The Utility of a Smartphone-Based Retinal Imaging Device as a Screening Tool in an Outpatient Clinic Setting: Protocol for an Observational Study
Bibliographic record
Abstract
BACKGROUND: Glaucoma, a disease leading to the degeneration of retinal ganglion cells, results in changes to the optic nerve head that are often diagnosed late when visual problems arise. With the prevalence of glaucoma surpassing 76 million adults worldwide and with glaucoma being the leading cause of irreversible blindness in the world, the early detection and management of glaucoma is imperative. Digital ophthalmoscopes, such as the D-EYE (D-EYE, Srl), have emerged as a technology that uses smartphone cameras with an attachment on the lens to visualize the retina and optic nerve head without the need for dilation. The purpose of this pilot study is to examine the acceptability and feasibility of a D-EYE digital ophthalmoscope to screen for ocular pathology involving the optic nerve, particularly glaucoma. OBJECTIVE: This study aimed to demonstrate the effect of a smartphone-based ophthalmoscope as a potential vision screening tool for optic nerve head pathology in participants enrolled in this study. The first specific aim was to determine the ability of the D-EYE smartphone ophthalmoscope to gather high-quality imaging to be used for grading the fundus into low- and high-risk categories for eye pathology. The second specific aim was to determine the difference in the quality of data capture between still retinal images and 30-second retinal video recordings produced by D-EYE smartphone ophthalmoscopes. METHODS: This observational pilot study enrolled 110 patients receiving routine eye care at the University of Florida Health from February 2019 to February 2022 to assess the use of the D-EYE device in capturing still images and 30-second videos of the bilateral retina and optic nerves of each participant. Study participants completed a survey to gather demographics and past medical history data with a particular focus on previous eye health history. Images were reviewed by 5 ophthalmology residents with interrater reliability analysis performed to assess findings. RESULTS: Ophthalmology resident review indicated greater visualizability and clarity of the bilateral retina and optic nerves with 30-second videos of retinal imaging compared with still-image ophthalmic capture. Furthermore, an increase in visualizability and clarity allowed for a more accurate measurement of the cup-to-disc ratio, a diagnostic marker for glaucoma. In addition, the likelihood of referral of the glaucomatous and healthy sample groups to ophthalmologists indicated a greater sensitivity of digital ophthalmoscopes in being able to detect retinal abnormalities requiring early intervention and management, supporting the technology's use as a screening tool. CONCLUSIONS: This investigation suggests that the use of smartphone-based digital ophthalmoscopes can be more effectively applied as a screening tool by capturing 30-second videos compared with still images alone. This novel assessment of an emerging technology in the field of ophthalmology may better equip further research as smartphone camera technology advances. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/52650.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.026 | 0.025 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.004 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.014 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".