Illuminating Bovine Cardiovascular Risks: A Hybrid Deep Learning and Biomarker Framework Using Retinal Imaging
Bibliographic record
Abstract
Bovine cardiovascular disease (CVD) represents a critical challenge to global agriculture, threatening animal welfare and economic sustainability. Current diagnostic methods, such as electrocardiography and echocardiography, are invasive, costly, and impractical for routine herdlevel monitoring, limiting early intervention. Retinal imaging, proven transformative in human medicine for non-invasive detection of systemic diseases, remains underexplored in veterinary diagnostics due to anatomical differences and challenges in interpreting AI-driven models. Here, we present a pioneering, hybrid artificial intelligence (AI) approach combining bovine-specific retinal vessel segmentation and clinically interpretable vascular biomarkers for accurate early detection of CVD in cattle. Leveraging a portable fundus camera, we developed and validated the first bovinetailored U-Net model achieving an 89.34% Dice coefficient in retinal vessel segmentation, overcoming significant anatomical disparities. From segmented retinal images, we systematically extracted five critical biomarkers: vessel density, bifurcation angle, vessel tortuosity, branching density, and fractal dimension. Integrating these interpretable biomarkers with deep learning features derived from ResNet18 in a hybrid multilayer perceptron classifier markedly enhanced diagnostic accuracy, reaching 97.32%, with sensitivity of 98.2%. Notably, increased vessel tortuosity emerged as a pivotal and clinically relevant biomarker, corroborating findings from human cardiovascular research. Our framework uniquely addresses the interpretability gap of medical AI, providing veterinarians with transparent, biologically meaningful diagnostic parameters. This scalable, non-invasive diagnostic tool enables proactive herd management, earlier interventions, reduced livestock mortality, and improved agricultural productivity, laying a robust foundation for broader applications of AI-driven diagnostics in ethical and sustainable livestock management.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.000 | 0.003 |
| 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".