Global disparity bias in ophthalmology artificial intelligence applications

Nakayama, Luis Filipe; Kras, Ashley; Ribeiro, Lucas Zago; Malerbi, Fernando Korn; Mendonça, Luis Salles; Celi, Leo Anthony; Regatieri, Caio V.; Waheed, Nadia K.

doi:10.1136/bmjhci-2021-100470

Cited by 13 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We compared the results with the current state of the art methods in BRSET [74,75], and with the current state of the art foundational model RetFound [32] to predict diabetic retinopathy. The models demonstrated varying degrees of accuracy and F1 scores across different classification tasks (5-class, 3-class, and binary).…”

Section: Resultsmentioning

confidence: 99%

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

Restrepo,

Wu,

Vásquez-Venegas

et al. 2024

Preprint

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

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

Restrepo,

Wu,

Vásquez-Venegas

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Cancer treatment outcomes have been observed due to inappropriate risk assessment and, therefore, inappropriate preventive practices [ 65 ]. In ophthalmology articles, there was an identified lack of representation of various demographic characteristics and pathological entities in publicly available datasets, prompting the need for a collaborative approach to reach real-world deployment [ 15 , 66 , 67 ].…”

Section: Resultsmentioning

confidence: 99%

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

Paik,

Hicklen,

Kaggwa

et al. 2023

PLOS Digit Health

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Incorrect training of ML models can lead to inaccurate results and potentially lead to inadequate care for patients in need [ 8 ]. For instance, the performance of automated DR algorithms varies considerably due to limited training data, heterogeneity in disease presentations, and suboptimal image quality [ 9 , 10 ]. Moreover, ophthalmological ML-ready datasets are only available in a few countries, leaving a large number of countries unrepresented in training and validation cohorts [ 11 ].…”

Section: Resultsmentioning

confidence: 99%

Behind the mask: a critical perspective on the ethical, moral, and legal implications of AI in ophthalmology

Veritti,

Rubinato,

Sarao

et al. 2023

Graefes Arch Clin Exp Ophthalmol

View full text Add to dashboard Cite

Purpose This narrative review aims to provide an overview of the dangers, controversial aspects, and implications of artificial intelligence (AI) use in ophthalmology and other medical-related fields. Methods We conducted a decade-long comprehensive search (January 2013–May 2023) of both academic and grey literature, focusing on the application of AI in ophthalmology and healthcare. This search included key web-based academic databases, non-traditional sources, and targeted searches of specific organizations and institutions. We reviewed and selected documents for relevance to AI, healthcare, ethics, and guidelines, aiming for a critical analysis of ethical, moral, and legal implications of AI in healthcare. Results Six main issues were identified, analyzed, and discussed. These include bias and clinical safety, cybersecurity, health data and AI algorithm ownership, the “black-box” problem, medical liability, and the risk of widening inequality in healthcare. Conclusion Solutions to address these issues include collecting high-quality data of the target population, incorporating stronger security measures, using explainable AI algorithms and ensemble methods, and making AI-based solutions accessible to everyone. With careful oversight and regulation, AI-based systems can be used to supplement physician decision-making and improve patient care and outcomes.

show abstract

Global disparity bias in ophthalmology artificial intelligence applications

Cited by 13 publications

References 11 publications

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

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

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

Behind the mask: a critical perspective on the ethical, moral, and legal implications of AI in ophthalmology

Contact Info

Product

Resources

About