DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era.

In the big data era, integrating diverse data modalities poses significant challenges, particularly in complex fields like healthcare. This paper introduces a new process model for multimodal Data Fusion for Data Mining, integrating embeddings and the Cross-Industry Standard Process for Data Mining with the existing Data Fusion Information Group model. Our model aims to decrease computational costs, complexity, and bias while improving efficiency and reliability. We also propose "disentangled dense fusion," a novel embedding fusion method designed to optimize mutual information and facilitate dense inter-modality feature interaction, thereby minimizing redundant information.We demonstrate the model's efficacy through three use cases: predicting diabetic retinopathy using retinal images and patient metadata, domestic violence prediction employing satellite imagery, internet, and census data, and identifying clinical and demographic features from radiography images and clinical notes. The model achieved a Macro F1 score of 0.92 in diabetic retinopathy prediction, an R-squared of 0.854 and sMAPE of 24.868 in domestic violence prediction, and a macro AUC of 0.92 and 0.99 for disease prediction and sex classification, respectively, in radiological analysis. These results underscore the Data Fusion for Data Mining model's potential to significantly impact multimodal data processing, promoting its adoption in diverse, resource-constrained settings.

Automated machine learning model for fundus image classification by health-care professionals with no coding experience.

To assess the feasibility of code-free deep learning (CFDL) platforms in the prediction of binary outcomes from fundus images in ophthalmology, evaluating two distinct online-based platforms (Google Vertex and Amazon Rekognition), and two distinct datasets. Two publicly available datasets, Messidor-2 and BRSET, were utilized for model development. The Messidor-2 consists of fundus photographs from diabetic patients and the BRSET is a multi-label dataset. The CFDL platforms were used to create deep learning models, with no preprocessing of the images, by a single ophthalmologist without coding expertise. The performance metrics employed to evaluate the models were F1 score, area under curve (AUC), precision and recall. The performance metrics for referable diabetic retinopathy and macular edema were above 0.9 for both tasks and CDFL. The Google Vertex models demonstrated superior performance compared to the Amazon models, with the BRSET dataset achieving the highest accuracy (AUC of 0.994). Multi-classification tasks using only BRSET achieved similar overall performance between platforms, achieving AUC of 0.994 for laterality, 0.942 for age grouping, 0.779 for genetic sex identification, 0.857 for optic, and 0.837 for normality with Google Vertex. The study demonstrates the feasibility of using automated machine learning platforms for predicting binary outcomes from fundus images in ophthalmology. It highlights the high accuracy achieved by the models in some tasks and the potential of CFDL as an entry-friendly platform for ophthalmologists to familiarize themselves with machine learning concepts.

Automated Identification of Different Severity Levels of Diabetic Retinopathy Using a Handheld Fundus Camera and Single-Image Protocol.

Purpose: To evaluate the performance of artificial intelligence (AI) systems embedded in a mobile, handheld retinal camera, with a single retinal image protocol, in detecting both diabetic retinopathy (DR) and more-than-mild diabetic retinopathy (mtmDR). Design: Multicenter cross-sectional diagnostic study, conducted at 3 diabetes care and eye care facilities. Participants: A total of 327 individuals with diabetes mellitus (type 1 or type 2) underwent a retinal imaging protocol enabling expert reading and automated analysis. Methods: Participants underwent fundus photographs using a portable retinal camera (Phelcom Eyer). The captured images were automatically analyzed by deep learning algorithms retinal alteration score (RAS) and diabetic retinopathy alteration score (DRAS), consisting of convolutional neural networks trained on EyePACS data sets and fine-tuned using data sets of portable device fundus images. The ground truth was the classification of DR corresponding to adjudicated expert reading, performed by 3 certified ophthalmologists. Main Outcome Measures: Primary outcome measures included the sensitivity and specificity of the AI system in detecting DR and/or mtmDR using a single-field, macula-centered fundus photograph for each eye, compared with a rigorous clinical reference standard comprising the reading center grading of 2-field imaging protocol using the International Classification of Diabetic Retinopathy severity scale. Results: Of 327 analyzed patients (mean age, 57.0 ± 16.8 years; mean diabetes duration, 16.3 ± 9.7 years), 307 completed the study protocol. Sensitivity and specificity of the AI system were high in detecting any DR with DRAS (sensitivity, 90.48% [95% confidence interval (CI), 84.99%-94.46%]; specificity, 90.65% [95% CI, 84.54%-94.93%]) and mtmDR with the combination of RAS and DRAS (sensitivity, 90.23% [95% CI, 83.87%-94.69%]; specificity, 85.06% [95% CI, 78.88%-90.00%]). The area under the receiver operating characteristic curve was 0.95 for any DR and 0.89 for mtmDR. Conclusions: This study showed a high accuracy for the detection of DR in different levels of severity with a single retinal photo per eye in an all-in-one solution, composed of a portable retinal camera powered by AI. Such a strategy holds great potential for increasing coverage rates of screening programs, contributing to prevention of avoidable blindness. Financial Disclosures: F.K.M. is a medical consultant for Phelcom Technologies. J.A.S. is Chief Executive Officer and proprietary of Phelcom Technologies. D.L. is Chief Technology Officer and proprietary of Phelcom Technologies. P.V.P. is an employee at Phelcom Technologies.

Transition from an in-person to a telemedicine diabetic retinopathy screening program.

PURPOSE: Timely screening and treatment are essential for preventing diabetic retinopathy blindness. Improving screening workflows can reduce waiting times for specialist evaluation and thus enhance patient outcomes. This study assessed different screening approaches in a Brazilian public healthcare setting. METHODS: This retrospective study evaluated a telemedicine-based diabetic retinopathy screening implemented during the COVID-19 pandemic and compared it with in-person strategies. The evaluation was conducted from the perspective of a specialized referral center in an urban area of Central-West Brazil. In the telemedicine approach, a trained technician would capture retinal images by using a handheld camera. These images were sent to specialists for remote evaluation. Patient variables, including age, gender, duration of diabetes diagnosis, diabetes treatment, comorbidities, and waiting time, were analyzed and compared. RESULTS: In total, 437 patients with diabetes mellitus were included in the study (mean age: 62.5 ± 11.0 years, female: 61.7%, mean diabetes duration: 15.3 ± 9.7 years, insulin users: 67.8%). In the in-person assessment group, the average waiting time between primary care referral and specialist evaluation was 292.3 ± 213.9 days, and the referral rate was 73.29%. In the telemedicine group, the average waiting time was 158.8 ± 192.4 days, and the referral rate was 29.38%. The telemedicine approach significantly reduced the waiting time (p<0.001) and significantly lowered the referral rate (p<0.001). CONCLUSION: The telemedicine approach significantly reduced the waiting time for specialist evaluation in a real-world setting. Employing portable retinal cameras may address the burden of diabetic retinopathy, especially in resource-limited settings.

Does diversity beget diversity? A scientometric analysis of over 150,000 studies and 49,000 authors published in high-impact medical journals between 2007 and 2022.

Background: Health research that significantly impacts global clinical practice and policy is often published in high-impact factor (IF) medical journals. These outlets play a pivotal role in the worldwide dissemination of novel medical knowledge. However, researchers identifying as women and those affiliated with institutions in low- and middle-income countries (LMIC) have been largely underrepresented in high-IF journals across multiple fields of medicine. To evaluate disparities in gender and geographical representation among authors who have published in any of five top general medical journals, we conducted scientometric analyses using a large-scale dataset extracted from the New England Journal of Medicine (NEJM), Journal of the American Medical Association (JAMA), The British Medical Journal (BMJ), The Lancet, and Nature Medicine. Methods: Author metadata from all articles published in the selected journals between 2007 and 2022 were collected using the DimensionsAI platform. The Genderize.io API was then utilized to infer each author's likely gender based on their extracted first name. The World Bank country classification was used to map countries associated with researcher affiliations to the LMIC or the high-income country (HIC) category. We characterized the overall gender and country income category representation across the medical journals. In addition, we computed article-level diversity metrics and contrasted their distributions across the journals. Findings: We studied 151,536 authors across 49,764 articles published in five top medical journals, over a long period spanning 15 years. On average, approximately one-third (33.1%) of the authors of a given paper were inferred to be women; this result was consistent across the journals we studied. Further, 86.6% of the teams were exclusively composed of HIC authors; in contrast, only 3.9% were exclusively composed of LMIC authors. The probability of serving as the first or last author was significantly higher if the author was inferred to be a man (18.1% vs 16.8%, P < .01) or was affiliated with an institution in a HIC (16.9% vs 15.5%, P < .01). Our primary finding reveals that having a diverse team promotes further diversity, within the same dimension (i.e., gender or geography) and across dimensions. Notably, papers with at least one woman among the authors were more likely to also involve at least two LMIC authors (11.7% versus 10.4% in baseline, P < .001; based on inferred gender); conversely, papers with at least one LMIC author were more likely to also involve at least two women (49.4% versus 37.6%, P < .001; based on inferred gender). Conclusion: We provide a scientometric framework to assess authorship diversity. Our research suggests that the inclusiveness of high-impact medical journals is limited in terms of both gender and geography. We advocate for medical journals to adopt policies and practices that promote greater diversity and collaborative research. In addition, our findings offer a first step towards understanding the composition of teams conducting medical research globally and an opportunity for individual authors to reflect on their own collaborative research practices and possibilities to cultivate more diverse partnerships in their work.

Ophthalmology Optical Coherence Tomography Databases for Artificial Intelligence Algorithm: A Review.

BACKGROUND: Imaging plays a pivotal role in eye assessment. With the introduction of advanced machine learning and artificial intelligence (AI), the focus has shifted to imaging datasets in ophthalmology. While disparities and health inequalities hidden within data are well-documented, the ophthalmology field faces specific challenges to the creation and maintenance of datasets. Optical Coherence Tomography (OCT) is useful for the diagnosis and monitoring of retinal pathologies, making it valuable for AI applications. This review aims to identify and compare the landscape of publicly available optical coherence tomography databases for AI applications. METHODS: We conducted a literature review on OCT and AI articles with publicly accessible datasets, using PubMed, Scopus, and Web of Science databases. The review retrieved 183 articles, and after full-text analysis, 50 articles were included. From the included articles were identified 8 publicly available OCT datasets, focusing on patient demographics and clinical details for thorough assessment and comparison. RESULTS: The resulting datasets encompass 154,313 images collected from Spectralis, Cirrus HD, Topcon 3D, and Bioptigen devices. These datasets included normal exams, age-related macular degeneration, and diabetic maculopathy, among others. Comprehensive demographic information is available in one dataset and the USA is the most represented population. DISCUSSION: Current publicly available OCT databases for AI applications exhibit limitations, stemming from their non-representative nature and the lack of comprehensive demographic information. Limited datasets hamper research and equitable AI development. To promote equitable AI algorithmic development in ophthalmology, there is a need for the creation and dissemination of more representative datasets.

BRSET: A Brazilian Multilabel Ophthalmological Dataset of Retina Fundus Photos.

Introduction: The Brazilian Multilabel Ophthalmological Dataset (BRSET) addresses the scarcity of publicly available ophthalmological datasets in Latin America. BRSET comprises 16,266 color fundus retinal photos from 8,524 Brazilian patients, aiming to enhance data representativeness, serving as a research and teaching tool. It contains sociodemographic information, enabling investigations into differential model performance across demographic groups. Methods: Data from three São Paulo outpatient centers yielded demographic and medical information from electronic records, including nationality, age, sex, clinical history, insulin use, and duration of diabetes diagnosis. A retinal specialist labeled images for anatomical features (optic disc, blood vessels, macula), quality control (focus, illumination, image field, artifacts), and pathologies (e.g., diabetic retinopathy). Diabetic retinopathy was graded using International Clinic Diabetic Retinopathy and Scottish Diabetic Retinopathy Grading. Validation used Dino V2 Base for feature extraction, with 70% training and 30% testing subsets. Support Vector Machines (SVM) and Logistic Regression (LR) were employed with weighted training. Performance metrics included area under the receiver operating curve (AUC) and Macro F1-score. Results: BRSET comprises 65.1% Canon CR2 and 34.9% Nikon NF5050 images. 61.8% of the patients are female, and the average age is 57.6 years. Diabetic retinopathy affected 15.8% of patients, across a spectrum of disease severity. Anatomically, 20.2% showed abnormal optic discs, 4.9% abnormal blood vessels, and 28.8% abnormal macula. Models were trained on BRSET in three prediction tasks: "diabetes diagnosis"; "sex classification"; and "diabetic retinopathy diagnosis". Discussion: BRSET is the first multilabel ophthalmological dataset in Brazil and Latin America. It provides an opportunity for investigating model biases by evaluating performance across demographic groups. The model performance of three prediction tasks demonstrates the value of the dataset for external validation and for teaching medical computer vision to learners in Latin America using locally relevant data sources.

Image quality assessment of retinal fundus photographs for diabetic retinopathy in the machine learning era: a review.

This study aimed to evaluate the image quality assessment (IQA) and quality criteria employed in publicly available datasets for diabetic retinopathy (DR). A literature search strategy was used to identify relevant datasets, and 20 datasets were included in the analysis. Out of these, 12 datasets mentioned performing IQA, but only eight specified the quality criteria used. The reported quality criteria varied widely across datasets, and accessing the information was often challenging. The findings highlight the importance of IQA for AI model development while emphasizing the need for clear and accessible reporting of IQA information. The study suggests that automated quality assessments can be a valid alternative to manual labeling and emphasizes the importance of establishing quality standards based on population characteristics, clinical use, and research purposes. In conclusion, image quality assessment is important for AI model development; however, strict data quality standards must not limit data sharing. Given the importance of IQA for developing, validating, and implementing deep learning (DL) algorithms, it's recommended that this information be reported in a clear, specific, and accessible way whenever possible. Automated quality assessments are a valid alternative to the traditional manual labeling process, and quality standards should be determined according to population characteristics, clinical use, and research purpose.

An emergency room influx and trauma cases prediction in a Brazilian ophthalmological hospital by an ophthalmologist without code experience / Predição do influxo de atendimentos e casos de trauma em um serviço de urgência oftalmológico brasileiro realizado por um oftalmologista sem experiência em programação

ABSTRACT Purpose: The emergency medical service is a fundamental part of healthcare, albeit crowded emergency rooms lead to delayed and low-quality assistance in actual urgent cases. Machine-learning algorithms can provide a smart and effective estimation of emergency patients' volume, which was previously restricted to artificial intelligence (AI) experts in coding and computer science but is now feasible by anyone without any coding experience through auto machine learning. This study aimed to create a machine-learning model designed by an ophthalmologist without any coding experience using AutoML to predict the influx in the emergency department and trauma cases. Methods: A dataset of 356,611 visits at Hospital da Universidade Federal de São Paulo from January 01, 2014 to December 31, 2019 was included in the model training, which included visits/day and the international classification disease code. The training and prediction were made with the Amazon Forecast by 2 ophthalmologists with no prior coding experience. Results: The forecast period predicted a mean emergency patient volume of 216.27/day in p90, 180.75/day in p50, and 140.35/day in p10, and a mean of 7.42 trauma cases/ day in p90, 3.99/day in p50, and 0.56/day in p10. In January of 2020, there were a total of 6,604 patient visits and a mean of 206.37 patients/day, which is 13.5% less than the p50 prediction. This period involved a total of 199 trauma cases and a mean of 6.21 cases/day, which is 55.77% more traumas than that by the p50 prediction. Conclusions: The development of models was previously restricted to data scientists' experts in coding and computer science, but transfer learning autoML has enabled AI development by any person with no code experience mandatory. This study model showed a close value to the actual 2020 January visits, and the only factors that may have influenced the results between the two approaches are holidays and dataset size. This is the first study to apply AutoML in hospital visits forecast, showing a close prediction of the actual hospital influx.

RESUMO Objetivo: Esse estudo tem como objetivo criar um modelo de Machine Learning por um oftalmologista sem experiência em programação utilizando auto Machine Learning predizendo influxo de pacientes em serviço de emergência e casos de trauma. Métodos: Um dataset de 366,610 visitas em Hospital Universitário da Universidade Federal de São Paulo de 01 de janeiro de 2014 até 31 de dezembro de 2019 foi incluído no treinamento do modelo, incluindo visitas/dia e código internacional de doenças. O treinamento e predição foram realizados com o Amazon Forecast por dois oftalmologistas sem experiência com programação. Resultados: O período de previsão estimou um volume de 206,37 pacientes/dia em p90, 180,75 em p50, 140,35 em p10 e média de 7,42 casos de trauma/dia em p90, 3,99 em p50 e 0,56 em p10. Janeiro de 2020 teve um total de 6.604 pacientes e média de 206,37 pacientes/dia, 13,5% menos do que a predição em p50. O período teve um total de 199 casos de trauma e média de 6,21 casos/dia, 55,77% mais casos do que a predição em p50. Conclusão: O desenvolvimento de modelos era restrito a cientistas de dados com experiencia em programação, porém a transferência de ensino com a tecnologia de auto Machine Learning permite o desenvolvimento de algoritmos por qualquer pessoa sem experiencia em programação. Esse estudo mostra um modelo com valores preditos próximos ao que ocorreram em janeiro de 2020. Fatores que podem ter influenciados no resultado foram feriados e tamanho do banco de dados. Esse é o primeiro estudo que aplicada auto Machine Learning em predição de visitas hospitalares com resultados próximos aos que ocorreram.

A scoping review of the landscape of health-related open datasets in Latin America.

Artificial intelligence (AI) algorithms have the potential to revolutionize healthcare, but their successful translation into clinical practice has been limited. One crucial factor is the data used to train these algorithms, which must be representative of the population. However, most healthcare databases are derived from high-income countries, leading to non-representative models and potentially exacerbating health inequities. This review focuses on the landscape of health-related open datasets in Latin America, aiming to identify existing datasets, examine data-sharing frameworks, techniques, platforms, and formats, and identify best practices in Latin America. The review found 61 datasets from 23 countries, with the DATASUS dataset from Brazil contributing to the majority of articles. The analysis revealed a dearth of datasets created by the authors themselves, indicating a reliance on existing open datasets. The findings underscore the importance of promoting open data in Latin America. We provide recommendations for enhancing data sharing in the region.

Disparity dashboards: an evaluation of the literature and framework for health equity improvement.

The growing recognition of differences in health outcomes across populations has led to a slow but increasing shift towards transparent reporting of patient outcomes. In addition, pay-for-equity initiatives, such as those proposed by the Centers for Medicare and Medicaid, will require the reporting of health outcomes across subgroups over time. Dashboards offer one means of visualising data in the health-care context that can highlight essential disparities in clinical outcomes, guide targeted quality-improvement efforts, and ultimately improve health equity. In this Viewpoint, we evaluate all studies that have reported the successful development of a disparity dashboard and share the data collected and unintended consequences reported. We propose a framework for systematic equality improvement through incentivisation of the collecting and reporting of health data and through implementation of reward systems to reduce health disparities.

BOLD: Blood-gas and Oximetry Linked Dataset - Open Source Research.

Pulse oximeters measure peripheral arterial oxygen saturation (SpO 2 ) noninvasively, while the gold standard (SaO 2 ) involves arterial blood gas measurement. There are known racial and ethnic disparities in their performance. BOLD is a new comprehensive dataset that aims to underscore the importance of addressing biases in pulse oximetry accuracy, which disproportionately affect darker-skinned patients. The dataset was created by harmonizing three Electronic Health Record databases (MIMIC-III, MIMIC-IV, eICU-CRD) comprising Intensive Care Unit stays of US patients. Paired SpO 2 and SaO 2 measurements were time-aligned and combined with various other sociodemographic and parameters to provide a detailed representation of each patient. BOLD includes 49,099 paired measurements, within a 5-minute window and with oxygen saturation levels between 70-100%. Minority racial and ethnic groups account for ∼25% of the data - a proportion seldom achieved in previous studies. The codebase is publicly available. Given the prevalent use of pulse oximeters in the hospital and at home, we hope that BOLD will be leveraged to develop debiasing algorithms that can result in more equitable healthcare solutions.

Digital Determinants of Health: Health data poverty amplifies existing health disparities-A scoping review.

Artificial intelligence (AI) and machine learning (ML) have an immense potential to transform healthcare as already demonstrated in various medical specialties. This scoping review focuses on the factors that influence health data poverty, by conducting a literature review, analysis, and appraisal of results. Health data poverty is often an unseen factor which leads to perpetuating or exacerbating health disparities. Improvements or failures in addressing health data poverty will directly impact the effectiveness of AI/ML systems. The potential causes are complex and may enter anywhere along the development process. The initial results highlighted studies with common themes of health disparities (72%), AL/ML bias (28%) and biases in input data (18%). To properly evaluate disparities that exist we recommend a strengthened effort to generate unbiased equitable data, improved understanding of the limitations of AI/ML tools, and rigorous regulation with continuous monitoring of the clinical outcomes of deployed tools.

Performance of ChatGPT-4 in answering questions from the Brazilian National Examination for Medical Degree Revalidation.

OBJECTIVE: The aim of this study was to evaluate the performance of ChatGPT-4.0 in answering the 2022 Brazilian National Examination for Medical Degree Revalidation (Revalida) and as a tool to provide feedback on the quality of the examination. METHODS: A total of two independent physicians entered all examination questions into ChatGPT-4.0. After comparing the outputs with the test solutions, they classified the large language model answers as adequate, inadequate, or indeterminate. In cases of disagreement, they adjudicated and achieved a consensus decision on the ChatGPT accuracy. The performance across medical themes and nullified questions was compared using chi-square statistical analysis. RESULTS: In the Revalida examination, ChatGPT-4.0 answered 71 (87.7%) questions correctly and 10 (12.3%) incorrectly. There was no statistically significant difference in the proportions of correct answers among different medical themes (p=0.4886). The artificial intelligence model had a lower accuracy of 71.4% in nullified questions, with no statistical difference (p=0.241) between non-nullified and nullified groups. CONCLUSION: ChatGPT-4.0 showed satisfactory performance for the 2022 Brazilian National Examination for Medical Degree Revalidation. The large language model exhibited worse performance on subjective questions and public healthcare themes. The results of this study suggested that the overall quality of the Revalida examination questions is satisfactory and corroborates the nullified questions.

Bacterial endophthalmitis following anti-VEGF intravitreal injections: a retrospective case series.

BACKGROUND: To describe the incidence of endophthalmitis and the treatment outcomes of acute bacterial endophthalmitis following intravitreal anti-vascular endothelial growth factor (anti-VEGF) injections in a Brazilian hospital. The analysis was based on the timing of infection after intravitreal injection, culture results, visual acuity, and the presence of epiretinal membrane after a 1-year follow-up period, spanning nine years. METHODS: This retrospective case series, conducted over a 9-year period, aimed to evaluate the treatment outcomes of acute endophthalmitis following intravitreal Bevacizumab injections. The inclusion criteria involved a chart review of 25 patients who presented clinical signs of acute endophthalmitis out of a total of 12,441 injections administered between January 2011 and December 2019. Negative culture results of vitreous samples or incomplete data were excluded. Ultimately, 23 patients were enrolled in the study. Eight patients were treated with intravitreal antibiotic injections (IVAI) using vancomycin 1.0 mg/0.05mL and ceftazidime 2.25 mg/0.05mL, while 15 patients underwent pars plana vitrectomy (PPV) followed by intravitreal antibiotic injections at the end of surgery (IVAIES). The main outcome measures were the efficacy of controlling the infection with IVAI as a standalone therapy compared to early PPV followed by IVAIES. Data collected included pre-infection and one-year post-treatment best corrected visual acuity (BCVA), optical coherence tomography (OCT) abnormalities, and enucleation/evisceration rates. To compare groups, Mann-Whitney and ANOVA tests were employed for statistical analysis. RESULTS: The incidence rate of bacterial endophthalmitis was 0.185% (1/541 anti-VEGF injections), with the highest infection rates observed in 2014 and 2017. Patients presented clinical symptoms between 2 and 7 days after injection. The most common isolated organisms were coagulase-negative Staphylococci and Streptococci spp. Treatment outcomes showed that both IVAI and PPV + IVAIES effectively controlled the infection and prevented globe atrophy. After one year, the PPV group with BCVA better than Light Perception had a significantly better BCVA compared to the IVAI group (p 0.003). However, PPV group had higher incidence of epiretinal membranes formation compared to the IVAI group. (P 0.035) CONCLUSION: Anti-VEGF injections carry a risk of developing acute bacterial endophthalmitis. Isolated antibiotic therapy could be an effective treatment to control the infection, but performing PPV + IVAIES as a primary treatment showed promising results in terms of improving BCVA after one year, despite a higher rate of epiretinal membrane formation. Further studies are needed to confirm these findings.

Artificial intelligence for telemedicine diabetic retinopathy screening: a review.

PURPOSE: This study aims to compare artificial intelligence (AI) systems applied in diabetic retinopathy (DR) teleophthalmology screening, currently deployed systems, fairness initiatives and the challenges for implementation. METHODS: The review included articles retrieved from PubMed/Medline/EMBASE literature search strategy regarding telemedicine, DR and AI. The screening criteria included human articles in English, Portuguese or Spanish and related to telemedicine and AI for DR screening. The author's affiliations and the study's population income group were classified according to the World Bank Country and Lending Groups. RESULTS: The literature search yielded a total of 132 articles, and nine were included after full-text assessment. The selected articles were published between 2004 and 2020 and were grouped as telemedicine systems, algorithms, economic analysis and image quality assessment. Four telemedicine systems that perform a quality assessment, image preprocessing and pathological screening were reviewed. A data and post-deployment bias assessment are not performed in any of the algorithms, and none of the studies evaluate the social impact implementations. There is a lack of representativeness in the reviewed articles, with most authors and target populations from high-income countries and no low-income country representation. CONCLUSIONS: Telemedicine and AI hold great promise for augmenting decision-making in medical care, expanding patient access and enhancing cost-effectiveness. Economic studies and social science analysis are crucial to support the implementation of AI in teleophthalmology screening programs. Promoting fairness and generalizability in automated systems combined with telemedicine screening programs is not straightforward. Improving data representativeness, reducing biases and promoting equity in deployment and post-deployment studies are all critical steps in model development.

Fairness and generalizability of OCT normative databases: a comparative analysis.

PURPOSE: In supervised Machine Learning algorithms, labels and reports are important in model development. To provide a normality assessment, the OCT has an in-built normative database that provides a color base scale from the measurement database comparison. This article aims to evaluate and compare normative databases of different OCT machines, analyzing patient demographic, contrast inclusion and exclusion criteria, diversity index, and statistical approach to assess their fairness and generalizability. METHODS: Data were retrieved from Cirrus, Avanti, Spectralis, and Triton's FDA-approval and equipment manual. The following variables were compared: number of eyes and patients, inclusion and exclusion criteria, statistical approach, sex, race and ethnicity, age, participant country, and diversity index. RESULTS: Avanti OCT has the largest normative database (640 eyes). In every database, the inclusion and exclusion criteria were similar, including adult patients and excluding pathological eyes. Spectralis has the largest White (79.7%) proportionately representation, Cirrus has the largest Asian (24%), and Triton has the largest Black (22%) patient representation. In all databases, the statistical analysis applied was Regression models. The sex diversity index is similar in all datasets, and comparable to the ten most populous contries. Avanti dataset has the highest diversity index in terms of race, followed by Cirrus, Triton, and Spectralis. CONCLUSION: In all analyzed databases, the data framework is static, with limited upgrade options and lacking normative databases for new modules. As a result, caution in OCT normality interpretation is warranted. To address these limitations, there is a need for more diverse, representative, and open-access datasets that take into account patient demographics, especially considering the development of supervised Machine Learning algorithms in healthcare.

Fairness and generalisability in deep learning of retinopathy of prematurity screening algorithms: a literature review.

BACKGROUND: Retinopathy of prematurity (ROP) is a vasoproliferative disease responsible for more than 30 000 blind children worldwide. Its diagnosis and treatment are challenging due to the lack of specialists, divergent diagnostic concordance and variation in classification standards. While artificial intelligence (AI) can address the shortage of professionals and provide more cost-effective management, its development needs fairness, generalisability and bias controls prior to deployment to avoid producing harmful unpredictable results. This review aims to compare AI and ROP study's characteristics, fairness and generalisability efforts. METHODS: Our review yielded 220 articles, of which 18 were included after full-text assessment. The articles were classified into ROP severity grading, plus detection, detecting treatment requiring, ROP prediction and detection of retinal zones. RESULTS: All the article's authors and included patients are from middle-income and high-income countries, with no low-income countries, South America, Australia and Africa Continents representation.Code is available in two articles and in one on request, while data are not available in any article. 88.9% of the studies use the same retinal camera. In two articles, patients' sex was described, but none applied a bias control in their models. CONCLUSION: The reviewed articles included 180 228 images and reported good metrics, but fairness, generalisability and bias control remained limited. Reproducibility is also a critical limitation, with few articles sharing codes and none sharing data. Fair and generalisable ROP and AI studies are needed that include diverse datasets, data and code sharing, collaborative research, and bias control to avoid unpredictable and harmful deployments.

The Digital Divide in Brazil and Barriers to Telehealth and Equal Digital Health Care: Analysis of Internet Access Using Publicly Available Data.

BACKGROUND: The COVID-19 pandemic has increased the use of digital solutions in medical care, especially for patients in remote areas and those requiring regular medical care. However, internet access is essential for the implementation of digital health care. The digital divide is the unequal distribution of access to digital technology, and the first level digital divide encompasses structural barriers. Brazil, a country with economic inequality and uneven population distribution, faces challenges in achieving internet access for all. OBJECTIVE: This study aims to provide a comprehensive overview of the first-level digital divide in Brazil, estimate the relationship between variables, and identify the challenges and opportunities for digital health care implementation. METHODS: Data were retrieved from the Brazilian Institute of Geography and Statistics National Continuous House survey database, including demographic, health, and internet-related variables. Statistical analysis included 2-tailed t tests, chi-square, and multivariate logistic regression to assess associations between variables. RESULTS: Our analysis included 279,382 interviews throughout Brazil. The sample included more houses from the northeast (n=99,553) and fewer houses from the central west (n=30,804). A total of 223,386 (80.13%) of the interviewed population used the internet, with urban areas having higher internet access (187,671/212,109, 88.48%) than rural areas (35,715/67,077, 53.24%). Among the internet users, those interviewed who lived in urban houses, were women, were younger, and had higher income had a statistically higher prevalence (P<.001). Cell phones were the most common device used to access the internet (141,874/143,836, 98.63%). Reasons for not using the internet included lack of interest, knowledge, availability, and cost, with regional variations. The prevalence of internet access also varied among races, with 84,747 of 98,968 (85.63%) White respondents having access, compared to 22,234 of 28,272 (78.64%) Black respondents, 113,518 of 148,191 (76.6%) multiracial respondents, and 2887 of 3755 (76.88%) other respondents. In the southeast, central west, and south regions, the numbers of people with internet access were 49,790 of 56,298 (88.44%), 27,209 of 30,782 (88.39%), and 27,035 of 31,226 (86.58%), respectively, and in the north and northeast, 45,038 of 61,404 (73.35%) and 74,314 of 99,476 (74.7%). The income of internet users was twice the income of internet nonusers. Among those with diabetes-related limitations in daily activities, 945 of 2377 (39.75%) did not have internet access, and among those with daily activity restrictions, 1381 of 3644 (37.89%) did not have access. In a multivariate logistic regression analysis, women (odds ratio [OR] 1.147, 95% CI 0.118-0.156; P<.001), urban households (OR 6.743, 95% CI 1.888-1.929; P<.001), and those earning more than the minimum wage (OR 2.087, 95% CI 0.716-0.756; P<.01) had a positive association with internet access. CONCLUSIONS: Brazil's diverse regions have different demographic distributions, house characteristics, and internet access levels, requiring targeted measures to address the first-level digital divide in rural areas and reduce inequalities in digital health solutions. Older people, poor, and rural populations face the greatest challenges in the first level digital divide in Brazil, highlighting the need to tackle the digital divide in order to promote equitable access to digital health care.

Sociodemographic disparities in ophthalmological clinical trials.

INTRODUCTION: In ophthalmology, clinical trials (CTs) guide the treatment of diseases such as diabetic retinopathy, myopia, age-related macular degeneration, glaucoma and keratoconus with distinct presentations, pathological characteristics and responses to treatment in minority populations.Reporting gender and race and ethnicity in healthcare studies is currently recommended by National Institutes of Health (NIH) and Food and Drug Administration (FDA) guidelines to ensure representativeness and generalisability; however, CT results that include this information have been limited in the past 30 years.The objective of this review is to analyse the sociodemographic disparities in ophthalmological phases III and IV CT based on publicly available data. METHODS: This study included phases III and IV complete ophthalmological CT available from clinicaltrials.org, and describes the country distribution, race and ethnicity description and gender, and funding characteristics. RESULTS: After a screening process, we included 654 CTs, with findings that corroborate the previous CT reviews' findings that most ophthalmological participants are white and from high-income countries. A description of race and ethnicity is reported in 37.1% of studies but less frequently included within the most studied ophthalmological specialty area (cornea, retina, glaucoma and cataracts). The incidence of race and ethnicity reporting has improved during the past 7 years. DISCUSSION: Although NIH and FDA promote guidelines to improve generalisability in healthcare studies, the inclusion of race and ethnicity in publications and diverse participants in ophthalmological CT is still limited. Actions from the research community and related stakeholders are necessary to increase representativeness and guarantee generalisability in ophthalmological research results to optimise care and reduce related healthcare disparities.