Abstract 11594: Deep Learning of the Retina Enables Phenome- and Genome- Wide Analyses of the Microvasculature
Bibliographic record
Abstract
Introduction: The retinal fundus is a window for non-invasive assessment of the microvasculature. However, the range of phenotypes and inherited genetic variants associated with the retinal microvasculature remain unknown. Hypothesis: Deep learning of retinal fundus images enables large-scale quantification of vascular indices and an unbiased assessment of phenotypes and genetic variants linked to the microvasculature. Methods: We utilized 97,895 retinal fundus images from 54,813 UK Biobank participants (ages 40-70y, 55% female). Using convolutional neural networks to segment vessels, we calculated vascular branching complexity using fractal dimension (FD), and vascular density, and associated these indices with 1,100 incident ICD-based conditions (median 10y follow-up) and 88 quantitative traits, adjusting for age, sex, smoking status, and ethnicity. Genome-wide association study (GWAS) among 38,932 unrelated individuals was performed. Results: Low retinal vascular FD and density were significantly associated with increased risk of incident hypertension, congestive heart failure, renal failure, type 2 diabetes, sleep apnea, anemia, and multiple ocular conditions. Low retinal vascular FD and density were also linked to quantitative traits including elevated blood pressure, anemia indices, abnormal pulmonary function tests, measures of metabolic disease (high HbA1c, % body fat, BMI), and ocular traits (decreased visual acuity and increased intraocular pressure). GWAS of vascular FD and density identified loci enriched among pathways linked to angiogenesis (VEGF, PDGFR, angiopoietin, and WNT signaling pathways), and inflammation (interleukin, cytokine signaling). Conclusions: Through phenotypic and genotypic analyses, our study showed that the retinal vasculature may serve as a biomarker for future cardiometabolic and ocular disease, and provided insights on genes and biological pathways influencing microvascular indices.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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".