Femtosecond laser-assisted in situ keratomileusis versus small-incision lenticule extraction: current approach based on evidence.

PURPOSE OF REVIEW: Laser keratorefractive surgery achieves excellent visual outcomes for refractive error correction. With femtosecond laser, small incision lenticule extraction (SMILE) is an increasingly viable alternative to laser-assisted in situ keratomileusis (LASIK). Comparative studies demonstrate similar efficacy and predictability between SMILE and LASIK, making it difficult for clinicians to choose which to use. This review thus compares femtosecond-LASIK (FS-LASK) and SMILE in various scenarios, to assist clinicians in deciding which refractive surgery procedure to recommend. RECENT FINDINGS: SMILE may be superior for highly myopic eyes due to a smaller decrease in functional optical zone. SMILE further induces less spherical aberration and less overall higher order aberrations in mesopic conditions. SMIILE also has less postoperative dry eye, making it suitable those with preexisting dry eye. For low to moderate myopic astigmatism correction, FS-LASIK has less undercorrection compared to SMILE. Lastly, SMILE has not yet received Food and Drug Administration or Conformité Européenne approval for hyperopic correction, rendering FS-LASIK the choice of procedure for hyperopic correction. SUMMARY: Both FS-LASIK and SMILE demonstrate good efficacy and predictability. Understanding specific clinical scenarios where one may be superior to the other will aid clinicians in choosing the most suitable procedure for personalized care.

Recent advances in the use of optical coherence tomography in neuro-ophthalmology: A review.

Optical coherence tomography (OCT) is an in vivo imaging modality that provides non-invasive, high resolution and fast cross-sectional images of the optic nerve head, retina and choroid. OCT angiography (OCTA) is an emerging tool. It is a non-invasive, dye-free imaging approach of visualising the microvasculature of the retina and choroid by employing motion contrast imaging for blood flow detection and is gradually receiving attention for its potential roles in various neuro-ophthalmic and retinal conditions. We will review the clinical utility of the OCT in the management of various common neuro-ophthalmic and neurological disorders. We also review some of the OCTA research findings in these conditions. Finally, we will discuss the limitations of OCT as well as introduce other emerging technologies.

Artificial intelligence enabled smart digital eye wearables.

PURPOSE OF REVIEW: Smart eyewear is a head-worn wearable device that is evolving as the next phase of ubiquitous wearables. Although their applications in healthcare are being explored, they have the potential to revolutionize teleophthalmology care. This review highlights their applications in ophthalmology care and discusses future scope. RECENT FINDINGS: Smart eyewear equips advanced sensors, optical displays, and processing capabilities in a wearable form factor. Rapid technological developments and the integration of artificial intelligence are expanding their reach from consumer space to healthcare applications. This review systematically presents their applications in treating and managing eye-related conditions. This includes remote assessments, real-time monitoring, telehealth consultations, and the facilitation of personalized interventions. They also serve as low-vision assistive devices to help visually impaired, and can aid physicians with operational and surgical tasks. SUMMARY: Wearables such as smart eyewear collects rich, continuous, objective, individual-specific data, which is difficult to obtain in a clinical setting. By leveraging sophisticated data processing and artificial intelligence based algorithms, these data can identify at-risk patients, recognize behavioral patterns, and make timely interventions. They promise cost-effective and personalized treatment for vision impairments in an effort to mitigate the global burden of eye-related conditions and aging.

Explainable artificial intelligence in ophthalmology.

PURPOSE OF REVIEW: Despite the growing scope of artificial intelligence (AI) and deep learning (DL) applications in the field of ophthalmology, most have yet to reach clinical adoption. Beyond model performance metrics, there has been an increasing emphasis on the need for explainability of proposed DL models. RECENT FINDINGS: Several explainable AI (XAI) methods have been proposed, and increasingly applied in ophthalmological DL applications, predominantly in medical imaging analysis tasks. SUMMARY: We summarize an overview of the key concepts, and categorize some examples of commonly employed XAI methods. Specific to ophthalmology, we explore XAI from a clinical perspective, in enhancing end-user trust, assisting clinical management, and uncovering new insights. We finally discuss its limitations and future directions to strengthen XAI for application to clinical practice.

Six-Year Incidence and Risk Factors for Primary Angle-Closure Disease: The Singapore Epidemiology of Eye Diseases Study.

PURPOSE: To determine the incidence and risk factors of primary angle-closure disease (PACD) over 6 years in a multi-ethnic Asian population. DESIGN: Population-based, longitudinal study. PARTICIPANTS: The Singapore Epidemiology of Eye Diseases study is a population-based cohort study conducted among adults aged 40 years or more. The baseline examination was conducted between 2004 and 2010, and the 6-year follow-up visit was conducted between 2011 and 2017. Of 6762 participants who attended the follow-up examination, 5298 at risk for primary angle-closure glaucoma (PACG) and 5060 at risk for PACD were included for analyses. METHODS: Standardized examinations including slit-lamp biomicroscopy, indentation gonioscopy, intraocular pressure (IOP) measurement, and static automated perimetry were performed. In this study, PACD includes primary angle-closure suspect (PACS), primary angle-closure (PAC), and PACG. MAIN OUTCOME MEASURES: The 6-year PACD incidence was evaluated among an at-risk population excluding adults with baseline glaucoma, PACS, PAC, pseudophakia at baseline or follow-up, or laser peripheral iridotomy or iridectomy at baseline visit. Logistic regression analysis adjusting for age, gender, and ethnicity was performed to evaluate associations between PACD development and demographic or ocular characteristics. Forward selection based on the Quasi-likelihood Information Criterion was used in multivariable analysis to reduce potential multicollinearity. RESULTS: The 6-year age-adjusted PACD incidence was 3.50% (95% confidence interval [CI], 2.94-4.16). In multivariable analysis, increasing age per decade (odds ratio [OR], 1.35; 95% CI, 1.15-1.59), higher IOP (OR, 1.04; 95% CI, 1.00-1.08), and shallower anterior chamber depth (OR, 1.11; 95% CI, 1.08-1.14) at baseline were associated with higher odds of PACD, whereas late posterior subcapsular cataract (PSC) (OR, 0.60; 95% CI, 0.48-0.76) was associated with lower odds of PACD. The 6-year age-adjusted incidences of PACG, PAC, and PACS were 0.29% (95% CI, 0.14-0.55), 0.46% (95% CI, 0.29-0.75), and 2.54% (95% CI, 2.07-3.12), respectively. CONCLUSIONS: Our study showed that the 6-year incidence of PACD was 3.50%. Increasing age, higher IOP, and shallower anterior chamber were associated with a higher risk of incident PACD, whereas late PSC was associated with a lower odds of PACD. These findings can aid in future projections and formulation of health care policies for screening of at-risk individuals for timely intervention.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology.

PURPOSE OF REVIEW: The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each. RECENT FINDINGS: Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks. SUMMARY: AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.

Association of Antihypertensive Medication with Retinal Nerve Fiber Layer and Ganglion Cell-Inner Plexiform Layer Thickness.

PURPOSE: To evaluate the association between different classes of antihypertensive medication with retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform layer (GC-IPL) thickness in a nonglaucomatous multiethnic Asian population. DESIGN: Population-based, cross-sectional study. PARTICIPANTS: A total of 9144 eyes for RNFL analysis (2668 Malays, 3554 Indians, and 2922 Chinese) and 8549 eyes for GC-IPL analysis (2460 Malays, 3230 Indians, and 2859 Chinese) aged 44 to 86 years. METHODS: Participants underwent standardized systemic and ocular examinations and interviewer-administered questionnaires for collection of data on medication and other variables. Intraocular pressure (IOP) readings were obtained by Goldmann applanation tonometry before pupil dilation for fundoscopy and OCT imaging. Blood pressure (BP) was measured with an automatic BP monitor. Mean arterial pressure (MAP) was defined as diastolic BP plus 1/3 (systolic BP - diastolic BP). Regression models were used to investigate the association of antihypertensive medication with OCT measurements of RNFL and GC-IPL. MAIN OUTCOME MEASURES: Average and sectoral RNFL and GC-IPL thickness. RESULTS: After adjusting for age, gender, ethnicity, MAP, IOP, body mass index (BMI), and presence of diabetes, we found that participants taking any type of antihypertensive medication (ß = -0.83; 95% confidence interval [CI], -1.46 to -0.02; P = 0.01), specifically angiotensin-converting enzyme inhibitors (ACEIs) (ß = -1.66; 95% CI, -2.57 to -0.75; P < 0.001) or diuretics (ß = -1.38; 95% CI, -2.59 to -0.17; P < 0.05), had thinner average RNFL in comparison with participants who were not receiving antihypertensive treatment. Use of a greater number of antihypertensive medications was significantly associated with thinner average RNFL (P for trend = 0.001). This association was most evident in the inferior RNFL quadrant in participants using ACEIs (ß = -2.44; 95% CI, -3.99 to -0.89; P = 0.002) or diuretics (ß = -2.76; 95% CI, -4.76 to -0.76; P = 0.007). A similar trend was noted in our analysis of macular GC-IPL thickness. CONCLUSIONS: Use of 2 or more antihypertensive medications, ACEI, and diuretics were associated with a loss of structural markers of retinal ganglion cell health in a multiethnic Asian population.

Global Prevalence of Diabetic Retinopathy and Projection of Burden through 2045: Systematic Review and Meta-analysis.

TOPIC: To provide updated estimates on the global prevalence and number of people with diabetic retinopathy (DR) through 2045. CLINICAL RELEVANCE: The International Diabetes Federation (IDF) estimated the global population with diabetes mellitus (DM) to be 463 million in 2019 and 700 million in 2045. Diabetic retinopathy remains a common complication of DM and a leading cause of preventable blindness in the adult working population. METHODS: We conducted a systematic review using PubMed, Medline, Web of Science, and Scopus for population-based studies published up to March 2020. Random effect meta-analysis with logit transformation was performed to estimate global and regional prevalence of DR, vision-threatening DR (VTDR), and clinically significant macular edema (CSME). Projections of DR, VTDR, and CSME burden were based on population data from the IDF Atlas 2019. RESULTS: We included 59 population-based studies. Among individuals with diabetes, global prevalence was 22.27% (95% confidence interval [CI], 19.73%-25.03%) for DR, 6.17% (95% CI, 5.43%-6.98%) for VTDR, and 4.07% (95% CI, 3.42%-4.82%) for CSME. In 2020, the number of adults worldwide with DR, VTDR, and CSME was estimated to be 103.12 million, 28.54 million, and 18.83 million, respectively; by 2045, the numbers are projected to increase to 160.50 million, 44.82 million, and 28.61 million, respectively. Diabetic retinopathy prevalence was highest in Africa (35.90%) and North American and the Caribbean (33.30%) and was lowest in South and Central America (13.37%). In meta-regression models adjusting for habitation type, response rate, study year, and DR diagnostic method, Hispanics (odds ratio [OR], 2.92; 95% CI, 1.22-6.98) and Middle Easterners (OR, 2.44; 95% CI, 1.51-3.94) with diabetes were more likely to have DR compared with Asians. DISCUSSION: The global DR burden is expected to remain high through 2045, disproportionately affecting countries in the Middle East and North Africa and the Western Pacific. These updated estimates may guide DR screening, treatment, and public health care strategies.

Using Uniocular Visual Acuity Substantially Underestimates the Impact of Visual Impairment on Quality of Life Compared with Binocular Visual Acuity.

PURPOSE: Although the impact of vision-related quality of life (VRQoL) is assessed optimally using binocular visual acuity (VA), uniocular VA remains the preferred measurement method in clinic-based and epidemiologic studies. We compared the impact of distance presenting binocular VA and uniocular VA in the better-seeing (better-eye VA) and worse-seeing (worse-eye VA) eye on VRQoL. DESIGN: The Singapore Chinese Eye Study 2 (2015-2017), a population-based, cross-sectional study. PARTICIPANTS: One thousand eight hundred twenty-two individuals (mean age, 66.2 years [standard deviation, 8.9 years]; 51.1% women) were included. METHODS: Presenting uniocular VA and binocular VA were assessed using a logarithm of the minimum angle of resolution number chart at a distance of 4 m under standard lighting by trained and certified study optometrists. Multiple linear regression models were constructed to determine the independent associations between binocular VA, better-eye VA, and worse-eye VA and the outcome (VRQoL), adjusted for potential confounders, including age, gender, socioeconomic status, and presence of comorbidities. In addition, a cluster sandwich estimator was used to determine if any differences in ß estimates between the associations were statistically significant. MAIN OUTCOME MEASURES: Vision-related quality of life was measured using Rasch-transformed scores from the emotional, mobility, and reading domains of the Impact of Visual Impairment (IVI) questionnaire. RESULTS: Although every 2-line increase (worsening) in binocular VA and uniocular VA was associated independently with decrements in emotional, mobility, and reading IVI scores (P < 0.05 for all), the reductions in all VRQoL domains were substantially lower (P < 0.1) when using either the better-eye VA (compared with binocular VA ß-estimates, -27.8%, -19.4%, and -24.2% difference in emotional, mobility, and reading IVI scores, respectively) or worse-eye VA (compared with binocular VA ß estimates, -38.9%, -58.1%, and -57.5% reduction in emotional, mobility, and reading IVI scores, respectively) to quantify vision loss. CONCLUSIONS: Uniocular VA seems to underestimate the impact of vision loss on VRQoL indices compared with binocular VA. Our data suggest that researchers, clinicians, and policy planners should consider using binocular instead of uniocular measures of VA in patient-reported outcome evaluation of vision loss because it may better reflect its impact on VRQoL.

Cybersecurity in the generative artificial intelligence era.

Generative Artificial Intelligence (GenAI) are algorithms capable of generating original content. The ability of GenAI to learn and generate novel outputs alike human cognition has taken the world by storm and ushered in a new era. In this review, we explore the role of GenAI in healthcare, including clinical, operational, and research applications, and delve into the cybersecurity risks of this technology. We discuss risks such as data privacy risks, data poisoning attacks, the propagation of bias, and hallucinations. In this review, we recommend risk mitigation strategies to enhance cybersecurity in GenAI technologies and further explore the use of GenAI as a tool in itself to enhance cybersecurity across the various AI algorithms. GenAI is emerging as a pivotal catalyst across various industries including the healthcare domain. Comprehending the intricacies of this technology and its potential risks will be imperative for us to fully capitalise on the benefits that GenAI can bring.

Clinical performance of automated machine learning: A systematic review.

Introduction: Automated machine learning (autoML) removes technical and technological barriers to building artificial intelligence models. We aimed to summarise the clinical applications of autoML, assess the capabilities of utilised platforms, evaluate the quality of the evidence trialling autoML, and gauge the performance of autoML platforms relative to conventionally developed models, as well as each other. Method: This review adhered to a prospectively registered protocol (PROSPERO identifier CRD42022344427). The Cochrane Library, Embase, MEDLINE and Scopus were searched from inception to 11 July 2022. Two researchers screened abstracts and full texts, extracted data and conducted quality assessment. Disagreement was resolved through discussion and if required, arbitration by a third researcher. Results: There were 26 distinct autoML platforms featured in 82 studies. Brain and lung disease were the most common fields of study of 22 specialties. AutoML exhibited variable performance: area under the receiver operator characteristic curve (AUCROC) 0.35-1.00, F1-score 0.16-0.99, area under the precision-recall curve (AUPRC) 0.51-1.00. AutoML exhibited the highest AUCROC in 75.6% trials; the highest F1-score in 42.3% trials; and the highest AUPRC in 83.3% trials. In autoML platform comparisons, AutoPrognosis and Amazon Rekognition performed strongest with unstructured and structured data, respectively. Quality of reporting was poor, with a median DECIDE-AI score of 14 of 27. Conclusion: A myriad of autoML platforms have been applied in a variety of clinical contexts. The performance of autoML compares well to bespoke computational and clinical benchmarks. Further work is required to improve the quality of validation studies. AutoML may facilitate a transition to data-centric development, and integration with large language models may enable AI to build itself to fulfil user-defined goals.

Six-Year Incidence and Risk Factors for Primary Open-Angle Glaucoma and Ocular Hypertension: The Singapore Epidemiology of Eye Diseases Study.

OBJECTIVE: To determine the incidence and risk factors for primary open-angle glaucoma (POAG) and ocular hypertension (OHT) in a multiethnic Asian population. DESIGN: Population-based cohort study. PARTICIPANTS: The Singapore Epidemiology of Eye Diseases study included 10 033 participants in the baseline examination between 2004 and 2011. Of those, 6762 (response rate = 78.8%) participated in the 6-year follow-up visit between 2011 and 2017. METHODS: Standardized examination and investigations were performed, including slit lamp biomicroscopy, intraocular pressure (IOP) measurement, pachymetry, gonioscopy, optic disc examination and static automated perimetry. Glaucoma was defined according to a combination of clinical evaluation, ocular imaging (fundus photo, visual field, and OCT) and criteria given by International Society of Geographical and Epidemiological Ophthalmology. OHT was defined on the basis of elevated IOP over the upper limit of normal; i.e., 20.4 mmHg, 21.5 mmHg, and 22.6 mmHg for the Chinese, Indian, and Malay cohort respectively, without glaucomatous optic disc change. MAIN OUTCOME MEASURES: Incidence of POAG, OHT, and OHT progression. RESULTS: The overall 6-year age-adjusted incidences of POAG and OHT were 1.31% (95% confidence interval [CI], 1.04-1.62) and 0.47% (95% CI, 0.30-0.70). The rate of progression of baseline OHT to POAG at 6 years was 5.32%. Primary open-angle glaucoma incidence was similar (1.37%) in Chinese and Indians and lower (0.80%) in Malays. Malays had higher incidence (0.79%) of OHT than Indians (0.38%) and Chinese (0.37%). Baseline parameters associated with higher risk of POAG were older age (per decade: odds ratio [OR], 1.90; 95% CI, 1.54-2.35; P < 0.001), higher baseline IOP (per mmHg: OR, 1.20; 95% CI, 1.12-1.29; P < 0.001) and longer axial length (per mm: OR, 1.22; 95% CI, 1.07-1.40, P = 0.004). CONCLUSION: Six-year incidence of POAG was 1.31% in a multiethnic Asian population. Older age, higher IOP, and longer axial length were associated with higher risk of POAG. These findings can help in future projections and guide public healthcare policy decisions for screening at-risk individuals. FINANCIAL DISCLOSURE(S): The authors have no proprietary or commercial interest in any materials discussed in this article.

Federated machine learning in healthcare: A systematic review on clinical applications and technical architecture.

Federated learning (FL) is a distributed machine learning framework that is gaining traction in view of increasing health data privacy protection needs. By conducting a systematic review of FL applications in healthcare, we identify relevant articles in scientific, engineering, and medical journals in English up to August 31st, 2023. Out of a total of 22,693 articles under review, 612 articles are included in the final analysis. The majority of articles are proof-of-concepts studies, and only 5.2% are studies with real-life application of FL. Radiology and internal medicine are the most common specialties involved in FL. FL is robust to a variety of machine learning models and data types, with neural networks and medical imaging being the most common, respectively. We highlight the need to address the barriers to clinical translation and to assess its real-world impact in this new digital data-driven healthcare scene.

Artificial intelligence and digital health in global eye health: opportunities and challenges.

Global eye health is defined as the degree to which vision, ocular health, and function are maximised worldwide, thereby optimising overall wellbeing and quality of life. Improving eye health is a global priority as a key to unlocking human potential by reducing the morbidity burden of disease, increasing productivity, and supporting access to education. Although extraordinary progress fuelled by global eye health initiatives has been made over the last decade, there remain substantial challenges impeding further progress. The accelerated development of digital health and artificial intelligence (AI) applications provides an opportunity to transform eye health, from facilitating and increasing access to eye care to supporting clinical decision making with an objective, data-driven approach. Here, we explore the opportunities and challenges presented by digital health and AI in global eye health and describe how these technologies could be leveraged to improve global eye health. AI, telehealth, and emerging technologies have great potential, but require specific work to overcome barriers to implementation. We suggest that a global digital eye health task force could facilitate coordination of funding, infrastructural development, and democratisation of AI and digital health to drive progress forwards in this domain.

International incidence and temporal trends for rhegmatogenous retinal detachment: A systematic review and meta-analysis.

We set out to estimate the international incidence of rhegmatogenous retinal detachment (RRD) and to evaluate its temporal trend over time. There is a lack of robust estimates on the worldwide incidence and trend for RRD, a major cause of acute vision loss. We conducted a systematic review of RRD incidence. The electronic databases PubMed, Scopus, and Thomson Reuters' Web of Science were searched from inception through 2nd June 2022. Random-effects meta-analysis model with logit transformation was performed to obtain pooled annual incidence estimates of RRD. Pooled analysis was performed to evaluate the temporal trend of RRD incidence of the 20,958 records identified from the database searches; 33 studies from 21 countries were included for analysis (274,836 cases of RRD in 273,977 persons). Three of the 6 global regions as defined by WHO had studies that met the inclusion and exclusion criteria of the study. The annual international incidence of RRD was estimated to be 12.17 (95% confidence interval [CI] 10.51-14.09) per 100,000 population; with an increasing temporal trend of RRD at 5.4 per 100,000 per decade (p 0.001) from 1997 to 2019. Amongst world regions, the RRD incidence was highest in Europe (14.52 [95% CI 11.79 - 17.88] per 100,000 population), followed by Western Pacific (10.55 [95% CI 8.71-12.75] per 100,000 population) and Regions of Americas (8.95 [95% CI 6.73-11.92] per 100,000 population). About one in 10,000 persons develop RRD each year. There is evidence of increasing trend for RRD incidence over time, with possibly doubling of the current incidence rate within the next 2 decades.

Federated and distributed learning applications for electronic health records and structured medical data: a scoping review.

OBJECTIVES: Federated learning (FL) has gained popularity in clinical research in recent years to facilitate privacy-preserving collaboration. Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice. This review examines FL applications on structured medical data, identifies contemporary limitations, and discusses potential innovations. MATERIALS AND METHODS: We searched 5 databases, SCOPUS, MEDLINE, Web of Science, Embase, and CINAHL, to identify articles that applied FL to structured medical data and reported results following the PRISMA guidelines. Each selected publication was evaluated from 3 primary perspectives, including data quality, modeling strategies, and FL frameworks. RESULTS: Out of the 1193 papers screened, 34 met the inclusion criteria, with each article consisting of one or more studies that used FL to handle structured clinical/medical data. Of these, 24 utilized data acquired from electronic health records, with clinical predictions and association studies being the most common clinical research tasks that FL was applied to. Only one article exclusively explored the vertical FL setting, while the remaining 33 explored the horizontal FL setting, with only 14 discussing comparisons between single-site (local) and FL (global) analysis. CONCLUSIONS: The existing FL applications on structured medical data lack sufficient evaluations of clinically meaningful benefits, particularly when compared to single-site analyses. Therefore, it is crucial for future FL applications to prioritize clinical motivations and develop designs and methodologies that can effectively support and aid clinical practice and research.

A translational perspective towards clinical AI fairness.

Artificial intelligence (AI) has demonstrated the ability to extract insights from data, but the fairness of such data-driven insights remains a concern in high-stakes fields. Despite extensive developments, issues of AI fairness in clinical contexts have not been adequately addressed. A fair model is normally expected to perform equally across subgroups defined by sensitive variables (e.g., age, gender/sex, race/ethnicity, socio-economic status, etc.). Various fairness measurements have been developed to detect differences between subgroups as evidence of bias, and bias mitigation methods are designed to reduce the differences detected. This perspective of fairness, however, is misaligned with some key considerations in clinical contexts. The set of sensitive variables used in healthcare applications must be carefully examined for relevance and justified by clear clinical motivations. In addition, clinical AI fairness should closely investigate the ethical implications of fairness measurements (e.g., potential conflicts between group- and individual-level fairness) to select suitable and objective metrics. Generally defining AI fairness as "equality" is not necessarily reasonable in clinical settings, as differences may have clinical justifications and do not indicate biases. Instead, "equity" would be an appropriate objective of clinical AI fairness. Moreover, clinical feedback is essential to developing fair and well-performing AI models, and efforts should be made to actively involve clinicians in the process. The adaptation of AI fairness towards healthcare is not self-evident due to misalignments between technical developments and clinical considerations. Multidisciplinary collaboration between AI researchers, clinicians, and ethicists is necessary to bridge the gap and translate AI fairness into real-life benefits.

Artificial intelligence innovation in healthcare: Relevance of reporting guidelines for clinical translation from bench to bedside.

Artificial intelligence (AI) and digital innovation are transforming healthcare. Technologies such as machine learning in image analysis, natural language processing in medical chatbots and electronic medical record extraction have the potential to improve screening, diagnostics and prognostication, leading to precision medicine and preventive health. However, it is crucial to ensure that AI research is conducted with scientific rigour to facilitate clinical implementation. Therefore, reporting guidelines have been developed to standardise and streamline the development and validation of AI technologies in health. This commentary proposes a structured approach to utilise these reporting guidelines for the translation of promising AI techniques from research and development into clinical translation, and eventual widespread implementation from bench to bedside.

Metaverse and Virtual Health Care in Ophthalmology: Opportunities and Challenges.

ABSTRACT: The outbreak of the coronavirus disease 2019 has further increased the urgent need for digital transformation within the health care settings, with the use of artificial intelligence/deep learning, internet of things, telecommunication network/virtual platform, and blockchain. The recent advent of metaverse, an interconnected online universe, with the synergistic combination of augmented, virtual, and mixed reality described several years ago, presents a new era of immersive and real-time experiences to enhance human-to-human social interaction and connection. In health care and ophthalmology, the creation of virtual environment with three-dimensional (3D) space and avatar, could be particularly useful in patient-fronting platforms (eg, telemedicine platforms), operational uses (eg, meeting organization), digital education (eg, simulated medical and surgical education), diagnostics, and therapeutics. On the other hand, the implementation and adoption of these emerging virtual health care technologies will require multipronged approaches to ensure interoperability with real-world virtual clinical settings, user-friendliness of the technologies and clinical efficiencies while complying to the clinical, health economics, regulatory, and cybersecurity standards. To serve the urgent need, it is important for the eye community to continue to innovate, invent, adapt, and harness the unique abilities of virtual health care technology to provide better eye care worldwide.

Normative profiles of neuroretinal rim area in a multiethnic Asian population: the Singapore Epidemiology of Eye Diseases study.

AIMS: To evaluate the normative profiles for neuroretinal rim area (RA) in a multiethnic Asian population. METHODS: Subjects were recruited from the Singapore Epidemiology of Eye Diseases (2009-2015) study and underwent standardised examinations. RA measurements were performed using Cirrus high-definition optical coherence tomography (Carl Zeiss Meditec). Multivariable linear regression with generalised estimating equation model was used to evaluate the associations between demographic, systemic and ocular factors with RA. RESULTS: A total of 9394 eyes from 5116 subjects (1724 Chinese, 1463 Malay, 1929 Indian) were included in the final analysis. The mean (±SD) of RA was 1.28 (±0.23) mm2 for Chinese, 1.33 (±0.26) mm2 for Malays, and 1.23 (±0.23) mm2 for Indians. The 5th percentile value for RA was 0.94 mm2 for Chinese, 0.96 mm2 for Malay, and 0.89 mm2 for Indian. In multivariable analysis, following adjustment for age, gender, body mass index, diabetes mellitus, hyperlipidaemia, history of cataract surgery, axial length, intraocular pressure (IOP) and disc area, Indian eyes have smaller RA when compared with Malays (ß=-0.074; 95% CI -0.090 to -0.058; p<0.001) and Chinese (ß=-0.035; 95% CI -0.051 to -0.019; p<0.001), respectively. Additionally, older age (per decade, ß=-0.022), male gender (ß=-0.031), longer axial length (per mm, ß=-0.025), spherical equivalent (per negative dioptre, ß=-0.005), higher IOP (per mm Hg, ß=-0.009) were associated with smaller RA (all p≤0.004). CONCLUSION: In this multiethnic population-based study, we observed significantly smaller RA in Indian eyes, compared with Chinese and Malays. This indicates the need of a more refined ethnic-specific RA normative databases among Asians.