography (OCT) is applied for the parametrization of the optic nerve and macular area, the eye movements analysis relies on a wide range of eye-tracker devices and the application of machine-learning techniques. We discuss the results of clinical and eye-tracking oculomotor examination, the OCT findings and some advancing of computer science in ARCAs thus providing evidence sustaining the identification of robust eye parameters as possible markers of ARCAs.

The incidence of retinopathy of prematurity in neonates in Germany in 2019; a nationwide epidemiological cohort study

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness in preterm infants. The incidence of ROP varies widely across countries, with rates as high as 30% in some regions. This study investigated the incidence, risk factors, treatment, and mortality of ROP patients in Germany. Data were extracted from the German Federal Statistical Office (Destatis) diagnosis-related group (DRG) and Institute for the Remuneration System in Hospitals (InEK) databases. Patients with a secondary diagnosis of ROP (ICD-10 code H35.1) in the first 28 days of life were included. Data were extracted for patients admitted between January 1, 2019 and December 31, 2019. The diagnoses and procedures were determined using the German version of the International Classification of Diseases (ICD-10-GM) and the German procedure coding system (OPS). The codes 5-154.xx, 5-155.xx, 8-020.xx, 5-156.9, 6-003.(c&d), 6-007.(2&8) were utilised to denote different ocular treatments. Patient Clinical Complexity Levels were extracted and used to compare ROP with non-ROP patients. A total of 1326 patients with ROP were identified. The incidence of ROP is estimated to be 17.04 per 10,000 live births. The incidence was highest in infants with birth weights less than 500 g and decreased with increasing birth weight. The most common risk factors for ROP were low birth weight, male sex, and prematurity. Of the infants with ROP, 7.2% required ocular treatment. The most common treatment was intraocular injections, followed by photocoagulation. No surgical treatment was required for any of the infants during the study period. The mortality rate for infants with ROP was 60.33 per 10,000. This is higher than the overall neonatal death rate of 24.2 per 10,000.

CONCLUSIONS

This study found that the incidence of ROP in Germany is similar to that in other developed countries. The study also found that the mortality rate for infants with ROP is higher than the overall neonatal death rate. These findings highlight the importance of early detection and treatment of ROP in preterm infants.

WHAT IS KNOWN

• ROP is a severe eye condition often affecting preterm infants. • Previous data are limited in scope and generalizability.

WHAT IS NEW

• Based on a national database, our study found ROP incidence to be 17.04 per 10,000 new births, higher in males (17.71) than in females (16.34). • 7.2% of ROP cases required ocular treatment, inversely correlated with birth weight. • High rates of multimorbidity such as neonatal jaundice (84.69%), respiratory distress syndrome (80.84%), and apnea (78.88%) were observed.

Clinical Decision Support Systems Used in Transplantation: Are They Tools for Success or an Unnecessary Gadget? A Systematic Review

Although clinical decision support systems (CDSSs) have been used since the 1970s for a wide variety of clinical tasks including optimization of medication orders, improved documentation, and improved patient adherence, to date, no systematic reviews have been carried out to assess their utilization and efficacy in transplant medicine. The aim of this study is to systematically review studies that utilized a CDSS and assess impact on patient outcomes. A total of 48 articles were identified as meeting the author-derived inclusion criteria, including tools for posttransplant monitoring, pretransplant risk assessment, waiting list management, immunosuppressant management, and interpretation of histopathology. Studies included 15 984 transplant recipients. Tools aimed at helping with transplant patient immunosuppressant management were the most common (19 studies). Thirty-four studies (85%) found an overall clinical benefit following the implementation of a CDSS in clinical practice. Although there are limitations to the existing literature, current evidence suggests that implementing CDSS in transplant clinical settings may improve outcomes for patients. Limited evidence was found using more advanced technologies such as artificial intelligence in transplantation, and future studies should investigate the role of these emerging technologies.

Artificial Intelligence in Ophthalmic Surgery: Current Applications and Expectations

Artificial Intelligence (AI) has found rapidly growing applications in ophthalmology, achieving robust recognition and classification in most kind of ocular diseases. Ophthalmic surgery is one of the most delicate microsurgery, requiring high fineness and stability of surgeons. The massive demand of the AI assist ophthalmic surgery will constitute an important factor in boosting accelerate precision medicine. In clinical practice, it is instrumental to update and review the considerable evidence of the current AI technologies utilized in the investigation of ophthalmic surgery involved in both the progression and innovation of precision medicine. Bibliographic databases including PubMed and Google Scholar were searched using keywords such as "ophthalmic surgery", "surgical selection", "candidate screening", and "robot-assisted surgery" to find articles about AI technology published from 2018 to 2023. In addition to the Editorials and letters to the editor, all types of approaches are considered. In this paper, we will provide an up-to-date review of artificial intelligence in eye surgery, with a specific focus on its application to candidate screening, surgery selection, postoperative prediction, and real-time intraoperative guidance.

Perception of Race and Sex Diversity in Ophthalmology by Artificial Intelligence: A DALL E-2 Study

Purpose

In the past few years, there has been remarkable progress in accessibility of open-source artificial intelligence (AI) image generators, developed to help humans understand how AI sees our world. Here, we characterize perception of racial and sex diversity in ophthalmology by AI.

Methods

OpenAI's open-source DALL E-2 AI was used for image generation of ophthalmologists with queries that all included "American" and "portrait photo". Factors used for queries contained categories of following: "Positive Characteristic", "Negative Characteristic", "Finances", "Region", "Experience", "Academic Rank", and "Subspecialty". The first 40 faces for each search were categorized on the basis of race and sex by two independent reviewers. If race or sex was not agreed upon, a third reviewer independently provided a classification, or if still indeterminate, the image was labeled as such. Images that did not adequately show facial features were excluded from categorization.

Results

A total of 1560 images were included in the analysis. Control search queries specifying solely ophthalmologist sex and/or race outputted (100%) accurate images validating the tool. The query "American ophthalmologist, portrait photo" portrayed the majority of ophthalmologists as White (75%) and male (77.5%). Young/inexperienced/amateur ophthalmologists were perceived to have greater non-White racial diversity (27.5%) and female representation (28.3%) relative to old/experienced/mature ophthalmologists (23.3% non-White and 18.3% female). Ophthalmology department chairs (25%) had slightly more racial diversity compared to residents (22.5%), but residents had greater female representation (30%) compared to chairs (15%).

Conclusion

Our results suggest the DALL E-2 AI may perceive a trend of increasing racial and sex diversity in younger, newer ophthalmologists compared to more senior ophthalmologists. Future investigations should attempt to validate how AI may be used as a tool to evaluate ophthalmology's progress towards becoming more inclusive of increasingly diverse ophthalmologists.

An Update on Strategies to Deliver Protein and Peptide Drugs to the Eye

In the past few decades, advancements in protein engineering, biotechnology, and structural biochemistry have resulted in the discovery of various techniques that enhanced the production yield of proteins, targetability, circulating half-life, product purity, and functionality of proteins and peptides. As a result, the utilization of proteins and peptides has increased in the treatment of many conditions, including ocular diseases. Ocular delivery of large molecules poses several challenges due to their high molecular weight, hydrophilicity, unstable nature, and poor permeation through cellular and enzymatic barriers. The use of novel strategies for delivering protein and peptides such as glycoengineering, PEGylation, Fc-fusion, chitosan nanoparticles, and liposomes have improved the efficacy, safety, and stability, which consequently expanded the therapeutic potential of proteins. This review article highlights various proteins and peptides that are useful in ocular disorders, challenges in their delivery to the eye, and strategies to enhance ocular bioavailability using novel delivery approaches. In addition, a few futuristic approaches that will assist in the ocular delivery of proteins and peptides were also discussed.

ChatGPT Assisting Diagnosis of Neuro-ophthalmology Diseases Based on Case Reports

Purpose

To evaluate the efficiency of large language models (LLMs) including ChatGPT to assist in diagnosing neuro-ophthalmic diseases based on case reports.

Design

Prospective study.

Subjects or Participants

We selected 22 different case reports of neuro-ophthalmic diseases from a publicly available online database. These cases included a wide range of chronic and acute diseases that are commonly seen by neuro-ophthalmic sub-specialists.

Methods

We inserted the text from each case as a new prompt into both ChatGPT v3.5 and ChatGPT Plus v4.0 and asked for the most probable diagnosis. We then presented the exact information to two neuro-ophthalmologists and recorded their diagnoses followed by comparison to responses from both versions of ChatGPT.

Main Outcome Measures

Diagnostic accuracy in terms of number of correctly diagnosed cases among diagnoses.

Results

ChatGPT v3.5, ChatGPT Plus v4.0, and the two neuro-ophthalmologists were correct in 13 (59%), 18 (82%), 19 (86%), and 19 (86%) out of 22 cases, respectively. The agreement between the various diagnostic sources were as follows: ChatGPT v3.5 and ChatGPT Plus v4.0, 13 (59%); ChatGPT v3.5 and the first neuro-ophthalmologist, 12 (55%); ChatGPT v3.5 and the second neuro-ophthalmologist, 12 (55%); ChatGPT Plus v4.0 and the first neuro-ophthalmologist, 17 (77%); ChatGPT Plus v4.0 and the second neuro-ophthalmologist, 16 (73%); and first and second neuro-ophthalmologists 17 (17%).

Conclusions

The accuracy of ChatGPT v3.5 and ChatGPT Plus v4.0 in diagnosing patients with neuro-ophthalmic diseases was 59% and 82%, respectively. With further development, ChatGPT Plus v4.0 may have potential to be used in clinical care settings to assist clinicians in providing quick, accurate diagnoses of patients in neuro-ophthalmology. The applicability of using LLMs like ChatGPT in clinical settings that lack access to subspeciality trained neuro-ophthalmologists deserves further research.

Artificial intelligence in retinal image analysis: Development, advances, and challenges

Modern advances in diagnostic technologies offer the potential for unprecedented insight into ophthalmic conditions relating to the retina. We discuss the current landscape of artificial intelligence in retina with respect to screening, diagnosis, and monitoring of retinal pathologies such as diabetic retinopathy, diabetic macular edema, central serous chorioretinopathy, and age-related macular degeneration. We review the methods used in these models and evaluate their performance in both research and clinical contexts and discuss potential future directions for investigation, use of multiple imaging modalities in artificial intelligence algorithms, and challenges in the application of artificial intelligence in retinal pathologies.

Ocular conditions and injuries, detection and management in spaceflight

Ocular trauma or other ocular conditions can be significantly debilitating in space. A literature review of over 100 articles and NASA evidence books, queried for eye related trauma, conditions, and exposures was conducted. Ocular trauma and conditions during NASA space missions during the Space Shuttle Program and ISS through Expedition 13 in 2006 were reviewed. There were 70 corneal abrasions, 4 dry eyes, 4 eye debris, 5 complaints of ocular irritation, 6 chemical burns, and 5 ocular infections noted. Unique exposures on spaceflight, such as foreign bodies, including celestial dust, which may infiltrate the habitat and contact the ocular surface, as well as chemical and thermal injuries due to prolonged CO2 and heat exposure were reported. Diagnostic modalities used to evaluate the above conditions in space flight include vision questionnaires, visual acuity and Amsler grid testing, fundoscopy, orbital ultrasound, and ocular coherence tomography. Several types of ocular injuries and conditions, mostly affecting the anterior segment, are reported. Further research is necessary to understand the greatest ocular risks that astronauts face and how better we can prevent, but also diagnose and treat these conditions in space.

The use of artificial intelligence for automating or semi-automating biomedical literature analyses: a scoping review

OBJECTIVE

Evidence-based medicine (EBM) is a decision-making process based on the conscious and judicious use of the best available scientific evidence. However, the exponential increase in the amount of information currently available likely exceeds the capacity of human-only analysis. In this context, artificial intelligence (AI) and its branches such as machine learning (ML) can be used to facilitate human efforts in analyzing the literature to foster EBM. The present scoping review aimed to examine the use of AI in the automation of biomedical literature survey and analysis with a view to establishing the state-of-the-art and identifying knowledge gaps.

MATERIALS AND METHODS

Comprehensive searches of the main databases were performed for articles published up to June 2022 and studies were selected according to inclusion and exclusion criteria. Data were extracted from the included articles and the findings categorized.

RESULTS

The total number of records retrieved from the databases was 12,145, of which 273 were included in the review. Classification of the studies according to the use of AI in evaluating the biomedical literature revealed three main application groups, namely assembly of scientific evidence (n=127; 47%), mining the biomedical literature (n=112; 41%) and quality analysis (n=34; 12%). Most studies addressed the preparation of systematic reviews, while articles focusing on the development of guidelines and evidence synthesis were the least frequent. The biggest knowledge gap was identified within the quality analysis group, particularly regarding methods and tools that assess the strength of recommendation and consistency of evidence.

CONCLUSION

Our review shows that, despite significant progress in the automation of biomedical literature surveys and analyses in recent years, intense research is needed to fill knowledge gaps on more difficult aspects of ML, deep learning and natural language processing, and to consolidate the use of automation by end-users (biomedical researchers and healthcare professionals).

The use of artificial intelligence in detecting papilledema from fundus photographs

Papilledema is an optic disc swelling with increased intracranial pressure as the underlying cause. Diagnosis of papilledema is made based on ophthalmoscopy findings. Although important, ophthalmoscopy can be challenging for general physicians and nonophthalmic specialists. Meanwhile, artificial intelligence (AI) has the potential to be a useful tool for the detection of fundus abnormalities, including papilledema. Even more, AI might also be useful in grading papilledema. We aim to review the latest advancement in the diagnosis of papilledema using AI and explore its potential. This review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines. A systematic literature search was performed on four databases (PubMed, Cochrane, ProQuest, and Google Scholar) using the Keywords "AI" and "papilledema" including their synonyms. The literature search identified 372 articles, of which six met the eligibility criteria. Of the six articles included in this review, three articles assessed the use of AI for detecting papilledema, one article evaluated the use of AI for papilledema grading using Frisèn criteria, and two articles assessed the use of AI for both detection and grading. The models for both papilledema detection and grading had shown good diagnostic value, with high sensitivity (83.1%-99.82%), specificity (82.6%-98.65%), and accuracy (85.89%-99.89%). Even though studies regarding the use of AI in papilledema are still limited, AI has shown promising potential for papilledema detection and grading. Further studies will help provide more evidence to support the use of AI in clinical practice.

Comparison of the new Hoffer QST with 4 modern accurate formulas

PURPOSE

To investigate the new Hoffer QST (Savini/Taroni) formula (HQST) and compare it with the original Hoffer Q (HQ) and 4 latest generation formulas.

SETTING

I.R.C.C.S.-G.B. Bietti Foundation, Rome, Italy.

DESIGN

Retrospective case series.

METHODS

Refractive outcomes of the HQST, Barrett Universal II (BUII), Emmetropia Verifying Optical (EVO) 2.0, HQ, Kane, and Radial Basis Function (RBF) 3.0 formulas were compared. Subgroup analysis was performed in short (<22 mm) and long (>25 mm) axial length eyes. The SD of the prediction error (PE) was investigated using the heteroscedastic method.

RESULTS

1259 eyes of 1259 patients divided in a White group (n=696), implanted with the AcriSof SN60AT (Alcon Labs), and an Asian group (n=563), implanted with the SN60WF (Alcon Labs), were investigated. In the Asian group, the heteroscedastic method did not disclose any significant difference among the SD of the 4 modern formulas (range from 0.333 to 0.346 D), whereas the SD of the HQ formula (0.384 D) was significantly higher. Compared with the original HQ formula, in both White and Asian groups, the HQST formula avoided the mean myopic PE in short eyes and the mean hyperopic PE in long eyes.

CONCLUSIONS

The new HQST formula was superior to the original HQ formula and reached statistical and clinical results comparable with those achieved by the BUII, EVO, Kane, and RBF formulas.

Artificial Intelligence for Hip Fracture Detection and Outcome Prediction: A Systematic Review and Meta-analysis

IMPORTANCE

Artificial intelligence (AI) enables powerful models for establishment of clinical diagnostic and prognostic tools for hip fractures; however the performance and potential impact of these newly developed algorithms are currently unknown.

OBJECTIVE

To evaluate the performance of AI algorithms designed to diagnose hip fractures on radiographs and predict postoperative clinical outcomes following hip fracture surgery relative to current practices.

DATA SOURCES

A systematic review of the literature was performed using the MEDLINE, Embase, and Cochrane Library databases for all articles published from database inception to January 23, 2023. A manual reference search of included articles was also undertaken to identify any additional relevant articles.

STUDY SELECTION

Studies developing machine learning (ML) models for the diagnosis of hip fractures from hip or pelvic radiographs or to predict any postoperative patient outcome following hip fracture surgery were included.

DATA EXTRACTION AND SYNTHESIS

This study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses and was registered with PROSPERO. Eligible full-text articles were evaluated and relevant data extracted independently using a template data extraction form. For studies that predicted postoperative outcomes, the performance of traditional predictive statistical models, either multivariable logistic or linear regression, was recorded and compared with the performance of the best ML model on the same out-of-sample data set.

MAIN OUTCOMES AND MEASURES

Diagnostic accuracy of AI models was compared with the diagnostic accuracy of expert clinicians using odds ratios (ORs) with 95% CIs. Areas under the curve for postoperative outcome prediction between traditional statistical models (multivariable linear or logistic regression) and ML models were compared.

RESULTS

Of 39 studies that met all criteria and were included in this analysis, 18 (46.2%) used AI models to diagnose hip fractures on plain radiographs and 21 (53.8%) used AI models to predict patient outcomes following hip fracture surgery. A total of 39 598 plain radiographs and 714 939 hip fractures were used for training, validating, and testing ML models specific to diagnosis and postoperative outcome prediction, respectively. Mortality and length of hospital stay were the most predicted outcomes. On pooled data analysis, compared with clinicians, the OR for diagnostic error of ML models was 0.79 (95% CI, 0.48-1.31; P = .36; I2 = 60%) for hip fracture radiographs. For the ML models, the mean (SD) sensitivity was 89.3% (8.5%), specificity was 87.5% (9.9%), and F1 score was 0.90 (0.06). The mean area under the curve for mortality prediction was 0.84 with ML models compared with 0.79 for alternative controls (P = .09).

CONCLUSIONS AND RELEVANCE

The findings of this systematic review and meta-analysis suggest that the potential applications of AI to aid with diagnosis from hip radiographs are promising. The performance of AI in diagnosing hip fractures was comparable with that of expert radiologists and surgeons. However, current implementations of AI for outcome prediction do not seem to provide substantial benefit over traditional multivariable predictive statistics.

Use of Machine Learning to Assess Cataract Surgery Skill Level With Tool Detection

Purpose

To develop a method for objective analysis of the reproducible steps in routine cataract surgery.

Design

Prospective study; machine learning.

Participants

Deidentified faculty and trainee surgical videos.

Methods

Consecutive cataract surgeries performed by a faculty or trainee surgeon in an ophthalmology residency program over 6 months were collected and labeled according to degrees of difficulty. An existing image classification network, ResNet 152, was fine-tuned for tool detection in cataract surgery to allow for automatic identification of each unique surgical instrument. Individual microscope video frame windows were subsequently encoded as a vector. The relation between vector encodings and perceived skill using k-fold user-out cross-validation was examined. Algorithms were evaluated using area under the receiver operating characteristic curve (AUC) and the classification accuracy.

Main Outcome Measures

Accuracy of tool detection and skill assessment.

Results

In total, 391 consecutive cataract procedures with 209 routine cases were used. Our model achieved an AUC ranging from 0.933 to 0.998 for tool detection. For skill classification, AUC was 0.550 (95% confidence interval [CI], 0.547–0.553) with an accuracy of 54.3% (95% CI, 53.9%–54.7%) for a single snippet, AUC was 0.570 (0.565–0.575) with an accuracy of 57.8% (56.8%–58.7%) for a single surgery, and AUC was 0.692 (0.659–0.758) with an accuracy of 63.3% (56.8%–69.8%) for a single user given all their trials.

Conclusions

Our research shows that machine learning can accurately and independently identify distinct cataract surgery tools in videos, which is crucial for comparing the use of the tool in a step. However, it is more challenging for machine learning to accurately differentiate overall and specific step skill to assess the level of training or expertise.

Financial Disclosure(s)

The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Artificial intelligence (AI) acceptance in primary care during the coronavirus pandemic: What is the role of patients' gender, age and health awareness? A two-phase pilot study

Background

Artificial intelligence (AI) is steadily entering and transforming the health care and Primary Care (PC) domains. AI-based applications assist physicians in disease detection, medical advice, triage, clinical decision-making, diagnostics and digital public health. Recent literature has explored physicians' perspectives on the potential impact of digital public health on key tasks in PC. However, limited attention has been given to patients' perspectives of AI acceptance in PC, specifically during the coronavirus pandemic. Addressing this research gap, we administered a pilot study to investigate criteria for patients' readiness to use AI-based PC applications by analyzing key factors affecting the adoption of digital public health technology.

Methods

The pilot study utilized a two-phase mixed methods approach. First, we conducted a qualitative study with 18 semi-structured interviews. Second, based on the Technology Readiness and Acceptance Model (TRAM), we conducted an online survey (n = 447).

Results

The results indicate that respondents who scored high on innovativeness had a higher level of readiness to use AI-based technology in PC during the coronavirus pandemic. Surprisingly, patients' health awareness and sociodemographic factors, such as age, gender and education, were not significant predictors of AI-based technology acceptance in PC.

Conclusions

This paper makes two major contributions. First, we highlight key social and behavioral determinants of acceptance of AI-enabled health care and PC applications. Second, we propose that to increase the usability of digital public health tools and accelerate patients' AI adoption, in complex digital public health care ecosystems, we call for implementing adaptive, population-specific promotions of AI technologies and applications.

Application of artificial intelligence in medical technologies: A systematic review of main trends

Objective

Artificial intelligence (AI) has been increasingly applied in various fields of science and technology. In line with the current research, medicine involves an increasing number of artificial intelligence technologies. The introduction of rapid AI can lead to positive and negative effects. This is a multilateral analytical literature review aimed at identifying the main branches and trends in the use of using artificial intelligence in medical technologies.

Methods

The total number of literature sources reviewed is n = 89, and they are analyzed based on the literature reporting evidence-based guideline PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) for a systematic review.

Results

As a result, from the initially selected 198 references, 155 references were obtained from the databases and the remaining 43 sources were found on open internet as direct links to publications. Finally, 89 literature sources were evaluated after exclusion of unsuitable references based on the duplicated and generalized information without focusing on the users.

Conclusions

This article is identifying the current state of artificial intelligence in medicine and prospects for future use. The findings of this review will be useful for healthcare and AI professionals for improving the circulation and use of medical AI from design to implementation stage.

Teleophthalmology research: Where do we stand?

PURPOSE

To identify global research trends in teleophthalmology, as well as productivity and its association with Human development index (HDI).

METHODS

A cross-sectional study. The main outcome measures were publication count, citation count, and publications count per million populations. Bibliographic data were derived from the Web of Science website. HDI data were derived from Human Development Report [2020]. One-way ANOVA test was used to examine the association between HDI and the outcome measures. We studied the correlation between continuous variables using Spearman's. Bibliometric analysis software's VOSviewer and Citspace were used to analyse results and creating visualizing maps.

RESULTS

The results retrieved 355 publications, one-third of them have been published in the year of the COVID-19 pandemic; (2020). The USA has contributed to one-half of all publications, and just five countries have contributed to about 90% of all records. Very high HDI countries had significantly more publications count per million populations, than high (p-value = 0.0047), medium (p-value = 0.0081) or low HDI countries (p-value = 0.002). The main themes are screening programmes, reliability, photography, COVID-19, access, artificial intelligence, and cost-effectiveness. The leading countries in terms of both publications and citation count are the USA and India. In terms of publications count per million populations, the leading countries are Singapore and Australia.

CONCLUSION

Most of the contribution in teleophthalmology research was confined to a small number of countries. More effort is needed to expand the global contribution. The hotspots in this field are artificial intelligence applications and COVID-19 impact.

Integration of Artificial Intelligence into the Approach for Diagnosis and Monitoring of Dry Eye Disease

Dry eye disease (DED) is one of the most common diseases worldwide that can lead to a significant impairment of quality of life. The diagnosis and treatment of the disease are often challenging because of the lack of correlation between the signs and symptoms, limited reliability of diagnostic tests, and absence of established consensus on the diagnostic criteria. The advancement of machine learning, particularly deep learning technology, has enabled the application of artificial intelligence (AI) in various anterior segment disorders, including DED. Currently, many studies have reported promising results of AI-based algorithms for the accurate diagnosis of DED and precise and reliable assessment of data obtained by imaging devices for DED. Thus, the integration of AI into clinical approaches for DED can enhance diagnostic and therapeutic performance. In this review, in addition to a brief summary of the application of AI in anterior segment diseases, we will provide an overview of studies regarding the application of AI in DED and discuss the recent advances in the integration of AI into the clinical approach for DED.

Application of Deep Learning for Automated Detection of Polypoidal Choroidal Vasculopathy in Spectral Domain Optical Coherence Tomography

Objective

To develop an automated polypoidal choroidal vasculopathy (PCV) screening model to distinguish PCV from wet age-related macular degeneration (wet AMD).

Methods

A retrospective review of spectral domain optical coherence tomography (SD-OCT) images was undertaken. The included SD-OCT images were classified into two distinct categories (PCV or wet AMD) prior to the development of the PCV screening model. The automated detection of PCV using the developed model was compared with the results of gold-standard fundus fluorescein angiography and indocyanine green (FFA + ICG) angiography. A framework of SHapley Additive exPlanations was used to interpret the results from the model.

Results

A total of 2334 SD-OCT images were enrolled for training purposes, and an additional 1171 SD-OCT images were used for external validation. The ResNet attention model yielded superior performance with average area under the curve values of 0.8 and 0.81 for the training and external validation data sets, respectively. The sensitivity/specificity calculated at a patient level was 100%/60% and 85%/71% for the training and external validation data sets, respectively.

Conclusions

A conventional FFA + ICG investigation to differentiate PCV from wet AMD requires intense health care resources and adversely affects patients. A deep learning algorithm is proposed to automatically distinguish PCV from wet AMD. The developed algorithm exhibited promising performance for further development into an alternative PCV screening tool. Enhancement of the model's performance with additional data is needed prior to implementation of this diagnostic tool in real-world clinical practice. The invisibility of disease signs within SD-OCT images is the main limitation of the proposed model.

Translational Relevance

Basic research of deep learning algorithms was applied to differentiate PCV from wet AMD based on OCT images, benefiting a diagnosis process and minimizing a risk of ICG angiogram.

Etiology of Macular Edema Defined by Deep Learning in Optical Coherence Tomography Scans

Purpose

To develop an automated method based on deep learning (DL) to classify macular edema (ME) from the evaluation of optical coherence tomography (OCT) scans.

Methods

A total of 4230 images were obtained from data repositories of patients attended in an ophthalmology clinic in Colombia and two free open-access databases. They were annotated with four biomarkers (BMs) as intraretinal fluid, subretinal fluid, hyperreflective foci/tissue, and drusen. Then the scans were labeled as control or ocular disease among diabetic macular edema (DME), neovascular age-related macular degeneration (nAMD), and retinal vein occlusion (RVO) by two expert ophthalmologists. Our method was developed by following four consecutive phases: segmentation of BMs, the combination of BMs, feature extraction with convolutional neural networks to achieve binary classification for each disease, and, finally, multiclass classification of diseases and control images.

Results

The accuracy of our model for nAMD was 97%, and for DME, RVO, and control were 94%, 93%, and 93%, respectively. Area under curve values were 0.99, 0.98, 0.96, and 0.97, respectively. The mean Cohen's kappa coefficient for the multiclass classification task was 0.84.

Conclusions

The proposed DL model may identify OCT scans as normal and ME. In addition, it may classify its cause among three major exudative retinal diseases with high accuracy and reliability.

Translational Relevance

Our DL approach can optimize the efficiency and timeliness of appropriate etiological diagnosis of ME, thus improving patient access and clinical decision making. It could be useful in places with a shortage of specialists and for readers that evaluate OCT scans remotely.

Protocol for a systematic review and meta-analysis of the diagnostic accuracy of artificial intelligence for grading of ophthalmology imaging modalities

BACKGROUND

With the rise of artificial intelligence (AI) in ophthalmology, the need to define its diagnostic accuracy is increasingly important. The review aims to elucidate the diagnostic accuracy of AI algorithms in screening for all ophthalmic conditions in patient care settings that involve digital imaging modalities, using the reference standard of human graders.

METHODS

This is a systematic review and meta-analysis. A literature search will be conducted on Ovid MEDLINE, Ovid EMBASE, and Wiley Cochrane CENTRAL from January 1, 2000, to December 20, 2021. Studies will be selected via screening the titles and abstracts, followed by full-text screening. Articles that compare the results of AI-graded ophthalmic images with results from human graders as a reference standard will be included; articles that do not will be excluded. The systematic review software DistillerSR will be used to automate part of the screening process as an adjunct to human reviewers. After the full-text screening, data will be extracted from each study via the categories of study characteristics, patient information, AI methods, intervention, and outcomes. Risk of bias will be scored using Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) by two trained independent reviewers. Disagreements at any step will be addressed by a third adjudicator. The study results will include summary receiver operating characteristic (sROC) curve plots as well as pooled sensitivity and specificity of artificial intelligence for detection of any ophthalmic conditions based on imaging modalities compared to the reference standard. Statistics will be calculated in the R statistical software.

DISCUSSION

This study will provide novel insights into the diagnostic accuracy of AI in new domains of ophthalmology that have not been previously studied. The protocol also outlines the use of an AI-based software to assist in article screening, which may serve as a reference for improving the efficiency and accuracy of future large systematic reviews.

TRIAL REGISTRATION

PROSPERO, CRD42021274441.

The Deception of Certainty: how Non-Interpretable Machine Learning Outcomes Challenge the Epistemic Authority of Physicians. A deliberative-relational Approach

Developments in Machine Learning (ML) have attracted attention in a wide range of healthcare fields to improve medical practice and the benefit of patients. Particularly, this should be achieved by providing more or less automated decision recommendations to the treating physician. However, some hopes placed in ML for healthcare seem to be disappointed, at least in part, by a lack of transparency or traceability. Skepticism exists primarily in the fact that the physician, as the person responsible for diagnosis, therapy, and care, has no or insufficient insight into how such recommendations are reached. The following paper aims to make understandable the specificity of the deliberative model of a physician-patient relationship that has been achieved over decades. By outlining the (social-)epistemic and inherently normative relationship between physicians and patients, I want to show how this relationship might be altered by non-traceable ML recommendations. With respect to some healthcare decisions, such changes in deliberative practice may create normatively far-reaching challenges. Therefore, in the future, a differentiation of decision-making situations in healthcare with respect to the necessary depth of insight into the process of outcome generation seems essential.

Automatic Classification of Hospital Settings through Artificial Intelligence

Modern hospitals have to meet requirements from national and international institutions in order to ensure hygiene, quality and organisational standards. Moreover, a hospital must be flexible and adaptable to new delivery models for healthcare services. Various hospital monitoring tools have been developed over the years, which allow for a detailed picture of the effectiveness and efficiency of the hospital itself. Many of these systems are based on database management systems (DBMSs), building information modelling (BIM) or geographic information systems (GISs). This work presents an automatic recognition system for hospital settings that integrates these tools. Three alternative proposals were analysed in terms of the construction of the system: the first was based on the use of general models that are present on the cloud for the classification of images; the second consisted of the creation of a customised model and referred to the Clarifai Custom Model service; the third used an object recognition software that was developed by Facebook AI Research combined with a random forest classifier. The obtained results were promising. The customised model almost always classified the photos according to the correct intended use, resulting in a high percentage of confidence of up to 96%. Classification using the third tool was excellent when considering a limited number of hospital settings, with a peak accuracy of higher than 99% and an area under the ROC curve (AUC) of one for specific classes. As expected, increasing the number of room typologies to be discerned negatively affected performance.

Artificial Intelligence Meets Neuro-Ophthalmology

ABSTRACT

Recent advances in artificial intelligence have provided ophthalmologists with fast, accurate, and automated means for diagnosing and treating ocular conditions, paving the way to a modern and scalable eye care system. Compared to other ophthalmic disciplines, neuro-ophthalmology has, until recently, not benefitted from significant advances in the area of artificial intelligence. In this narrative review, we summarize and discuss recent advancements utilizing artificial intelligence for the detection of structural and functional optic nerve head abnormalities, and ocular movement disorders in neuro-ophthalmology.

The Role of Artificial Intelligence in the Diagnosis and Management of Glaucoma

Glaucomatous optic neuropathy is the leading cause of irreversible blindness worldwide. Diagnosis and monitoring of disease involves integrating information from the clinical examination with subjective data from visual field testing and objective biometric data that includes pachymetry, corneal hysteresis, and optic nerve and retinal imaging. This intricate process is further complicated by the lack of clear definitions for the presence and progression of glaucomatous optic neuropathy, which makes it vulnerable to clinician interpretation error. Artificial intelligence (AI) and AI-enabled workflows have been proposed as a plausible solution. Applications derived from this field of computer science can improve the quality and robustness of insights obtained from clinical data that can enhance the clinician's approach to patient care. This review clarifies key terms and concepts used in AI literature, discusses the current advances of AI in glaucoma, elucidates the clinical advantages and challenges to implementing this technology, and highlights potential future applications.

A clinical perspective on the expanding role of artificial intelligence in age-related macular degeneration

In recent years, there has been intense development of artificial intelligence (AI) techniques, which have the potential to improve the clinical management of age-related macular degeneration (AMD) and facilitate the prevention of irreversible vision loss from this condition. Such AI techniques could be used as clinical decision support tools to: (i) improve the detection of AMD by community eye health practitioners, (ii) enhance risk stratification to enable personalised monitoring strategies for those with the early stages of AMD, and (iii) enable early detection of signs indicative of possible choroidal neovascularisation allowing triaging of patients requiring urgent review. This review discusses the latest developments in AI techniques that show promise for these tasks, as well as how they may help in the management of patients being treated for choroidal neovascularisation and in accelerating the discovery of new treatments in AMD.

Analysis of international publication trends in artificial intelligence in ophthalmology

PURPOSE

Artificial intelligence (AI) has entered the field of medicine, and ophthalmology is no exception. The objective of this study was to report on scientific production and publication trends, to identify journals, countries, international collaborations, and major MeSH terms involved in AI in ophthalmology research.

METHODS

Scientometric methods were used to evaluate global scientific production and development trends in AI in ophthalmology using PubMed and the Web of Science Core Collection.

RESULTS

A total of 1356 articles were retrieved over the period 1966-2019. The yearly growth of AI in ophthalmology publications has been 18.89% over the last ten years, indicating that AI in ophthalmology is a very attractive topic in science. Analysis of the most productive journals showed that most were specialized in computer and medical systems. No journal was found to specialize in AI in ophthalmology. The USA, China, and the UK were the three most productive countries. The study of international collaboration showed that, besides the USA, researchers tended to collaborate with peers from neighboring countries. Among the twenty most frequent MeSH terms retrieved, there were only four related to clinical topics, revealing the retina and glaucoma as the most frequently encountered subjects of interest in AI in ophthalmology. Analysis of the top ten Journal Citation Reports categories of journals and MeSH terms for articles confirmed that AI in ophthalmology research is mainly focused on engineering and computing and is mainly technical research related to computer methods.

CONCLUSIONS

This study provides a broad view of the current status and trends in AI in ophthalmology research and shows that AI in ophthalmology research is an attractive topic focusing on retinal diseases and glaucoma. This study may be useful for researchers in AI in ophthalmology such as clinicians, but also for scientists to better understand this research topic, know the main actors in this field (including journals and countries), and have a general overview of this research theme.

Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy

Background: In recent years, deep learning has been widely used in a variety of ophthalmic diseases. As a common ophthalmic disease, meibomian gland dysfunction (MGD) has a unique phenotype in in-vivo laser confocal microscope imaging (VLCMI). The purpose of our study was to investigate a deep learning algorithm to differentiate and classify obstructive MGD (OMGD), atrophic MGD (AMGD) and normal groups. Methods: In this study, a multi-layer deep convolution neural network (CNN) was trained using VLCMI from OMGD, AMGD and healthy subjects as verified by medical experts. The automatic differential diagnosis of OMGD, AMGD and healthy people was tested by comparing its image-based identification of each group with the medical expert diagnosis. The CNN was trained and validated with 4,985 and 1,663 VLCMI images, respectively. By using established enhancement techniques, 1,663 untrained VLCMI images were tested. Results: In this study, we included 2,766 healthy control VLCMIs, 2,744 from OMGD and 2,801 from AMGD. Of the three models, differential diagnostic accuracy of the DenseNet169 CNN was highest at over 97%. The sensitivity and specificity of the DenseNet169 model for OMGD were 88.8 and 95.4%, respectively; and for AMGD 89.4 and 98.4%, respectively. Conclusion: This study described a deep learning algorithm to automatically check and classify VLCMI images of MGD. By optimizing the algorithm, the classifier model displayed excellent accuracy. With further development, this model may become an effective tool for the differential diagnosis of MGD.

Development of glaucoma predictive model and risk factors assessment based on supervised models

Objectives

To develop and to propose a machine learning model for predicting glaucoma and identifying its risk factors.

Method

Data analysis pipeline is designed for this study based on Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. The main steps of the pipeline include data sampling, preprocessing, classification and evaluation and validation. Data sampling for providing the training dataset was performed with balanced sampling based on over-sampling and under-sampling methods. Data preprocessing steps were missing value imputation and normalization. For classification step, several machine learning models were designed for predicting glaucoma including Decision Trees (DTs), K-Nearest Neighbors (K-NN), Support Vector Machines (SVM), Random Forests (RFs), Extra Trees (ETs) and Bagging Ensemble methods. Moreover, in the classification step, a novel stacking ensemble model is designed and proposed using the superior classifiers.

Results

The data were from Shahroud Eye Cohort Study including demographic and ophthalmology data for 5190 participants aged 40-64 living in Shahroud, northeast Iran. The main variables considered in this dataset were 67 demographics, ophthalmologic, optometric, perimetry, and biometry features for 4561 people, including 4474 non-glaucoma participants and 87 glaucoma patients. Experimental results show that DTs and RFs trained based on under-sampling of the training dataset have superior performance for predicting glaucoma than the compared single classifiers and bagging ensemble methods with the average accuracy of 87.61 and 88.87, the sensitivity of 73.80 and 72.35, specificity of 87.88 and 89.10 and area under the curve (AUC) of 91.04 and 94.53, respectively. The proposed stacking ensemble has an average accuracy of 83.56, a sensitivity of 82.21, a specificity of 81.32, and an AUC of 88.54.

Conclusions

In this study, a machine learning model is proposed and developed to predict glaucoma disease among persons aged 40-64. Top predictors in this study considered features for discriminating and predicting non-glaucoma persons from glaucoma patients include the number of the visual field detect on perimetry, vertical cup to disk ratio, white to white diameter, systolic blood pressure, pupil barycenter on Y coordinate, age, and axial length.

Classification Tree to Analyze Factors Connected with Post Operative Complications of Cataract Surgery in a Teaching Hospital

Background: Artificial intelligence (AI) is becoming ever more frequently applied in medicine and, consequently, also in ophthalmology to improve both the quality of work for physicians and the quality of care for patients. The aim of this study is to use AI, in particular classification tree, for the evaluation of both ocular and systemic features involved in the onset of complications due to cataract surgery in a teaching hospital. Methods: The charts of 1392 eyes of 1392 patients, with a mean age of 71.3 ± 8.2 years old, were reviewed to collect the ocular and systemic data before, during and after cataract surgery, including post-operative complications. All these data were processed by a classification tree algorithm, producing more than 260 million simulations, aiming to develop a predictive model. Results: Postoperative complications were observed in 168 patients. According to the AI analysis, the pre-operative characteristics involved in the insurgence of complications were: ocular comorbidities, lower visual acuity, higher astigmatism and intra-operative complications. Conclusions: Artificial intelligence application may be an interesting tool in the physician’s hands to develop customized algorithms that can, in advance, define the post-operative complication risk. This may help in improving both the quality and the outcomes of the surgery as well as in preventing patient dissatisfaction.

Classification Tree to Analyze Factors Connected with Post Operative Complications of Cataract Surgery in a Teaching Hospital

BACKGROUND

Artificial intelligence (AI) is becoming ever more frequently applied in medicine and, consequently, also in ophthalmology to improve both the quality of work for physicians and the quality of care for patients. The aim of this study is to use AI, in particular classification tree, for the evaluation of both ocular and systemic features involved in the onset of complications due to cataract surgery in a teaching hospital.

METHODS

The charts of 1392 eyes of 1392 patients, with a mean age of 71.3 ± 8.2 years old, were reviewed to collect the ocular and systemic data before, during and after cataract surgery, including post-operative complications. All these data were processed by a classification tree algorithm, producing more than 260 million simulations, aiming to develop a predictive model.

RESULTS

Postoperative complications were observed in 168 patients. According to the AI analysis, the pre-operative characteristics involved in the insurgence of complications were: ocular comorbidities, lower visual acuity, higher astigmatism and intra-operative complications.

CONCLUSIONS

Artificial intelligence application may be an interesting tool in the physician's hands to develop customized algorithms that can, in advance, define the post-operative complication risk. This may help in improving both the quality and the outcomes of the surgery as well as in preventing patient dissatisfaction.

Assessment and management of retinopathy of prematurity in the era of anti-vascular endothelial growth factor (VEGF)

The incidence of retinopathy of prematurity (ROP) continues to rise due to the improved survival of very low birth weight infants in developed countries. This epidemic is also fueled by increased survival of preterm babies with variable use of oxygen and a lack of ROP awareness and screening services in resource-limited regions. Improvements in technology and a basic understanding of the disease pathophysiology have changed the way we screen and manage ROP, educate providers and patients, and improve ROP awareness. Advancements in imaging techniques, expansion of telemedicine services, and the potential for artificial intelligence-assisted ROP screening programs have created opportunities to improve ROP care in areas with a shortage of ophthalmologists trained in ROP. To address the gap in provider knowledge regarding ROP, the Global Education Network for Retinopathy of Prematurity (GEN-ROP) created a web-based tele-education training module that can be used to educate all providers involved in ROP, including non-physician ROP screeners. Over the past 50 years, the treatment of severe ROP has evolved from limited treatment modalities to cryotherapy and laser photocoagulation. More recently, there has been growing evidence to support the use of anti-vascular endothelial growth factor (VEGF) agents for the treatment of severe ROP. However, VEGF is known to be important in organogenesis and microvascular maintenance, and given that intravitreal anti-VEGF treatment can result in systemic VEGF suppression over a period of at least 1-12 weeks, there are concerns regarding adverse effects and long-term ocular and systemic developmental consequences of anti-VEGF therapy. Future research in ophthalmology to address the growing burden of ROP should focus on cost-effective fundus imaging devices, implementation of artificial intelligence platforms, updated treatment algorithms with optimal use of anti-VEGF and careful investigation of its long-term effects, and surgical options in advanced ROP. Addressing these unmet needs will aid the global effort against the ROP epidemic and optimize our understanding and treatment of this blinding disease.

Artificial intelligence in ophthalmology and visual sciences: Current implications and future directions

Since its inception in 1959, artificial intelligence (AI) has evolved at an unprecedented rate and has revolutionized the world of medicine. Ophthalmology, being an image-driven field of medicine, is well-suited for the implementation of AI. Machine learning (ML) and deep learning (DL) models are being utilized for screening of vision threatening ocular conditions of the eye. These models have proven to be accurate and reliable for diagnosing anterior and posterior segment diseases, screening large populations, and even predicting the natural course of various ocular morbidities. With the increase in population and global burden of managing irreversible blindness, AI offers a unique solution when implemented in clinical practice. In this review, we discuss what are AI, ML, and DL, their uses, future direction for AI, and its limitations in ophthalmology.

Clinical Wide-Field Retinal Image Deep Learning Classification of Exudative and Non-Exudative Age-Related Macular Degeneration

Background: Age-related macular degeneration (AMD) is a disease that currently affects approximately 196 million individuals and is projected to affect 288 million in 2040. As a result, better and earlier detection methods for this disease are needed in an effort to provide a higher quality of care. One way to achieve this is through the utilization of machine learning. A deep neural network, specifically a convoluted neural network (CNN) can be trained to differentiate between different types of AMD images given the proper training data.

Methods: In this study, a CNN was trained on 420 Optos wide-field retinal images for 70 epochs in order to classify between exudative and non-exudative AMD. These images were obtained and labeled by ophthalmologists from the Martel Eye Clinic in Rancho Cordova, CA. 

Results: After completing the study, a model was created with 88% accuracy. Both the training and validation loss started above 1 and ended below 0.2. Despite only analyzing a single image at a time, the model was still able to accurately identify if the individual had AMD in both eyes or one eye only. The model had the most trouble with bilateral non-exudative AMD. Overall the model was fairly accurate in the other categories. It was noted that the neural network was able to further differentiate from a single image if the disease is present in left, right, or both eyes. This is a point of contention for further investigation as it is impossible for the artificial intelligence (AI) to extrapolate the condition of both eyes from only one image.

Conclusion: This research fostered the development of a CNN that was able to differentiate between exudative and non-exudative AMD. As well as determine if the disease is present in the right, left, or both eyes with a relatively high degree of accuracy. The model was trained on clinical data and can theoretically be used to classify other clinical images it has never encountered before. 

WSES project on decision support systems based on artificial neural networks in emergency surgery

The article is a scoping review of the literature on the use of decision support systems based on artificial neural networks in emergency surgery. The authors present modern literature data on the effectiveness of artificial neural networks for predicting, diagnosing and treating abdominal emergency conditions: acute appendicitis, acute pancreatitis, acute cholecystitis, perforated gastric or duodenal ulcer, acute intestinal obstruction, and strangulated hernia. The intelligent systems developed at present allow a surgeon in an emergency setting, not only to check his own diagnostic and prognostic assumptions, but also to use artificial intelligence in complex urgent clinical cases. The authors summarize the main limitations for the implementation of artificial neural networks in surgery and medicine in general. These limitations are the lack of transparency in the decision-making process; insufficient quality educational medical data; lack of qualified personnel; high cost of projects; and the complexity of secure storage of medical information data. The development and implementation of decision support systems based on artificial neural networks is a promising direction for improving the forecasting, diagnosis and treatment of emergency surgical diseases and their complications.

Real-Time Mobile Teleophthalmology for the Detection of Eye Disease in Minorities and Low Socioeconomics At-Risk Populations

PURPOSE

To examine the benefits and feasibility of a mobile, real-time, community-based, teleophthalmology program for detecting eye diseases in the New York metro area.

DESIGN

Single site, nonrandomized, cross-sectional, teleophthalmologic study.

METHODS

Participants underwent a comprehensive evaluation in a Wi-Fi-equipped teleophthalmology mobile unit. The evaluation consisted of a basic anamnesis with a questionnaire form, brief systemic evaluations and an ophthalmologic evaluation that included visual field, intraocular pressure, pachymetry, anterior segment optical coherence tomography, posterior segment optical coherence tomography, and nonmydriatic fundus photography. The results were evaluated in real-time and follow-up calls were scheduled to complete a secondary questionnaire form. Risk factors were calculated for different types of ophthalmological referrals.

RESULTS

A total of 957 participants were screened. Out of 458 (48%) participants that have been referred, 305 (32%) had glaucoma, 136 (14%) had narrow-angle, 124 (13%) had cataract, 29 had (3%) diabetic retinopathy, 9 (1%) had macular degeneration, and 97 (10%) had other eye disease findings. Significant risk factors for ophthalmological referral consisted of older age, history of high blood pressure, diabetes mellitus, Hemoglobin A1c measurement of ≥6.5, and stage 2 hypertension. As for the ocular parameters, all but central corneal thickness were found to be significant, including having an intraocular pressure >21 mm Hg, vertical cup-to-disc ratio ≥0.5, visual field abnormalities, and retinal nerve fiber layer thinning.

CONCLUSIONS

Mobile, real-time teleophthalmology is both workable and effective in increasing access to care and identifying the most common causes of blindness and their risk factors.

Artificial intelligence applications in different imaging modalities for corneal topography

Interpretation of topographical maps used to detect corneal ectasias requires a high level of expertise. Several artificial intelligence (AI) technologies have attempted to interpret topographic maps. The purpose of this study is to provide a review of AI algorithms in corneal topography from the perspectives of an eye care professional, a biomedical engineer, and a data scientist. A systematic literature review using Web of Science, Pubmed, and Google Scholar was performed from 2010 to 2020 on themes regarding imaging modalities, their parameters, purpose, and conclusions and their samples and performance related to AI in corneal topography. We provide a comprehensive summary of advances in corneal imaging and its applications in AI. Combined metrics from the Dual Scheimpflug and Placido device could be a good starting point to try AI models in corneal imaging systems. The range of area under the receiving operating curve for AI in keratoconus detection and classification was from 0.87 to 1, sensitivity was from 0.89 to 1, and specificity was from 0.82 to 1. A combination of different types of AI applications to corneal ectasia diagnosis is recommended.

Teleophthalmology and Artificial Intelligence As Game Changers in Ophthalmic Care After the COVID-19 Pandemic

The current COVID-19 pandemic has boosted a sudden demand for telemedicine due to quarantine and travel restrictions. The exponential increase in the use of telemedicine is expected to affect ophthalmology drastically. The aim of this review is to discuss the utility, effectiveness and challenges of teleophthalmological new tools for eyecare delivery as well as its implementation and possible facilitation with artificial intelligence. We used the terms: “teleophthalmology,” “telemedicine and COVID-19,” “retinal diseases and telemedicine,” “virtual ophthalmology,” “cost effectiveness of teleophthalmology,” “pediatric teleophthalmology,” “Artificial intelligence and ophthalmology,” “Glaucoma and teleophthalmology” and “teleophthalmology limitations” in the database of PubMed and selected the articles being published in the course of 2015-2020. After the initial search, 321 articles returned as relevant. A meticulous screening followed and eventually 103 published manuscripts were included and used as our references. Emerging in the market, teleophthalmology is showing great potential for the future of ophthalmological care, benefiting both patients and ophthalmologists in times of pandemics. The spectrum of eye diseases that could benefit from teleophthalmology is wide, including mostly retinal diseases such as diabetic retinopathy, retinopathy of prematurity, age-related macular degeneration but also glaucoma and anterior segment conditions. Simultaneously, artificial intelligence provides ways of implementing teleophthalmology easier and with better outcomes, contributing as significant changing factors for ophthalmology practice after the COVID-19 pandemic.

Fully Automated Colorimetric Analysis of the Optic Nerve Aided by Deep Learning and Its Association with Perimetry and OCT for the Study of Glaucoma

Background: Laguna-ONhE is an application for the colorimetric analysis of optic nerve images, which topographically assesses the cup and the presence of haemoglobin. Its latest version has been fully automated with five deep learning models. In this paper, perimetry in combination with Laguna-ONhE or Cirrus-OCT was evaluated. Methods: The morphology and perfusion estimated by Laguna ONhE were compiled into a “Globin Distribution Function” (GDF). Visual field irregularity was measured with the usual pattern standard deviation (PSD) and the threshold coefficient of variation (TCV), which analyses its harmony without taking into account age-corrected values. In total, 477 normal eyes, 235 confirmed, and 98 suspected glaucoma cases were examined with Cirrus-OCT and different fundus cameras and perimeters. Results: The best Receiver Operating Characteristic (ROC) analysis results for confirmed and suspected glaucoma were obtained with the combination of GDF and TCV (AUC: 0.995 and 0.935, respectively. Sensitivities: 94.5% and 45.9%, respectively, for 99% specificity). The best combination of OCT and perimetry was obtained with the vertical cup/disc ratio and PSD (AUC: 0.988 and 0.847, respectively. Sensitivities: 84.7% and 18.4%, respectively, for 99% specificity). Conclusion: Using Laguna ONhE, morphology, perfusion, and function can be mutually enhanced with the methods described for the purpose of glaucoma assessment, providing early sensitivity.

Progress of artificial intelligence in diabetic retinopathy screening

Diabetic retinopathy (DR) is one of the leading causes of blindness worldwide, and the limited availability of qualified ophthalmologists restricts its early diagnosis. For the past few years, artificial intelligence technology has developed rapidly and has been applied in DR screening. The upcoming technology provides support on DR screening and improves the identification of DR lesions with a high sensitivity and specificity. This review aims to summarize the progress on automatic detection and classification models for the diagnosis of DR.

Classifying Retinal Degeneration in Histological Sections Using Deep Learning

Purpose

Artificial intelligence (AI) techniques are increasingly being used to classify retinal diseases. In this study we investigated the ability of a convolutional neural network (CNN) in categorizing histological images into different classes of retinal degeneration.

Methods

Images were obtained from a chemically induced feline model of monocular retinal dystrophy and split into training and testing sets. The training set was graded for the level of retinal degeneration and used to train various CNN architectures. The testing set was evaluated through the best architecture and graded by six observers. Comparisons between model and observer classifications, and interobserver variability were measured. Finally, the effects of using less training images or images containing half the presentable context were investigated.

Results

The best model gave weighted-F1 scores in the range 85% to 90%. Cohen kappa scores reached up to 0.86, indicating high agreement between the model and observers. Interobserver variability was consistent with the model-observer variability in the model's ability to match predictions with the observers. Image context restriction resulted in model performance reduction by up to 6% and at least one training set size resulted in a model performance reduction of 10% compared to the original size.

Conclusions

Detecting the presence and severity of up to three classes of retinal degeneration in histological data can be reliably achieved with a deep learning classifier.

Translational Relevance

This work lays the foundations for future AI models which could aid in the evaluation of more intricate changes occurring in retinal degeneration, particularly in other types of clinically derived image data.

Detection of Fuchs' Uveitis Syndrome From Slit-Lamp Images Using Deep Convolutional Neural Networks in a Chinese Population

Fuchs' uveitis syndrome (FUS) is one of the most under- or misdiagnosed uveitis entities. Many undiagnosed FUS patients are unnecessarily overtreated with anti-inflammatory drugs, which may lead to serious complications. To offer assistance for ophthalmologists in the screening and diagnosis of FUS, we developed seven deep convolutional neural networks (DCNNs) to detect FUS using slit-lamp images. We also proposed a new optimized model with a mixed "attention" module to improve test accuracy. In the same independent set, we compared the performance between these DCNNs and ophthalmologists in detecting FUS. Seven different network models, including Xception, Resnet50, SE-Resnet50, ResNext50, SE-ResNext50, ST-ResNext50, and SET-ResNext50, were used to predict FUS automatically with the area under the receiver operating characteristic curves (AUCs) that ranged from 0.951 to 0.977. Our proposed SET-ResNext50 model (accuracy = 0.930; Precision = 0.918; Recall = 0.923; F1 measure = 0.920) with an AUC of 0.977 consistently outperformed the other networks and outperformed general ophthalmologists by a large margin. Heat-map visualizations of the SET-ResNext50 were provided to identify the target areas in the slit-lamp images. In conclusion, we confirmed that a trained classification method based on DCNNs achieved high effectiveness in distinguishing FUS from other forms of anterior uveitis. The performance of the DCNNs was better than that of general ophthalmologists and could be of value in the diagnosis of FUS.

Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration

OBJECTIVE

Reticular pseudodrusen (RPD), a key feature of age-related macular degeneration (AMD), are poorly detected by human experts on standard color fundus photography (CFP) and typically require advanced imaging modalities such as fundus autofluorescence (FAF). The objective was to develop and evaluate the performance of a novel multimodal, multitask, multiattention (M3) deep learning framework on RPD detection.

MATERIALS AND METHODS

A deep learning framework (M3) was developed to detect RPD presence accurately using CFP alone, FAF alone, or both, employing >8000 CFP-FAF image pairs obtained prospectively (Age-Related Eye Disease Study 2). The M3 framework includes multimodal (detection from single or multiple image modalities), multitask (training different tasks simultaneously to improve generalizability), and multiattention (improving ensembled feature representation) operation. Performance on RPD detection was compared with state-of-the-art deep learning models and 13 ophthalmologists; performance on detection of 2 other AMD features (geographic atrophy and pigmentary abnormalities) was also evaluated.

RESULTS

For RPD detection, M3 achieved an area under the receiver-operating characteristic curve (AUROC) of 0.832, 0.931, and 0.933 for CFP alone, FAF alone, and both, respectively. M3 performance on CFP was very substantially superior to human retinal specialists (median F1 score = 0.644 vs 0.350). External validation (the Rotterdam Study) demonstrated high accuracy on CFP alone (AUROC, 0.965). The M3 framework also accurately detected geographic atrophy and pigmentary abnormalities (AUROC, 0.909 and 0.912, respectively), demonstrating its generalizability.

CONCLUSIONS

This study demonstrates the successful development, robust evaluation, and external validation of a novel deep learning framework that enables accessible, accurate, and automated AMD diagnosis and prognosis.

Multidisease Deep Learning Neural Network for the Diagnosis of Corneal Diseases

PURPOSE

To report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and keratoconus (KCN) using anterior segment optical coherence tomography (AS-OCT) images.

STUDY DESIGN

Development of a deep learning neural network diagnosis algorithm.

METHODS

A total of 158,220 AS-OCT images from 879 eyes of 478 subjects were used to develop and validate a classification deep network. After a quality check, the network was trained and validated using 134,460 images. We tested the network using a test set of consecutive patients involving 23,760 AS-OCT images of 132 eyes of 69 patients. The area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and F1 score and 95% confidence intervals (CIs) were computed.

RESULTS

The MDDN achieved eye-level AUROCs >0.99 (95% CI: 0.90, 1.0), AUPRCs > 0.96 (95% CI: 0.90, 1.0), and F1 scores > 0.90 (95% CI: 0.81, 1.0) for DES, FED, and KCN, respectively.

CONCLUSIONS

MDDN is a novel diagnostic tool for corneal diseases that can be used to automatically diagnose KCN, FED, and DES using only AS-OCT images.