The muranga teleophthalmology study: A comparison of virtual (teleretina) assessment with in-person clinical examination to diagnose diabetic retinopathy and age-related macular degeneration in kenya
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
PURPOSE: This study compares a web-based teleophthalmology assessment with a clinical slit lamp examination to screen for diabetic retinopathy (DR) and age-related macular degeneration (AMD) among diabetic patients in a rural East African district. METHODS: Six hundred and twelve eyes from 306 diabetic patients underwent both a clinical slit lamp examination and a teleretina (TR) assessment by an experienced ophthalmologist. Both assessments were compared for any DR and AMD using the early treatment diabetic retinopathy study and age-related eye disease study grading scales, respectively. RESULTS: Of the 612 TR assessment photos, 74 (12%) were deemed ungradable due to media opacities, poor patient cooperation, or unsatisfactory photographs. The ability to detect DR and AMD showed a fair agreement (kappa statistic 0.27 and 0.23, respectively) between the TR and clinical slit lamp examination. Relative to a clinical slit lamp evaluation, a positive TR diagnosis carried a 75.0% positive predictive value when diagnosing DR and a 27.3% positive predictive value when diagnosing AMD. A negative TR diagnosis carried a 97.2% negative predictive value for the diagnosis of DR and a 98.1% negative predictive value for the diagnosis of AMD. CONCLUSION: When comparing TR assessments to clinical slit lamp examinations to diagnose DR and AMD, there was a fair agreement. Although further validation is needed, the TR approach provides a promising method to diagnose DR and AMD, two major causes of ocular impairment worldwide.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it