Considerations for addressing bias in artificial intelligence for health equity.

Health equity is a primary goal of healthcare stakeholders: patients and their advocacy groups, clinicians, other providers and their professional societies, bioethicists, payors and value based care organizations, regulatory agencies, legislators, and creators of artificial intelligence/machine learning (AI/ML)-enabled medical devices. Lack of equitable access to diagnosis and treatment may be improved through new digital health technologies, especially AI/ML, but these may also exacerbate disparities, depending on how bias is addressed. We propose an expanded Total Product Lifecycle (TPLC) framework for healthcare AI/ML, describing the sources and impacts of undesirable bias in AI/ML systems in each phase, how these can be analyzed using appropriate metrics, and how they can be potentially mitigated. The goal of these "Considerations" is to educate stakeholders on how potential AI/ML bias may impact healthcare outcomes and how to identify and mitigate inequities; to initiate a discussion between stakeholders on these issues, in order to ensure health equity along the expanded AI/ML TPLC framework, and ultimately, better health outcomes for all.

The Definition of Glaucomatous Optic Neuropathy in Artificial Intelligence Research and Clinical Applications.

OBJECTIVE: Although artificial intelligence (AI) models may offer innovative and powerful ways to use the wealth of data generated by diagnostic tools, there are important challenges related to their development and validation. Most notable is the lack of a perfect reference standard for glaucomatous optic neuropathy (GON). Because AI models are trained to predict presence of glaucoma or its progression, they generally rely on a reference standard that is used to train the model and assess its validity. If an improper reference standard is used, the model may be trained to detect or predict something that has little or no clinical value. This article summarizes the issues and discussions related to the definition of GON in AI applications as presented by the Glaucoma Workgroup from the Collaborative Community for Ophthalmic Imaging (CCOI) US Food and Drug Administration Virtual Workshop, on September 3 and 4, 2020, and on January 28, 2022. DESIGN: Review and conference proceedings. SUBJECTS: No human or animal subjects or data therefrom were used in the production of this article. METHODS: A summary of the Workshop was produced with input and approval from all participants. MAIN OUTCOME MEASURES: Consensus position of the CCOI Workgroup on the challenges in defining GON and possible solutions. RESULTS: The Workshop reviewed existing challenges that arise from the use of subjective definitions of GON and highlighted the need for a more objective approach to characterize GON that could facilitate replication and comparability of AI studies and allow for better clinical validation of proposed AI tools. Different tests and combination of parameters for defining a reference standard for GON have been proposed. Different reference standards may need to be considered depending on the scenario in which the AI models are going to be applied, such as community-based or opportunistic screening versus detection or monitoring of glaucoma in tertiary care. CONCLUSIONS: The development and validation of new AI-based diagnostic tests should be based on rigorous methodology with clear determination of how the reference standards for glaucomatous damage are constructed and the settings where the tests are going to be applied. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.

Artificial Intelligence for Glaucoma: Creating and Implementing Artificial Intelligence for Disease Detection and Progression.

On September 3, 2020, the Collaborative Community on Ophthalmic Imaging conducted its first 2-day virtual workshop on the role of artificial intelligence (AI) and related machine learning techniques in the diagnosis and treatment of various ophthalmic conditions. In a session entitled "Artificial Intelligence for Glaucoma," a panel of glaucoma specialists, researchers, industry experts, and patients convened to share current research on the application of AI to commonly used diagnostic modalities, including fundus photography, OCT imaging, standard automated perimetry, and gonioscopy. The conference participants focused on the use of AI as a tool for disease prediction, highlighted its ability to address inequalities, and presented the limitations of and challenges to its clinical application. The panelists' discussion addressed AI and health equities from clinical, societal, and regulatory perspectives.

From Data to Deployment: The Collaborative Community on Ophthalmic Imaging Roadmap for Artificial Intelligence in Age-Related Macular Degeneration.

OBJECTIVE: Health care systems worldwide are challenged to provide adequate care for the 200 million individuals with age-related macular degeneration (AMD). Artificial intelligence (AI) has the potential to make a significant, positive impact on the diagnosis and management of patients with AMD; however, the development of effective AI devices for clinical care faces numerous considerations and challenges, a fact evidenced by a current absence of Food and Drug Administration (FDA)-approved AI devices for AMD. PURPOSE: To delineate the state of AI for AMD, including current data, standards, achievements, and challenges. METHODS: Members of the Collaborative Community on Ophthalmic Imaging Working Group for AI in AMD attended an inaugural meeting on September 7, 2020, to discuss the topic. Subsequently, they undertook a comprehensive review of the medical literature relevant to the topic. Members engaged in meetings and discussion through December 2021 to synthesize the information and arrive at a consensus. RESULTS: Existing infrastructure for robust AI development for AMD includes several large, labeled data sets of color fundus photography and OCT images; however, image data often do not contain the metadata necessary for the development of reliable, valid, and generalizable models. Data sharing for AMD model development is made difficult by restrictions on data privacy and security, although potential solutions are under investigation. Computing resources may be adequate for current applications, but knowledge of machine learning development may be scarce in many clinical ophthalmology settings. Despite these challenges, researchers have produced promising AI models for AMD for screening, diagnosis, prediction, and monitoring. Future goals include defining benchmarks to facilitate regulatory authorization and subsequent clinical setting generalization. CONCLUSIONS: Delivering an FDA-authorized, AI-based device for clinical care in AMD involves numerous considerations, including the identification of an appropriate clinical application; acquisition and development of a large, high-quality data set; development of the AI architecture; training and validation of the model; and functional interactions between the model output and clinical end user. The research efforts undertaken to date represent starting points for the medical devices that eventually will benefit providers, health care systems, and patients.

Foundational Considerations for Artificial Intelligence Using Ophthalmic Images.

IMPORTANCE: The development of artificial intelligence (AI) and other machine diagnostic systems, also known as software as a medical device, and its recent introduction into clinical practice requires a deeply rooted foundation in bioethics for consideration by regulatory agencies and other stakeholders around the globe. OBJECTIVES: To initiate a dialogue on the issues to consider when developing a bioethically sound foundation for AI in medicine, based on images of eye structures, for discussion with all stakeholders. EVIDENCE REVIEW: The scope of the issues and summaries of the discussions under consideration by the Foundational Principles of Ophthalmic Imaging and Algorithmic Interpretation Working Group, as first presented during the Collaborative Community on Ophthalmic Imaging inaugural meeting on September 7, 2020, and afterward in the working group. FINDINGS: Artificial intelligence has the potential to improve health care access and patient outcome fundamentally while decreasing disparities, lowering cost, and enhancing the care team. Nevertheless, substantial concerns exist. Bioethicists, AI algorithm experts, as well as the Food and Drug Administration and other regulatory agencies, industry, patient advocacy groups, clinicians and their professional societies, other provider groups, and payors (i.e., stakeholders) working together in collaborative communities to resolve the fundamental ethical issues of nonmaleficence, autonomy, and equity are essential to attain this potential. Resolution impacts all levels of the design, validation, and implementation of AI in medicine. Design, validation, and implementation of AI warrant meticulous attention. CONCLUSIONS AND RELEVANCE: The development of a bioethically sound foundation may be possible if it is based in the fundamental ethical principles of nonmaleficence, autonomy, and equity for considerations for the design, validation, and implementation for AI systems. Achieving such a foundation will be helpful for continuing successful introduction into medicine before consideration by regulatory agencies. Important improvements in accessibility and quality of health care, decrease in health disparities, and lower cost thereby can be achieved. These considerations should be discussed with all stakeholders and expanded on as a useful initiation of this dialogue.

White Paper on Ophthalmic Imaging for Choroidal Nevus Identification and Transformation into Melanoma.

Purpose: To discuss the evolution of noninvasive diagnostic methods in the identification of choroidal nevus and determination of risk factors for malignant transformation as well as introduce the novel role that artificial intelligence (AI) can play in the diagnostic process. Methods: White paper. Results: Longstanding diagnostic methods to stratify benign choroidal nevus from choroidal melanoma and to further determine the risk for nevus transformation into melanoma have been dependent on recognition of key clinical features by ophthalmic examination. These risk factors have been derived from multiple large cohort research studies over the past several decades and have garnered widespread use throughout the world. More recent publications have applied ocular diagnostic testing (fundus photography, ultrasound examination, autofluorescence, and optical coherence tomography) to identify risk factors for the malignant transformation of choroidal nevus based on multimodal imaging features. The widespread usage of ophthalmic imaging systems to identify and follow choroidal nevus, in conjunction with the characterization of malignant transformation risk factors via diagnostic imaging, presents a novel path to apply AI. Conclusions: AI applied to existing ophthalmic imaging systems could be used for both identification of choroidal nevus and as a tool to aid in earlier detection of transformation to malignant melanoma. Translational Relevance: Advances in AI models applied to ophthalmic imaging systems have the potential to improve patient care, because earlier detection and treatment of melanoma has been proven to improve long-term clinical outcomes.

Study design considerations for sleep-disordered breathing devices.

None: In recent years, sleep-disordered breathing (SDB) has been recognized as a prevalent but under-diagnosed condition in adults and has prompted the need for new and better diagnostic and therapeutic options. To facilitate the development and availability of innovative, safe and effective SDB medical device technologies for patients in the United States, the US Food and Drug Administration collaborated with six SDB-related professional societies and a consumer advocacy organization to convene a public workshop focused on clinical investigations of SDB devices. Sleep medicine experts discussed appropriate definitions of terms used in the diagnosis and treatment of SDB, the use of home sleep testing versus polysomnography, clinical trial design issues in studying SDB devices, and current and future trends in digital health technologies for diagnosis and monitoring SDB. The panel's breadth of clinical expertise and experience across medical specialties provided useful and important insights regarding clinical trial designs for SDB devices.

Evaluating New Ophthalmic Digital Devices for Safety and Effectiveness in the Context of Rapid Technological Development.

IMPORTANCE: The US Food and Drug Administration's medical device regulatory pathway was initially conceived with hardware devices in mind. The emerging market for ophthalmic digital devices necessitates an evolution of this paradigm. OBJECTIVES: To facilitate innovation in ophthalmic digital health with attention to safety and effectiveness. EVIDENCE REVIEW: This article presents a summary of the presentations, discussions, and literature review that occurred during a joint Ophthalmic Digital Health workshop of the American Academy of Ophthalmology, the American Academy of Pediatrics, the American Association for Pediatric Ophthalmology and Strabismus, the American Society of Cataract and Refractive Surgery, the American Society of Retina Specialists, the Byers Eye Institute at Stanford and the US Food and Drug Administration. FINDINGS: Criterion standards and expert graders are critically important in the evaluation of automated systems and telemedicine platforms. Training at all levels is important for the safe and effective operation of digital health devices. The risks associated with automation are substantially increased in rapidly progressive diseases. Cybersecurity and patient privacy warrant meticulous attention. CONCLUSIONS AND RELEVANCE: With appropriate attention to safety and effectiveness, digital health technology could improve screening and treatment of ophthalmic diseases and improve access to care.

Food and Drug Administration, American Academy of Ophthalmology, American Academy of Optometry, American Association for Pediatric Ophthalmology and Strabismus, American Optometric Association, American Society of Cataract and Refractive Surgery, and Contact Lens Association of Ophthalmologists Co-Sponsored Workshop: Controlling the Progression of Myopia: Contact Lenses and Future Medical Devices.

The prevalence of myopia is high and increasing. Approximately 5 billion people around the world are expected to be myopic by the year 2050. Methods to slow the progression of myopia and therefore potentially decrease the associated sight-threatening complications have been the subject of a number of investigations. A workshop, sponsored by the United States Food and Drug Administration (FDA) Center for Devices and Radiological Health, American Academy of Ophthalmology, American Academy of Optometry, American Association for Pediatric Ophthalmology and Strabismus, American Optometric Association, American Society of Cataract and Refractive Surgery, and Contact Lens Association of Ophthalmologists, Inc, convened myopia experts from around the world to discuss principles to consider in the design of clinical trials investigating the effectiveness and safety of myopia control devices. Experts discussed parameters such as study endpoints, duration, enrollment criteria, patient-reported outcomes, recruitment, and retention. The discussions among the experts, FDA, and audience members should help to facilitate the development and evaluation of reasonably safe and effective myopia control devices.

Optimized Protocol for Testing Multipurpose Contact Lens Solution Efficacy Against Acanthamoeba.

OBJECTIVES: To evaluate the interlaboratory and intralaboratory reproducibility of a proposed protocol for multipurpose contact lens solution (MPS) disinfection efficacy against Acanthamoeba. METHODS: Acanthamoeba castellanii and Acanthamoeba polyphaga and four MPS with different biocidal agents were used to evaluate the protocol in two different laboratories. In addition to the negative control, a positive control and neutralization control were used. One experiment was performed in triplicate, and all other experiments were performed in duplicate in each laboratory. Acanthamoeba trophozoites were grown axenically, and cysts were generated using the starvation method. Trophozoites and cysts at a concentration of 2.0 × 10 to 2.0 × 10 organisms per milliliter were exposed to the test MPS for 0, 4 or 6 (manufacturer's recommended soak time [MRST]), 8, and 24 hr. Survivors were determined by a limiting dilution method that used a most probable number evaluation. RESULTS: The positive and negative controls displayed consistent results and trends both within each laboratory and between each laboratory for trophozoites and cysts of both A. castellanii and A. polyphaga. The neutralization control consistently demonstrated the ability of the neutralizing agents to neutralize the MPS and the positive control and demonstrated no inhibition of Acanthamoeba by the negative control. Testing in triplicate and duplicate demonstrated the reproducibility of the protocol both within each laboratory and between the laboratories. Our results demonstrated that the MPS at the MRST and at 8 hr (likely overnight soak time) are generally more effective against trophozoites than they are against cysts. Only the MPS with hydrogen peroxide as the biocidal agent was able to provide a greater than three-log kill of cysts at the MRST and longer. Among the MPS we tested, trophozoites of A. castellanii and A. polyphaga showed similar responses. Some variability was observed when testing cysts of both species. In both laboratories, one nonhydrogen peroxide containing MPS had some effect (>1 log kill) on A. polyphaga cysts. This solution had no effect (<1 log kill) on A. castellanii cysts, A. castellanii trophozoites, and A. polyphaga trophozoites. CONCLUSIONS: The protocol that we have revised and evaluated is a well-controlled and reproducible procedure that can effectively evaluate the efficacy of MPS against Acanthamoeba trophozoites. Some variability was observed when testing the cyst stage.

Assessment of Clinical Trials for Devices Intended to Control Myopia Progression in Children.

The increased prevalence of myopia in the United States and other regions of the world, and the sight-threatening problems associated with higher levels of myopia have led to great interest in research designed to reduce these rates. As most of the progression of myopia occurs in childhood, these investigations have been directed toward slowing the progression of myopia in children. Treatments described to potentially slow the progression of myopia have included pharmacological interventions, multifocal spectacles, and multifocal correction created by contact lenses. Although some contact lens clinical trials have demonstrated promising results in slowing the progression of myopia, many of these studies have significant limitations, including only short follow-up times, limited randomization, and incomplete masking. Such limitations have underscored the need to develop a more robust clinical study design, so that future studies can demonstrate whether contact lenses, as well as other medical devices, can be used in a safe and effective manner to control myopia progression. We review previous key studies and discuss study design and regulatory issues relevant to future clinical trials.