Categories
How to Cite
Copyright notice
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Erin Robinson, Giovanna Guidoboni, Alice Verticchio Vercellin, Ryan Zukerman, James Keller, Brent Siesky, Alon Harris
Keywords
Abstract
Purpose: The purpose of this pilot study was to explore the current understanding and application of artificial intelligence (AI) within clinical ophthalmology.
Design: This study used a qualitative research approach. One-on-one interviews were conducted with ophthalmologists (including residents/fellows/students) and medical professionals involved in ophthalmology.
Methods: Participants were recruited via professional networks, and an interview guide informed by prior research and expertise of the interdisciplinary research team led the question-asking process. Transcribed interviews were analyzed using qualitative thematic analysis methods with Nvivo12 software.
Results: Participants (N = 18) included attending clinicians (44%, n = 8), residents (44%, n = 8), a fellow (6%, n = 1), and a medical student (6%, n = 1). In-depth analysis of the interviews yielded 3 overarching themes: 1) AI has high utility in ophthalmology; 2) AI is a tool, but a balance between AI and the clinician is important; and 3) several challenges to integrating and accessing AI need to be addressed. Overall, participants believed an AI informed clinical practice is important and participants described ways AI could be incorporated into their own patient management. However, the majority of participants do not presently use AI in patient care, noting concerns about the current state of AI in research and clinical practice. Participants also described balance between AI and the provider as essential, suggesting AI applications are not currently able to replace the human element of clinical practice. AI applications in ophthalmic clinical practice are viewed positively across all participants, with noted caution towards the current ability to use AI as an automated tool and challenges for its integration into clinical management.
Conclusions and future perspectives: Although findings yielded generally favorable views, suggesting high potential for benefit with integration of AI systems, several barriers to adoption were noted by participants. While participants believe AI is the future of ophthalmology, a balance between the clinician and the computer is vital and concerns related to trustworthiness of the data were a consistent finding. This research lays important groundwork for developing future research that can bridge the gap between the development of AI systems and its translation to more effective clinical practice.
References
Malik P, Pathania M, Rathaur VK. Overview of artificial intelligence in medicine. J Fam Med Prim Care. 2019;8(7):2328–31. https://doi.org/10.4103/jfmpc.jfmpc_440_19
Wang L, Zhang Y, Wang D, et al. Artificial intelligence for COVID-19: a systematic review. Front Med (Lausanne). 2021;8:745719. https://doi.org/10.3389/fmed.2021.704256
Hogarty DT, Mackey DA, Hewitt AW. Current state and future prospects of artificial intelligence in ophthalmology: a review. Clin Exp Ophthalmol. 2019;47(1):128–39. https://doi.org/10.1111/ceo.13381
Nunez R, Harris A, Ibrahim O, et al. Artificial intelligence to aid glaucoma diagnosis and monitoring: state of the art and new directions. Photonics. 2022;9(11):810. https://doi.org/10.3390/photonics9110810
Ahn JM, Kim S, Ahn KS, Cho SH, Lee KB, Kim US. A deep learning model for the detection of both advanced and early glaucoma using fundus photography. PLoS One. 2018;13(11):e0207982. https://doi.org/10.1371/journal.pone.0207982
Wang M, Tichelaar J, Pasquale LR, et al. Characterization of central visual field loss in end-stage glaucoma by unsupervised artificial intelligence. JAMA Ophthalmol. 2020;138(2):190–8. https://doi.org/10.1001/jamaophthalmol.2019.5413
Medeiros FA, Jammal AA, Thompson AC. From machine to machine: an OCT-trained deep learning algorithm for objective quantification of glaucomatous damage in fundus photographs. Ophthalmology. 2019;126(4):513–21. https://doi.org/10.1016/j.ophtha.2018.12.033
Harris A, Guidoboni G, Siesky B, et al. Ocular blood flow as a clinical observation: value, limitations and data analysis. Prog Retin Eye Res. 2020;78:100841. https://doi.org/10.1016/j.preteyeres.2020.100841
Scheetz J, Rothschild P, McGuinness M, et al. A survey of clinicians on the use of artificial intelligence in ophthalmology, dermatology, radiology and radiation oncology. Sci Rep. 2021;11:5193. https://doi.org/10.1038/s41598-021-84698-5
Hennink M, Kaiser BN. Sample sizes for saturation in qualitative research: a systematic review of empirical tests. Soc Sci Med. 2022;292:114523. https://doi.org/10.1016/j.socscimed.2021.114523
Creswell JW. Educational research: planning, conducting, and evaluating quantitative and qualitative research. 5th ed. Boston: Pearson Higher Ed; 2015.
Marshall B, Cardon P, Poddar A, Fontenot R. Does sample size matter in qualitative research? A review of qualitative interviews in IS research. J Comput Inf Syst. 2013;54(1):11–22. https://doi.org/10.1080/08874417.2013.11645667
Guest G, Namey E, Chen M. A simple method to assess and report thematic saturation in qualitative research. PLoS One. 2020;15(5):e0232076. https://doi.org/10.1371/journal.pone.0232076
Guest G, Bunce A, Johnson L. How many interviews are enough? An experiment with data saturation and variability. Field Methods. 2006;18(1):59–82. https://doi.org/10.1177/1525822X05279903
Saldaña J. The coding manual for qualitative researchers. 4th ed. London: SAGE; 2021.
Guest G, MacQueen KM, Namey EE. Applied thematic analysis. Thousand Oaks: SAGE; 2012.
Gunasekeran DV, Zheng F, Lim GY, Chong CC, Zhang S, Ng WY, et al. Acceptance and perception of artificial intelligence usability in eye care (APPRAISE) for ophthalmologists: a multinational perspective. Front Med (Lausanne). 2022;9:875242. https://doi.org/10.3389/fmed.2022.875242
National Artificial Intelligence Office. Advancing trustworthy AI [Internet]. Washington (DC): US Government; 2023 [cited 2023 Feb 26]. Available from: https://www.ai.gov/strategic-pillars/advancing-trustworthy-ai/
European Commission. High-level expert group on artificial intelligence [online]. 2023. [Accessed 26 Feb 2023] Available from: https://digital-strategy.ec.europa.eu/en/policies/expert-group-ai
Siesky B, Harris A, Vercellin ACV, Guidoboni G, Tsai JC. Ocular blood flow as it relates to race and disease on glaucoma. Adv Ophthalmol Optom. 2021 Aug;6:245-262. https://doi.org/10.1016/j.yaoo.2021.04.016
Siesky B, Harris A, Verticchio Vercellin A, et al. Heterogeneity of Ocular Hemodynamic Biomarkers among Open Angle Glaucoma Patients of African and European Descent. J Clin Med. 2023 Feb 6;12(4):1287. https://doi.org/10.3390/jcm12041287