Abstract P400: Screening for Hypertension Using Retinal Vascular Calibre in Ultra-Widefield Fundus Imaging
Bibliographic record
Abstract
Fundus images from the left eyes of 440 subjects aged 50-59 years enrolled in the Northern Ireland Cohort of Longitudinal Ageing were analyzed. Subjects were categorized as normotensive or hypertensive, according to thresholds on systolic/diastolic blood pressure measurement (140/90 mm Hg) averaged over two sitting measurements in a clinical setting. A fully automatic system to analyze each image used conventional and deep neural network machine learning techniques to locate retinal landmarks and detect, classify and measure retinal vessels. From this data, a measure of the arteriolar-venular ratio (AVR) in the peripheral retina was calculated. Semi-automatic analysis was also performed. Results are presented in Table 1. Subjects had mean age of 54.6 ± 2.9 years; 56.1% (247 of 440) females, with 34.3% (151 of 440) subjects categorized as hypertensive. Narrower arterioles and smaller AVR were observed in subjects with hypertension. This was also observed in fully-automated analysis, however 4% (17 of 440) subjects failed to be processed by the system. In fully-automated analysis the area under a receiver operator characteristic curve of AVR for hypertensive status was 0.69 (95% CI, 0.63 to 0.74). Table 1 - Results for semi-automated and automated analysis of retinal vessel parameters. *p<0.005 Automated measurement of AVR in ultra-widefield fundus imaging was associated with hypertension. With further development, such as evaluation against diagnosis of hypertension obtained from ambulatory blood pressure monitoring clinics, this system could become a test for undiagnosed hypertension in people attending routine eye health check-ups.
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 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 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".